{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Header 1\n",
    "\n",
    "## Header 2\n",
    "\n",
    "### Header 3.1"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "metadata": {}
   },
   "outputs": [],
   "source": [
    "import pandas as pd\n",
    "import numpy as np\n",
    "import seaborn as sns\n",
    "import matplotlib.pyplot as plt\n",
    "import matplotlib as mpl\n",
    "import mplcatppuccin\n",
    "import plotly.express as px\n",
    "import plotly.graph_objects as go\n",
    "from plotly.subplots import make_subplots\n",
    "import plotly.figure_factory as ff\n",
    "import warnings\n",
    "import plotly.io as pio\n",
    "\n",
    "warnings.filterwarnings('ignore')\n",
    "\n",
    "pio.renderers.default = 'notebook_connected'\n",
    "pio.templates.default = 'plotly_dark'\n",
    "\n",
    "\n",
    "%matplotlib inline\n",
    "%config InlineBackend.figure_format = 'retina'\n",
    "pd.set_option('display.max_columns', None)\n",
    "pd.set_option('display.precision', 2)\n",
    "pd.set_option('display.colheader_justify', 'left')\n",
    "\n",
    "mpl.rc(\n",
    "    'figure',\n",
    "    autolayout=True,\n",
    "    titlesize=18\n",
    ")\n",
    "\n",
    "mpl.style.use(['ggplot', 'mocha'])\n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Header 3.2\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "metadata": {}
   },
   "outputs": [],
   "source": [
    "df = pd.read_csv(\n",
    "    \"data.csv\",\n",
    "    parse_dates=[\"release_date\"],\n",
    ")\n",
    "df.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "metadata": {}
   },
   "outputs": [],
   "source": [
    "map_key = {\n",
    "    0: \"C\",\n",
    "    1: \"C#\",\n",
    "    2: \"D\",\n",
    "    3: \"D#\",\n",
    "    4: \"E\",\n",
    "    5: \"F\",\n",
    "    6: \"F#\",\n",
    "    7: \"G\",\n",
    "    8: \"G#\",\n",
    "    9: \"A\",\n",
    "    10: \"A#\",\n",
    "    11: \"B\",\n",
    "}\n",
    "\n",
    "map_mode = {1: \"Major\", 0: \"Minor\"}\n",
    "\n",
    "df[\"mode\"] = df[\"mode\"].map(map_mode)\n",
    "df[\"key\"] = df[\"key\"].map(map_key)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "1\n"
     ]
    }
   ],
   "source": [
    "print(1)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "metadata": {}
   },
   "outputs": [],
   "source": [
    "check_dups = df[[\"artists\", \"name\"]]\n",
    "dups = check_dups[check_dups.duplicated()].index"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "metadata": {}
   },
   "outputs": [],
   "source": [
    "print(\"Before dropping duplicated:\", df.shape)\n",
    "df = df.drop(dups)\n",
    "print(\"After dropping duplicated:\", df.shape)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Header 1.3\n",
    "\n",
    "## Header 2.3\n",
    "\n",
    "### Header 3.5"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "metadata": {}
   },
   "outputs": [],
   "source": [
    "df[\"duration_ms\"] = df[\"duration_ms\"] / 60_000\n",
    "df = df.rename(columns={\"duration_ms\": \"duration_min\"})\n",
    "df.head()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Header 1.4\n",
    "\n",
    "## Header 2.4\n",
    "\n",
    "### Header 3.5"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "metadata": {}
   },
   "outputs": [],
   "source": [
    "df = df.drop([\"release_date\", \"id\"], axis=1)\n",
    "df.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "metadata": {}
   },
   "outputs": [],
   "source": [
    "def fun_subplots_plotly(df, col):\n",
    "\n",
    "    mean_val = df[col].mean()\n",
    "    median_val = df[col].median()\n",
    "    fig = make_subplots(rows=1, cols=2, column_widths=[0.75, 0.25])\n",
    "\n",
    "    fig.add_trace(\n",
    "        go.Histogram(\n",
    "            x=df[col], name=f\"Histogram {col}\", marker={\"color\": \"#EBA0AC\"}, nbinsx=50\n",
    "        ),\n",
    "        row=1,\n",
    "        col=1,\n",
    "    )\n",
    "\n",
    "    fig.add_shape(\n",
    "        type=\"line\",\n",
    "        xref=\"paper\",\n",
    "        yref=\"y\",\n",
    "        x0=-1,\n",
    "        x1=1,\n",
    "        y0=mean_val,\n",
    "        y1=mean_val,\n",
    "        row=1,\n",
    "        col=2,\n",
    "        line={\"color\": \"#A6E3A1\", \"width\": 3, \"dash\": \"dot\"},\n",
    "    )\n",
    "\n",
    "    fig.add_shape(\n",
    "        type=\"line\",\n",
    "        xref=\"paper\",\n",
    "        yref=\"y\",\n",
    "        x0=-1,\n",
    "        x1=1,\n",
    "        y0=median_val,\n",
    "        y1=median_val,\n",
    "        row=1,\n",
    "        col=2,\n",
    "        line={\"color\": \"#CBA6F7\", \"width\": 3, \"dash\": \"dot\"},\n",
    "    )\n",
    "\n",
    "    fig.add_annotation(\n",
    "        xref=\"paper\",\n",
    "        x=-0.7,\n",
    "        y=mean_val,\n",
    "        showarrow=True,\n",
    "        arrowhead=2,\n",
    "        text=f\"Mean = {mean_val:.2f}\",\n",
    "        row=1,\n",
    "        col=2,\n",
    "    )\n",
    "\n",
    "    fig.add_annotation(\n",
    "        xref=\"paper\",\n",
    "        x=0.7,\n",
    "        y=median_val,\n",
    "        showarrow=True,\n",
    "        arrowhead=2,\n",
    "        text=f\"Median = {median_val:.2f}\",\n",
    "        row=1,\n",
    "        col=2,\n",
    "    )\n",
    "\n",
    "    fig.add_trace(\n",
    "        go.Box(y=df[col], name=f\"Boxplot {col}\", marker={\"color\": \"#F9E2AF\"}),\n",
    "        row=1,\n",
    "        col=2,\n",
    "    )\n",
    "\n",
    "    fig.update_layout(\n",
    "        title={\"text\": f\"Distribution Plot {col}\", \"font\": {\"size\": 24}},\n",
    "        legend={\n",
    "            \"orientation\": \"h\",\n",
    "            \"yanchor\": \"bottom\",\n",
    "            \"y\": 1.02,\n",
    "            \"xanchor\": \"right\",\n",
    "            \"x\": 1,\n",
    "        },\n",
    "    )\n",
    "    fig.update_yaxes(title_text=\"Count\", row=1, col=1)\n",
    "    fig.update_yaxes(title_text=f\"{col}\", row=1, col=2)\n",
    "    fig.update_xaxes(title_text=f\"{col}\", row=1, col=1)\n",
    "    fig.update_xaxes(title_text=\"\", row=1, col=2)\n",
    "    fig.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "metadata": {}
   },
   "outputs": [],
   "source": [
    "music_vals = [\n",
    "    \"valence\",\n",
    "    \"acousticness\",\n",
    "    \"danceability\",\n",
    "    \"duration_min\",\n",
    "    \"energy\",\n",
    "    \"instrumentalness\",\n",
    "    \"liveness\",\n",
    "    \"loudness\",\n",
    "    \"popularity\",\n",
    "    \"speechiness\",\n",
    "    \"tempo\",\n",
    "]\n",
    "\n",
    "for col in music_vals:\n",
    "    fun_subplots_plotly(df, col)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Header 1.2\n",
    "\n",
    "## Header 2.2\n",
    "\n",
    "### Header 3.4"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Header 1\n",
    "\n",
    "## Header 2\n",
    "\n",
    "### Header 3.1"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Header 1\n",
    "\n",
    "## Header 2\n",
    "\n",
    "### Header 3.1"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {
    "metadata": {}
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "1\n"
     ]
    }
   ],
   "source": [
    "print(1)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Header 3.2\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "df = pd.read_csv(\n",
    "    \"data.csv\",\n",
    "    parse_dates=[\"release_date\"],\n",
    ")\n",
    "\n",
    "df.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "map_key = {\n",
    "    0: \"C\",\n",
    "    1: \"C#\",\n",
    "    2: \"D\",\n",
    "    3: \"D#\",\n",
    "    4: \"E\",\n",
    "    5: \"F\",\n",
    "    6: \"F#\",\n",
    "    7: \"G\",\n",
    "    8: \"G#\",\n",
    "    9: \"A\",\n",
    "    10: \"A#\",\n",
    "    11: \"B\",\n",
    "}\n",
    "\n",
    "map_mode = {1: \"Major\", 0: \"Minor\"}\n",
    "\n",
    "df[\"mode\"] = df[\"mode\"].map(map_mode)\n",
    "df[\"key\"] = df[\"key\"].map(map_key)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "check_dups = df[[\"artists\", \"name\"]]\n",
    "dups = check_dups[check_dups.duplicated()].index"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "print(\"Before dropping duplicated:\", df.shape)\n",
    "df = df.drop(dups)\n",
    "print(\"After dropping duplicated:\", df.shape)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Header 1.3\n",
    "\n",
    "## Header 2.3\n",
    "\n",
    "### Header 3.5"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "df[\"duration_ms\"] = df[\"duration_ms\"] / 60_000\n",
    "df = df.rename(columns={\"duration_ms\": \"duration_min\"})\n",
    "df.head()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Header 1.4\n",
    "\n",
    "## Header 2.4\n",
    "\n",
    "### Header 3.5"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "df = df.drop([\"release_date\", \"id\"], axis=1)\n",
    "df.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "def fun_subplots_plotly(df, col):\n",
    "\n",
    "    mean_val = df[col].mean()\n",
    "    median_val = df[col].median()\n",
    "    fig = make_subplots(rows=1, cols=2, column_widths=[0.75, 0.25])\n",
    "\n",
    "    fig.add_trace(\n",
    "        go.Histogram(\n",
    "            x=df[col], name=f\"Histogram {col}\", marker={\"color\": \"#EBA0AC\"}, nbinsx=50\n",
    "        ),\n",
    "        row=1,\n",
    "        col=1,\n",
    "    )\n",
    "\n",
    "    fig.add_shape(\n",
    "        type=\"line\",\n",
    "        xref=\"paper\",\n",
    "        yref=\"y\",\n",
    "        x0=-1,\n",
    "        x1=1,\n",
    "        y0=mean_val,\n",
    "        y1=mean_val,\n",
    "        row=1,\n",
    "        col=2,\n",
    "        line={\"color\": \"#A6E3A1\", \"width\": 3, \"dash\": \"dot\"},\n",
    "    )\n",
    "\n",
    "    fig.add_shape(\n",
    "        type=\"line\",\n",
    "        xref=\"paper\",\n",
    "        yref=\"y\",\n",
    "        x0=-1,\n",
    "        x1=1,\n",
    "        y0=median_val,\n",
    "        y1=median_val,\n",
    "        row=1,\n",
    "        col=2,\n",
    "        line={\"color\": \"#CBA6F7\", \"width\": 3, \"dash\": \"dot\"},\n",
    "    )\n",
    "\n",
    "    fig.add_annotation(\n",
    "        xref=\"paper\",\n",
    "        x=-0.7,\n",
    "        y=mean_val,\n",
    "        showarrow=True,\n",
    "        arrowhead=2,\n",
    "        text=f\"Mean = {mean_val:.2f}\",\n",
    "        row=1,\n",
    "        col=2,\n",
    "    )\n",
    "\n",
    "    fig.add_annotation(\n",
    "        xref=\"paper\",\n",
    "        x=0.7,\n",
    "        y=median_val,\n",
    "        showarrow=True,\n",
    "        arrowhead=2,\n",
    "        text=f\"Median = {median_val:.2f}\",\n",
    "        row=1,\n",
    "        col=2,\n",
    "    )\n",
    "\n",
    "    fig.add_trace(\n",
    "        go.Box(y=df[col], name=f\"Boxplot {col}\", marker={\"color\": \"#F9E2AF\"}),\n",
    "        row=1,\n",
    "        col=2,\n",
    "    )\n",
    "\n",
    "    fig.update_layout(\n",
    "        title={\"text\": f\"Distribution Plot {col}\", \"font\": {\"size\": 24}},\n",
    "        legend={\n",
    "            \"orientation\": \"h\",\n",
    "            \"yanchor\": \"bottom\",\n",
    "            \"y\": 1.02,\n",
    "            \"xanchor\": \"right\",\n",
    "            \"x\": 1,\n",
    "        },\n",
    "    )\n",
    "    fig.update_yaxes(title_text=\"Count\", row=1, col=1)\n",
    "    fig.update_yaxes(title_text=f\"{col}\", row=1, col=2)\n",
    "    fig.update_xaxes(title_text=f\"{col}\", row=1, col=1)\n",
    "    fig.update_xaxes(title_text=\"\", row=1, col=2)\n",
    "    fig.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "music_vals = [\n",
    "    \"valence\",\n",
    "    \"acousticness\",\n",
    "    \"danceability\",\n",
    "    \"duration_min\",\n",
    "    \"energy\",\n",
    "    \"instrumentalness\",\n",
    "    \"liveness\",\n",
    "    \"loudness\",\n",
    "    \"popularity\",\n",
    "    \"speechiness\",\n",
    "    \"tempo\",\n",
    "]\n",
    "\n",
    "for col in music_vals:\n",
    "    fun_subplots_plotly(df, col)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Header 1.2\n",
    "\n",
    "## Header 2.2\n",
    "\n",
    "### Header 3.4"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Header 1\n",
    "\n",
    "## Header 2\n",
    "\n",
    "### Header 3.1"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Header 1\n",
    "\n",
    "## Header 2\n",
    "\n",
    "### Header 3.1"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Header 1\n",
    "\n",
    "## Header 2\n",
    "\n",
    "### Header 3.1"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Header 1\n",
    "\n",
    "## Header 2\n",
    "\n",
    "### Header 3.1"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "import pandas as pd\n",
    "import numpy as np\n",
    "import seaborn as sns\n",
    "import matplotlib.pyplot as plt\n",
    "import matplotlib as mpl\n",
    "import mplcatppuccin\n",
    "import plotly.express as px\n",
    "import plotly.graph_objects as go\n",
    "from plotly.subplots import make_subplots\n",
    "import plotly.figure_factory as ff\n",
    "import warnings\n",
    "import plotly.io as pio\n",
    "\n",
    "warnings.filterwarnings('ignore')\n",
    "\n",
    "pio.renderers.default = 'notebook_connected'\n",
    "pio.templates.default = 'plotly_dark'\n",
    "\n",
    "\n",
    "%matplotlib inline\n",
    "%config InlineBackend.figure_format = 'retina'\n",
    "pd.set_option('display.max_columns', None)\n",
    "pd.set_option('display.precision', 2)\n",
    "pd.set_option('display.colheader_justify', 'left')\n",
    "\n",
    "mpl.rc(\n",
    "    'figure',\n",
    "    autolayout=True,\n",
    "    titlesize=18\n",
    ")\n",
    "\n",
    "mpl.style.use(['ggplot', 'mocha'])\n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Header 3.2\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "df = pd.read_csv(\n",
    "    \"data.csv\",\n",
    "    parse_dates=[\"release_date\"],\n",
    ")\n",
    "df.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "map_key = {\n",
    "    0: \"C\",\n",
    "    1: \"C#\",\n",
    "    2: \"D\",\n",
    "    3: \"D#\",\n",
    "    4: \"E\",\n",
    "    5: \"F\",\n",
    "    6: \"F#\",\n",
    "    7: \"G\",\n",
    "    8: \"G#\",\n",
    "    9: \"A\",\n",
    "    10: \"A#\",\n",
    "    11: \"B\",\n",
    "}\n",
    "\n",
    "map_mode = {1: \"Major\", 0: \"Minor\"}\n",
    "\n",
    "df[\"mode\"] = df[\"mode\"].map(map_mode)\n",
    "df[\"key\"] = df[\"key\"].map(map_key)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "check_dups = df[[\"artists\", \"name\"]]\n",
    "dups = check_dups[check_dups.duplicated()].index"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "print(\"Before dropping duplicated:\", df.shape)\n",
    "df = df.drop(dups)\n",
    "print(\"After dropping duplicated:\", df.shape)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Header 1.3\n",
    "\n",
    "## Header 2.3\n",
    "\n",
    "### Header 3.5"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "df[\"duration_ms\"] = df[\"duration_ms\"] / 60_000\n",
    "df = df.rename(columns={\"duration_ms\": \"duration_min\"})\n",
    "df.head()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Header 1.4\n",
    "\n",
    "## Header 2.4\n",
    "\n",
    "### Header 3.5"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "df = df.drop([\"release_date\", \"id\"], axis=1)\n",
    "df.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "def fun_subplots_plotly(df, col):\n",
    "\n",
    "    mean_val = df[col].mean()\n",
    "    median_val = df[col].median()\n",
    "    fig = make_subplots(rows=1, cols=2, column_widths=[0.75, 0.25])\n",
    "\n",
    "    fig.add_trace(\n",
    "        go.Histogram(\n",
    "            x=df[col], name=f\"Histogram {col}\", marker={\"color\": \"#EBA0AC\"}, nbinsx=50\n",
    "        ),\n",
    "        row=1,\n",
    "        col=1,\n",
    "    )\n",
    "\n",
    "    fig.add_shape(\n",
    "        type=\"line\",\n",
    "        xref=\"paper\",\n",
    "        yref=\"y\",\n",
    "        x0=-1,\n",
    "        x1=1,\n",
    "        y0=mean_val,\n",
    "        y1=mean_val,\n",
    "        row=1,\n",
    "        col=2,\n",
    "        line={\"color\": \"#A6E3A1\", \"width\": 3, \"dash\": \"dot\"},\n",
    "    )\n",
    "\n",
    "    fig.add_shape(\n",
    "        type=\"line\",\n",
    "        xref=\"paper\",\n",
    "        yref=\"y\",\n",
    "        x0=-1,\n",
    "        x1=1,\n",
    "        y0=median_val,\n",
    "        y1=median_val,\n",
    "        row=1,\n",
    "        col=2,\n",
    "        line={\"color\": \"#CBA6F7\", \"width\": 3, \"dash\": \"dot\"},\n",
    "    )\n",
    "\n",
    "    fig.add_annotation(\n",
    "        xref=\"paper\",\n",
    "        x=-0.7,\n",
    "        y=mean_val,\n",
    "        showarrow=True,\n",
    "        arrowhead=2,\n",
    "        text=f\"Mean = {mean_val:.2f}\",\n",
    "        row=1,\n",
    "        col=2,\n",
    "    )\n",
    "\n",
    "    fig.add_annotation(\n",
    "        xref=\"paper\",\n",
    "        x=0.7,\n",
    "        y=median_val,\n",
    "        showarrow=True,\n",
    "        arrowhead=2,\n",
    "        text=f\"Median = {median_val:.2f}\",\n",
    "        row=1,\n",
    "        col=2,\n",
    "    )\n",
    "\n",
    "    fig.add_trace(\n",
    "        go.Box(y=df[col], name=f\"Boxplot {col}\", marker={\"color\": \"#F9E2AF\"}),\n",
    "        row=1,\n",
    "        col=2,\n",
    "    )\n",
    "\n",
    "    fig.update_layout(\n",
    "        title={\"text\": f\"Distribution Plot {col}\", \"font\": {\"size\": 24}},\n",
    "        legend={\n",
    "            \"orientation\": \"h\",\n",
    "            \"yanchor\": \"bottom\",\n",
    "            \"y\": 1.02,\n",
    "            \"xanchor\": \"right\",\n",
    "            \"x\": 1,\n",
    "        },\n",
    "    )\n",
    "    fig.update_yaxes(title_text=\"Count\", row=1, col=1)\n",
    "    fig.update_yaxes(title_text=f\"{col}\", row=1, col=2)\n",
    "    fig.update_xaxes(title_text=f\"{col}\", row=1, col=1)\n",
    "    fig.update_xaxes(title_text=\"\", row=1, col=2)\n",
    "    fig.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "music_vals = [\n",
    "    \"valence\",\n",
    "    \"acousticness\",\n",
    "    \"danceability\",\n",
    "    \"duration_min\",\n",
    "    \"energy\",\n",
    "    \"instrumentalness\",\n",
    "    \"liveness\",\n",
    "    \"loudness\",\n",
    "    \"popularity\",\n",
    "    \"speechiness\",\n",
    "    \"tempo\",\n",
    "]\n",
    "\n",
    "for col in music_vals:\n",
    "    fun_subplots_plotly(df, col)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Header 1.2\n",
    "\n",
    "## Header 2.2\n",
    "\n",
    "### Header 3.4"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "bins = pd.IntervalIndex.from_breaks(\n",
    "    [1920, 1930, 1940, 1950, 1960, 1970, 1980, 1990, 2000, 2010, 2020]\n",
    ")\n",
    "\n",
    "df[\"decade\"] = pd.cut(df[\"year\"], bins).astype(\"str\")\n",
    "\n",
    "map_decade = {\n",
    "    \"(1920, 1930]\": \"1920s\",\n",
    "    \"(1930, 1940]\": \"1930s\",\n",
    "    \"(1940, 1950]\": \"1940s\",\n",
    "    \"(1950, 1960]\": \"1950s\",\n",
    "    \"(1960, 1970]\": \"1960s\",\n",
    "    \"(1970, 1980]\": \"1970s\",\n",
    "    \"(1980, 1990]\": \"1980s\",\n",
    "    \"(1990, 2000]\": \"1990s\",\n",
    "    \"(2000, 2010]\": \"2000s\",\n",
    "    \"(2010, 2020]\": \"2010s\",\n",
    "}\n",
    "\n",
    "df[\"decade\"] = df[\"decade\"].map(map_decade)\n",
    "\n",
    "df.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "decade_counts = (\n",
    "    df[\"decade\"].value_counts().reset_index().sort_values(by=\"decade\", ascending=True)\n",
    ")\n",
    "\n",
    "fig = px.bar(\n",
    "    data_frame=decade_counts,\n",
    "    y=\"decade\",\n",
    "    x=\"count\",\n",
    "    color=\"count\",\n",
    "    color_continuous_scale=px.colors.sequential.Sunset,\n",
    "    text_auto=True,\n",
    ")\n",
    "\n",
    "fig.update_layout(\n",
    "    title={\"text\": \"Count of songs per decade\", \"font\": {\"size\": 24}},\n",
    "    coloraxis_colorbar={\n",
    "        \"title\": \"Count\",\n",
    "        \"thicknessmode\": \"pixels\",\n",
    "        \"thickness\": 20,\n",
    "        \"lenmode\": \"pixels\",\n",
    "        \"len\": 500,\n",
    "        \"yanchor\": \"top\",\n",
    "        \"xanchor\": \"right\",\n",
    "        \"y\": 1.15,\n",
    "        \"x\": 0.95,\n",
    "        \"orientation\": \"h\",\n",
    "    },\n",
    "    margin={\"r\": 10},\n",
    ")\n",
    "\n",
    "fig.update_xaxes(title=\"Count\")\n",
    "fig.update_yaxes(title=\"Decades\")\n",
    "fig.show()\n",
    "\n",
    "del decade_counts"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "df = df.query(\"duration_min <= 5\")"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Header 1.2\n",
    "\n",
    "## Header 2.2\n",
    "\n",
    "### Header 3.4"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "decade_counts = (\n",
    "    df[\"decade\"].value_counts().reset_index().sort_values(by=\"decade\", ascending=True)\n",
    ")\n",
    "\n",
    "fig = px.bar(\n",
    "    data_frame=decade_counts,\n",
    "    y=\"decade\",\n",
    "    x=\"count\",\n",
    "    color=\"count\",\n",
    "    color_continuous_scale=px.colors.sequential.Sunset,\n",
    "    text_auto=True,\n",
    ")\n",
    "\n",
    "fig.update_layout(\n",
    "    title={\"text\": \"Count of songs per decade (< 5min)\", \"font\": {\"size\": 24}},\n",
    "    coloraxis_colorbar={\n",
    "        \"title\": \"Count\",\n",
    "        \"thicknessmode\": \"pixels\",\n",
    "        \"thickness\": 20,\n",
    "        \"lenmode\": \"pixels\",\n",
    "        \"len\": 500,\n",
    "        \"yanchor\": \"top\",\n",
    "        \"xanchor\": \"right\",\n",
    "        \"y\": 1.15,\n",
    "        \"x\": 0.95,\n",
    "        \"orientation\": \"h\",\n",
    "    },\n",
    "    margin={\"r\": 10},\n",
    ")\n",
    "\n",
    "fig.update_xaxes(title=\"Count\")\n",
    "fig.update_yaxes(title=\"Decades\")\n",
    "fig.show()\n",
    "\n",
    "del decade_counts"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "cols = [\n",
    "    \"valence\",\n",
    "    \"acousticness\",\n",
    "    \"danceability\",\n",
    "    \"duration_min\",\n",
    "    \"energy\",\n",
    "    \"instrumentalness\",\n",
    "    \"liveness\",\n",
    "    \"loudness\",\n",
    "    \"popularity\",\n",
    "    \"speechiness\",\n",
    "    \"tempo\",\n",
    "]\n",
    "for col in cols:\n",
    "    fig = px.histogram(\n",
    "        data_frame=df,\n",
    "        x=col,\n",
    "        color=\"decade\",\n",
    "        color_discrete_sequence=px.colors.qualitative.Light24,\n",
    "    )\n",
    "    fig.update_traces(opacity=0.7)\n",
    "    fig.update_layout(\n",
    "        bargap=0.1,\n",
    "        bargroupgap=0.05,\n",
    "        barmode=\"stack\",\n",
    "        title={\"text\": f\"Histogram of {col} per decade\", \"font\": {\"size\": 24}},\n",
    "        legend={\"title\": \"Decade\"},\n",
    "    )\n",
    "    fig.update_yaxes(title=\"Count\")\n",
    "    fig.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "decade_mean = df.groupby(\"decade\")[cols].mean()\n",
    "\n",
    "fig = make_subplots(\n",
    "    rows=4,\n",
    "    cols=3,\n",
    "    subplot_titles=(\n",
    "        decade_mean.columns[0],\n",
    "        decade_mean.columns[1],\n",
    "        decade_mean.columns[2],\n",
    "        decade_mean.columns[3],\n",
    "        decade_mean.columns[4],\n",
    "        decade_mean.columns[5],\n",
    "        decade_mean.columns[6],\n",
    "        decade_mean.columns[7],\n",
    "        decade_mean.columns[8],\n",
    "        decade_mean.columns[9],\n",
    "        decade_mean.columns[10],\n",
    "    ),\n",
    "    vertical_spacing=0.1,\n",
    ")\n",
    "\n",
    "fig.add_trace(\n",
    "    go.Bar(\n",
    "        y=decade_mean.index,\n",
    "        x=decade_mean.iloc[:, 0],\n",
    "        name=decade_mean.columns[0],\n",
    "        orientation=\"h\",\n",
    "    ),\n",
    "    row=1,\n",
    "    col=1,\n",
    ")\n",
    "\n",
    "fig.add_trace(\n",
    "    go.Bar(\n",
    "        y=decade_mean.index,\n",
    "        x=decade_mean.iloc[:, 1],\n",
    "        name=decade_mean.columns[1],\n",
    "        orientation=\"h\",\n",
    "    ),\n",
    "    row=1,\n",
    "    col=2,\n",
    ")\n",
    "\n",
    "fig.add_trace(\n",
    "    go.Bar(\n",
    "        y=decade_mean.index,\n",
    "        x=decade_mean.iloc[:, 2],\n",
    "        name=decade_mean.columns[2],\n",
    "        orientation=\"h\",\n",
    "    ),\n",
    "    row=1,\n",
    "    col=3,\n",
    ")\n",
    "\n",
    "fig.add_trace(\n",
    "    go.Bar(\n",
    "        y=decade_mean.index,\n",
    "        x=decade_mean.iloc[:, 3],\n",
    "        name=decade_mean.columns[3],\n",
    "        orientation=\"h\",\n",
    "    ),\n",
    "    row=2,\n",
    "    col=1,\n",
    ")\n",
    "\n",
    "fig.add_trace(\n",
    "    go.Bar(\n",
    "        y=decade_mean.index,\n",
    "        x=decade_mean.iloc[:, 4],\n",
    "        name=decade_mean.columns[4],\n",
    "        orientation=\"h\",\n",
    "    ),\n",
    "    row=2,\n",
    "    col=2,\n",
    ")\n",
    "\n",
    "fig.add_trace(\n",
    "    go.Bar(\n",
    "        y=decade_mean.index,\n",
    "        x=decade_mean.iloc[:, 5],\n",
    "        name=decade_mean.columns[5],\n",
    "        orientation=\"h\",\n",
    "    ),\n",
    "    row=2,\n",
    "    col=3,\n",
    ")\n",
    "\n",
    "fig.add_trace(\n",
    "    go.Bar(\n",
    "        y=decade_mean.index,\n",
    "        x=decade_mean.iloc[:, 6],\n",
    "        name=decade_mean.columns[6],\n",
    "        orientation=\"h\",\n",
    "    ),\n",
    "    row=3,\n",
    "    col=1,\n",
    ")\n",
    "\n",
    "fig.add_trace(\n",
    "    go.Bar(\n",
    "        y=decade_mean.index,\n",
    "        x=decade_mean.iloc[:, 7],\n",
    "        name=decade_mean.columns[7],\n",
    "        orientation=\"h\",\n",
    "    ),\n",
    "    row=3,\n",
    "    col=2,\n",
    ")\n",
    "\n",
    "fig.add_trace(\n",
    "    go.Bar(\n",
    "        y=decade_mean.index,\n",
    "        x=decade_mean.iloc[:, 8],\n",
    "        name=decade_mean.columns[8],\n",
    "        orientation=\"h\",\n",
    "    ),\n",
    "    row=3,\n",
    "    col=3,\n",
    ")\n",
    "\n",
    "fig.add_trace(\n",
    "    go.Bar(\n",
    "        y=decade_mean.index,\n",
    "        x=decade_mean.iloc[:, 9],\n",
    "        name=decade_mean.columns[9],\n",
    "        orientation=\"h\",\n",
    "    ),\n",
    "    row=4,\n",
    "    col=1,\n",
    ")\n",
    "\n",
    "fig.add_trace(\n",
    "    go.Bar(\n",
    "        y=decade_mean.index,\n",
    "        x=decade_mean.iloc[:, 10],\n",
    "        name=decade_mean.columns[10],\n",
    "        orientation=\"h\",\n",
    "    ),\n",
    "    row=4,\n",
    "    col=2,\n",
    ")\n",
    "\n",
    "fig.update_layout(\n",
    "    title={\"text\": \"Mean Musical Values per Decade\", \"font\": {\"size\": 22}},\n",
    "    legend={\n",
    "        \"orientation\": \"v\",\n",
    "        \"yanchor\": \"top\",\n",
    "        \"y\": 0.2,\n",
    "        \"xanchor\": \"right\",\n",
    "        \"x\": 0.9,\n",
    "    },\n",
    "    margin={\"b\": 10, \"r\": 10},\n",
    "    height=980,\n",
    ")\n",
    "\n",
    "fig.show()\n",
    "\n",
    "del decade_mean"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "decade_median = df.groupby(\"decade\")[cols].median()\n",
    "\n",
    "fig = make_subplots(\n",
    "    rows=4,\n",
    "    cols=3,\n",
    "    subplot_titles=(\n",
    "        decade_median.columns[0],\n",
    "        decade_median.columns[1],\n",
    "        decade_median.columns[2],\n",
    "        decade_median.columns[3],\n",
    "        decade_median.columns[4],\n",
    "        decade_median.columns[5],\n",
    "        decade_median.columns[6],\n",
    "        decade_median.columns[7],\n",
    "        decade_median.columns[8],\n",
    "        decade_median.columns[9],\n",
    "        decade_median.columns[10],\n",
    "    ),\n",
    "    vertical_spacing=0.1,\n",
    ")\n",
    "\n",
    "fig.add_trace(\n",
    "    go.Bar(\n",
    "        y=decade_median.index,\n",
    "        x=decade_median.iloc[:, 0],\n",
    "        name=decade_median.columns[0],\n",
    "        orientation=\"h\",\n",
    "    ),\n",
    "    row=1,\n",
    "    col=1,\n",
    ")\n",
    "\n",
    "fig.add_trace(\n",
    "    go.Bar(\n",
    "        y=decade_median.index,\n",
    "        x=decade_median.iloc[:, 1],\n",
    "        name=decade_median.columns[1],\n",
    "        orientation=\"h\",\n",
    "    ),\n",
    "    row=1,\n",
    "    col=2,\n",
    ")\n",
    "\n",
    "fig.add_trace(\n",
    "    go.Bar(\n",
    "        y=decade_median.index,\n",
    "        x=decade_median.iloc[:, 2],\n",
    "        name=decade_median.columns[2],\n",
    "        orientation=\"h\",\n",
    "    ),\n",
    "    row=1,\n",
    "    col=3,\n",
    ")\n",
    "\n",
    "fig.add_trace(\n",
    "    go.Bar(\n",
    "        y=decade_median.index,\n",
    "        x=decade_median.iloc[:, 3],\n",
    "        name=decade_median.columns[3],\n",
    "        orientation=\"h\",\n",
    "    ),\n",
    "    row=2,\n",
    "    col=1,\n",
    ")\n",
    "\n",
    "fig.add_trace(\n",
    "    go.Bar(\n",
    "        y=decade_median.index,\n",
    "        x=decade_median.iloc[:, 4],\n",
    "        name=decade_median.columns[4],\n",
    "        orientation=\"h\",\n",
    "    ),\n",
    "    row=2,\n",
    "    col=2,\n",
    ")\n",
    "\n",
    "fig.add_trace(\n",
    "    go.Bar(\n",
    "        y=decade_median.index,\n",
    "        x=decade_median.iloc[:, 5],\n",
    "        name=decade_median.columns[5],\n",
    "        orientation=\"h\",\n",
    "    ),\n",
    "    row=2,\n",
    "    col=3,\n",
    ")\n",
    "\n",
    "fig.add_trace(\n",
    "    go.Bar(\n",
    "        y=decade_median.index,\n",
    "        x=decade_median.iloc[:, 6],\n",
    "        name=decade_median.columns[6],\n",
    "        orientation=\"h\",\n",
    "    ),\n",
    "    row=3,\n",
    "    col=1,\n",
    ")\n",
    "\n",
    "fig.add_trace(\n",
    "    go.Bar(\n",
    "        y=decade_median.index,\n",
    "        x=decade_median.iloc[:, 7],\n",
    "        name=decade_median.columns[7],\n",
    "        orientation=\"h\",\n",
    "    ),\n",
    "    row=3,\n",
    "    col=2,\n",
    ")\n",
    "\n",
    "fig.add_trace(\n",
    "    go.Bar(\n",
    "        y=decade_median.index,\n",
    "        x=decade_median.iloc[:, 8],\n",
    "        name=decade_median.columns[8],\n",
    "        orientation=\"h\",\n",
    "    ),\n",
    "    row=3,\n",
    "    col=3,\n",
    ")\n",
    "\n",
    "fig.add_trace(\n",
    "    go.Bar(\n",
    "        y=decade_median.index,\n",
    "        x=decade_median.iloc[:, 9],\n",
    "        name=decade_median.columns[9],\n",
    "        orientation=\"h\",\n",
    "    ),\n",
    "    row=4,\n",
    "    col=1,\n",
    ")\n",
    "\n",
    "fig.add_trace(\n",
    "    go.Bar(\n",
    "        y=decade_median.index,\n",
    "        x=decade_median.iloc[:, 10],\n",
    "        name=decade_median.columns[10],\n",
    "        orientation=\"h\",\n",
    "    ),\n",
    "    row=4,\n",
    "    col=2,\n",
    ")\n",
    "\n",
    "fig.update_layout(\n",
    "    title={\"text\": \"Median Musical Values per Decade\", \"font\": {\"size\": 22}},\n",
    "    legend={\n",
    "        \"orientation\": \"v\",\n",
    "        \"yanchor\": \"top\",\n",
    "        \"y\": 0.2,\n",
    "        \"xanchor\": \"right\",\n",
    "        \"x\": 0.9,\n",
    "    },\n",
    "    margin={\"b\": 10, \"r\": 10},\n",
    "    height=980,\n",
    ")\n",
    "\n",
    "fig.show()\n",
    "\n",
    "del decade_median"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "explicit_count = (\n",
    "    df.groupby([\"decade\", \"explicit\"], as_index=False)[\"year\"]\n",
    "    .count()\n",
    "    .rename(columns={\"year\": \"count\"})\n",
    ")\n",
    "key_count = (\n",
    "    df.groupby([\"decade\", \"key\"], as_index=False)[\"year\"]\n",
    "    .count()\n",
    "    .rename(columns={\"year\": \"count\"})\n",
    ")\n",
    "mode_count = (\n",
    "    df.groupby([\"decade\", \"mode\"], as_index=False)[\"year\"]\n",
    "    .count()\n",
    "    .rename(columns={\"year\": \"count\"})\n",
    ")\n",
    "\n",
    "fig = px.histogram(\n",
    "    data_frame=explicit_count,\n",
    "    x=\"decade\",\n",
    "    y=\"count\",\n",
    "    color=\"explicit\",\n",
    "    histfunc=\"sum\",\n",
    "    color_discrete_sequence=px.colors.qualitative.Pastel,\n",
    "    text_auto=True,\n",
    ")\n",
    "fig.update_layout(\n",
    "    title={\"text\": \"Explicit Count per Decade\", \"font\": {\"size\": 24}},\n",
    "    bargap=0.2,\n",
    "    bargroupgap=0.1,\n",
    "    barmode=\"group\",\n",
    "    xaxis_title=\"Decade\",\n",
    "    yaxis_title=\"Count\",\n",
    ")\n",
    "fig.show()\n",
    "\n",
    "fig = px.histogram(\n",
    "    data_frame=mode_count,\n",
    "    x=\"decade\",\n",
    "    y=\"count\",\n",
    "    color=\"mode\",\n",
    "    histfunc=\"sum\",\n",
    "    color_discrete_sequence=px.colors.qualitative.Pastel,\n",
    "    text_auto=True,\n",
    ")\n",
    "fig.update_layout(\n",
    "    title={\"text\": \"Mode Count per Decade\", \"font\": {\"size\": 24}},\n",
    "    bargap=0.2,\n",
    "    bargroupgap=0.1,\n",
    "    barmode=\"group\",\n",
    "    xaxis_title=\"Decade\",\n",
    "    yaxis_title=\"Count\",\n",
    ")\n",
    "fig.show()\n",
    "\n",
    "fig = px.histogram(\n",
    "    data_frame=key_count,\n",
    "    x=\"decade\",\n",
    "    y=\"count\",\n",
    "    color=\"key\",\n",
    "    histfunc=\"sum\",\n",
    "    color_discrete_sequence=px.colors.qualitative.Pastel,\n",
    "    text_auto=True,\n",
    ")\n",
    "fig.update_layout(\n",
    "    title={\"text\": \"Key Count per Decade\", \"font\": {\"size\": 24}},\n",
    "    bargap=0.2,\n",
    "    bargroupgap=0.1,\n",
    "    barmode=\"stack\",\n",
    "    xaxis_title=\"Decade\",\n",
    "    yaxis_title=\"Count\",\n",
    ")\n",
    "fig.show()\n",
    "\n",
    "del (mode_count, key_count, explicit_count)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "cols = [\n",
    "    \"valence\",\n",
    "    \"acousticness\",\n",
    "    \"danceability\",\n",
    "    \"duration_min\",\n",
    "    \"energy\",\n",
    "    \"instrumentalness\",\n",
    "    \"liveness\",\n",
    "    \"loudness\",\n",
    "    \"year\",\n",
    "    \"speechiness\",\n",
    "    \"tempo\",\n",
    "]\n",
    "\n",
    "for col in cols:\n",
    "\n",
    "    fig = px.scatter(\n",
    "        data_frame=df,\n",
    "        x=col,\n",
    "        y=\"popularity\",\n",
    "        trendline=\"ols\",\n",
    "        trendline_color_override=\"#A6E3A1\",\n",
    "    )\n",
    "    fig.update_traces(marker={\"opacity\": 0.3, \"size\": 3, \"color\": \"#B4BEFE\"})\n",
    "    fig.update_layout(title={\"text\": f\"{col} vs popularity\", \"font\": {\"size\": 24}})\n",
    "    fig.show()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Header 1\n",
    "\n",
    "## Header 2\n",
    "\n",
    "### Header 3.1"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "cols = [\n",
    "    \"valence\",\n",
    "    \"acousticness\",\n",
    "    \"danceability\",\n",
    "    \"duration_min\",\n",
    "    \"energy\",\n",
    "    \"instrumentalness\",\n",
    "    \"liveness\",\n",
    "    \"loudness\",\n",
    "    \"year\",\n",
    "    \"speechiness\",\n",
    "    \"tempo\",\n",
    "]\n",
    "\n",
    "plt.figure(figsize=(15, 10))\n",
    "\n",
    "for i, col in enumerate(cols):\n",
    "    ax = plt.subplot(3, 4, i + 1)\n",
    "    sns.regplot(\n",
    "        data=df,\n",
    "        x=\"popularity\",\n",
    "        y=col,\n",
    "        ax=ax,\n",
    "        scatter_kws={\"alpha\": 0.5},\n",
    "        line_kws={\"color\": \"#F38BA8\"},\n",
    "    )\n",
    "\n",
    "plt.tight_layout()\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "cols = [\n",
    "    \"valence\",\n",
    "    \"acousticness\",\n",
    "    \"danceability\",\n",
    "    \"duration_min\",\n",
    "    \"energy\",\n",
    "    \"instrumentalness\",\n",
    "    \"liveness\",\n",
    "    \"loudness\",\n",
    "    \"year\",\n",
    "    \"speechiness\",\n",
    "    \"tempo\",\n",
    "    \"popularity\",\n",
    "]\n",
    "\n",
    "plt.figure(figsize=(10, 7))\n",
    "mask = np.triu(np.ones_like(df[cols].corr()))\n",
    "sns.heatmap(\n",
    "    df[cols].corr(),\n",
    "    annot=True,\n",
    "    fmt=\".2f\",\n",
    "    cmap=\"Blues\",\n",
    "    mask=mask,\n",
    ")\n",
    "plt.grid(visible=False)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "df[\"first_artist\"] = (\n",
    "    df[\"artists\"]\n",
    "    .apply(lambda x: str(x).split(\"x\")[0])\n",
    "    .apply(lambda x: str(x).replace(\"[\", \"\"))\n",
    "    .apply(lambda x: str(x).replace(\"]\", \"\"))\n",
    "    .apply(lambda x: str(x).replace(\"'\", \"\"))\n",
    ")\n",
    "df = df.drop(\"artists\", axis=1)\n",
    "df[\"first_artist\"] = df[\"first_artist\"].apply(lambda x: str(x).split(\",\")[0])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "popularity_check = (\n",
    "    df.groupby([\"first_artist\"], as_index=False)[\"popularity\"]\n",
    "    .agg({\"mean\", \"count\", \"median\"})\n",
    "    .sort_values(by=\"mean\", ascending=False)\n",
    "    .reset_index(drop=True)\n",
    ")\n",
    "\n",
    "popularity_check = popularity_check.drop(16091, axis=0)\n",
    "popularity_check = popularity_check.drop(16086, axis=0)\n",
    "popularity_check = popularity_check.drop(16429, axis=0)\n",
    "\n",
    "to_drop = popularity_check[popularity_check[\"count\"] <= 45].index\n",
    "popularity_check = popularity_check.drop(to_drop)\n",
    "popularity_check = popularity_check.sort_values(by=\"mean\", ascending=False).head(50)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Header 1\n",
    "\n",
    "## Header 2\n",
    "\n",
    "### Header 3.1"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "top_50_artists = pd.DataFrame()\n",
    "\n",
    "for i in popularity_check[\"first_artist\"].unique():\n",
    "    artist = df.query(\"first_artist == @i\")\n",
    "    top_50_artists = pd.concat([top_50_artists, artist], axis=0)\n",
    "\n",
    "top_50_artists = top_50_artists.reset_index(drop=True)\n",
    "top_50_artists.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "plt.figure(figsize=(12, 8))\n",
    "(\n",
    "    top_50_artists[\"first_artist\"]\n",
    "    .value_counts()\n",
    "    .sort_values(ascending=True)\n",
    "    .plot(kind=\"barh\")\n",
    ")\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "top_50_artists[\"decade\"].value_counts().sort_values(ascending=True).plot(kind=\"barh\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "cols = [\n",
    "    \"valence\",\n",
    "    \"acousticness\",\n",
    "    \"danceability\",\n",
    "    \"duration_min\",\n",
    "    \"energy\",\n",
    "    \"instrumentalness\",\n",
    "    \"liveness\",\n",
    "    \"loudness\",\n",
    "    \"year\",\n",
    "    \"speechiness\",\n",
    "    \"tempo\",\n",
    "]\n",
    "\n",
    "plt.figure(figsize=(15, 10))\n",
    "\n",
    "for i, col in enumerate(cols):\n",
    "    ax = plt.subplot(3, 4, i + 1)\n",
    "    sns.kdeplot(data=top_50_artists, x=col, hue=\"first_artist\", legend=False)\n",
    "\n",
    "plt.tight_layout()\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Header 1\n",
    "\n",
    "## Header 2\n",
    "\n",
    "### Header 3.1"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "import pandas as pd\n",
    "import numpy as np\n",
    "import seaborn as sns\n",
    "import matplotlib.pyplot as plt\n",
    "import matplotlib as mpl\n",
    "import mplcatppuccin\n",
    "import plotly.express as px\n",
    "import plotly.graph_objects as go\n",
    "from plotly.subplots import make_subplots\n",
    "import plotly.figure_factory as ff\n",
    "import warnings\n",
    "import plotly.io as pio\n",
    "\n",
    "warnings.filterwarnings('ignore')\n",
    "\n",
    "pio.renderers.default = 'notebook_connected'\n",
    "pio.templates.default = 'plotly_dark'\n",
    "\n",
    "\n",
    "%matplotlib inline\n",
    "%config InlineBackend.figure_format = 'retina'\n",
    "pd.set_option('display.max_columns', None)\n",
    "pd.set_option('display.precision', 2)\n",
    "pd.set_option('display.colheader_justify', 'left')\n",
    "\n",
    "mpl.rc(\n",
    "    'figure',\n",
    "    autolayout=True,\n",
    "    titlesize=18\n",
    ")\n",
    "\n",
    "mpl.style.use(['ggplot', 'mocha'])\n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Header 3.2\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "df = pd.read_csv(\n",
    "    \"data.csv\",\n",
    "    parse_dates=[\"release_date\"],\n",
    ")\n",
    "df.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "map_key = {\n",
    "    0: \"C\",\n",
    "    1: \"C#\",\n",
    "    2: \"D\",\n",
    "    3: \"D#\",\n",
    "    4: \"E\",\n",
    "    5: \"F\",\n",
    "    6: \"F#\",\n",
    "    7: \"G\",\n",
    "    8: \"G#\",\n",
    "    9: \"A\",\n",
    "    10: \"A#\",\n",
    "    11: \"B\",\n",
    "}\n",
    "\n",
    "map_mode = {1: \"Major\", 0: \"Minor\"}\n",
    "\n",
    "df[\"mode\"] = df[\"mode\"].map(map_mode)\n",
    "df[\"key\"] = df[\"key\"].map(map_key)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "check_dups = df[[\"artists\", \"name\"]]\n",
    "dups = check_dups[check_dups.duplicated()].index"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "print(\"Before dropping duplicated:\", df.shape)\n",
    "df = df.drop(dups)\n",
    "print(\"After dropping duplicated:\", df.shape)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Header 1.3\n",
    "\n",
    "## Header 2.3\n",
    "\n",
    "### Header 3.5"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "df[\"duration_ms\"] = df[\"duration_ms\"] / 60_000\n",
    "df = df.rename(columns={\"duration_ms\": \"duration_min\"})\n",
    "df.head()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Header 1.4\n",
    "\n",
    "## Header 2.4\n",
    "\n",
    "### Header 3.5"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "df = df.drop([\"release_date\", \"id\"], axis=1)\n",
    "df.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "def fun_subplots_plotly(df, col):\n",
    "\n",
    "    mean_val = df[col].mean()\n",
    "    median_val = df[col].median()\n",
    "    fig = make_subplots(rows=1, cols=2, column_widths=[0.75, 0.25])\n",
    "\n",
    "    fig.add_trace(\n",
    "        go.Histogram(\n",
    "            x=df[col], name=f\"Histogram {col}\", marker={\"color\": \"#EBA0AC\"}, nbinsx=50\n",
    "        ),\n",
    "        row=1,\n",
    "        col=1,\n",
    "    )\n",
    "\n",
    "    fig.add_shape(\n",
    "        type=\"line\",\n",
    "        xref=\"paper\",\n",
    "        yref=\"y\",\n",
    "        x0=-1,\n",
    "        x1=1,\n",
    "        y0=mean_val,\n",
    "        y1=mean_val,\n",
    "        row=1,\n",
    "        col=2,\n",
    "        line={\"color\": \"#A6E3A1\", \"width\": 3, \"dash\": \"dot\"},\n",
    "    )\n",
    "\n",
    "    fig.add_shape(\n",
    "        type=\"line\",\n",
    "        xref=\"paper\",\n",
    "        yref=\"y\",\n",
    "        x0=-1,\n",
    "        x1=1,\n",
    "        y0=median_val,\n",
    "        y1=median_val,\n",
    "        row=1,\n",
    "        col=2,\n",
    "        line={\"color\": \"#CBA6F7\", \"width\": 3, \"dash\": \"dot\"},\n",
    "    )\n",
    "\n",
    "    fig.add_annotation(\n",
    "        xref=\"paper\",\n",
    "        x=-0.7,\n",
    "        y=mean_val,\n",
    "        showarrow=True,\n",
    "        arrowhead=2,\n",
    "        text=f\"Mean = {mean_val:.2f}\",\n",
    "        row=1,\n",
    "        col=2,\n",
    "    )\n",
    "\n",
    "    fig.add_annotation(\n",
    "        xref=\"paper\",\n",
    "        x=0.7,\n",
    "        y=median_val,\n",
    "        showarrow=True,\n",
    "        arrowhead=2,\n",
    "        text=f\"Median = {median_val:.2f}\",\n",
    "        row=1,\n",
    "        col=2,\n",
    "    )\n",
    "\n",
    "    fig.add_trace(\n",
    "        go.Box(y=df[col], name=f\"Boxplot {col}\", marker={\"color\": \"#F9E2AF\"}),\n",
    "        row=1,\n",
    "        col=2,\n",
    "    )\n",
    "\n",
    "    fig.update_layout(\n",
    "        title={\"text\": f\"Distribution Plot {col}\", \"font\": {\"size\": 24}},\n",
    "        legend={\n",
    "            \"orientation\": \"h\",\n",
    "            \"yanchor\": \"bottom\",\n",
    "            \"y\": 1.02,\n",
    "            \"xanchor\": \"right\",\n",
    "            \"x\": 1,\n",
    "        },\n",
    "    )\n",
    "    fig.update_yaxes(title_text=\"Count\", row=1, col=1)\n",
    "    fig.update_yaxes(title_text=f\"{col}\", row=1, col=2)\n",
    "    fig.update_xaxes(title_text=f\"{col}\", row=1, col=1)\n",
    "    fig.update_xaxes(title_text=\"\", row=1, col=2)\n",
    "    fig.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "music_vals = [\n",
    "    \"valence\",\n",
    "    \"acousticness\",\n",
    "    \"danceability\",\n",
    "    \"duration_min\",\n",
    "    \"energy\",\n",
    "    \"instrumentalness\",\n",
    "    \"liveness\",\n",
    "    \"loudness\",\n",
    "    \"popularity\",\n",
    "    \"speechiness\",\n",
    "    \"tempo\",\n",
    "]\n",
    "\n",
    "for col in music_vals:\n",
    "    fun_subplots_plotly(df, col)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Header 1.2\n",
    "\n",
    "## Header 2.2\n",
    "\n",
    "### Header 3.4"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "bins = pd.IntervalIndex.from_breaks(\n",
    "    [1920, 1930, 1940, 1950, 1960, 1970, 1980, 1990, 2000, 2010, 2020]\n",
    ")\n",
    "\n",
    "df[\"decade\"] = pd.cut(df[\"year\"], bins).astype(\"str\")\n",
    "\n",
    "map_decade = {\n",
    "    \"(1920, 1930]\": \"1920s\",\n",
    "    \"(1930, 1940]\": \"1930s\",\n",
    "    \"(1940, 1950]\": \"1940s\",\n",
    "    \"(1950, 1960]\": \"1950s\",\n",
    "    \"(1960, 1970]\": \"1960s\",\n",
    "    \"(1970, 1980]\": \"1970s\",\n",
    "    \"(1980, 1990]\": \"1980s\",\n",
    "    \"(1990, 2000]\": \"1990s\",\n",
    "    \"(2000, 2010]\": \"2000s\",\n",
    "    \"(2010, 2020]\": \"2010s\",\n",
    "}\n",
    "\n",
    "df[\"decade\"] = df[\"decade\"].map(map_decade)\n",
    "\n",
    "df.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "decade_counts = (\n",
    "    df[\"decade\"].value_counts().reset_index().sort_values(by=\"decade\", ascending=True)\n",
    ")\n",
    "\n",
    "fig = px.bar(\n",
    "    data_frame=decade_counts,\n",
    "    y=\"decade\",\n",
    "    x=\"count\",\n",
    "    color=\"count\",\n",
    "    color_continuous_scale=px.colors.sequential.Sunset,\n",
    "    text_auto=True,\n",
    ")\n",
    "\n",
    "fig.update_layout(\n",
    "    title={\"text\": \"Count of songs per decade\", \"font\": {\"size\": 24}},\n",
    "    coloraxis_colorbar={\n",
    "        \"title\": \"Count\",\n",
    "        \"thicknessmode\": \"pixels\",\n",
    "        \"thickness\": 20,\n",
    "        \"lenmode\": \"pixels\",\n",
    "        \"len\": 500,\n",
    "        \"yanchor\": \"top\",\n",
    "        \"xanchor\": \"right\",\n",
    "        \"y\": 1.15,\n",
    "        \"x\": 0.95,\n",
    "        \"orientation\": \"h\",\n",
    "    },\n",
    "    margin={\"r\": 10},\n",
    ")\n",
    "\n",
    "fig.update_xaxes(title=\"Count\")\n",
    "fig.update_yaxes(title=\"Decades\")\n",
    "fig.show()\n",
    "\n",
    "del decade_counts"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "df = df.query(\"duration_min <= 5\")"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Header 1.2\n",
    "\n",
    "## Header 2.2\n",
    "\n",
    "### Header 3.4"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "decade_counts = (\n",
    "    df[\"decade\"].value_counts().reset_index().sort_values(by=\"decade\", ascending=True)\n",
    ")\n",
    "\n",
    "fig = px.bar(\n",
    "    data_frame=decade_counts,\n",
    "    y=\"decade\",\n",
    "    x=\"count\",\n",
    "    color=\"count\",\n",
    "    color_continuous_scale=px.colors.sequential.Sunset,\n",
    "    text_auto=True,\n",
    ")\n",
    "\n",
    "fig.update_layout(\n",
    "    title={\"text\": \"Count of songs per decade (< 5min)\", \"font\": {\"size\": 24}},\n",
    "    coloraxis_colorbar={\n",
    "        \"title\": \"Count\",\n",
    "        \"thicknessmode\": \"pixels\",\n",
    "        \"thickness\": 20,\n",
    "        \"lenmode\": \"pixels\",\n",
    "        \"len\": 500,\n",
    "        \"yanchor\": \"top\",\n",
    "        \"xanchor\": \"right\",\n",
    "        \"y\": 1.15,\n",
    "        \"x\": 0.95,\n",
    "        \"orientation\": \"h\",\n",
    "    },\n",
    "    margin={\"r\": 10},\n",
    ")\n",
    "\n",
    "fig.update_xaxes(title=\"Count\")\n",
    "fig.update_yaxes(title=\"Decades\")\n",
    "fig.show()\n",
    "\n",
    "del decade_counts"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "cols = [\n",
    "    \"valence\",\n",
    "    \"acousticness\",\n",
    "    \"danceability\",\n",
    "    \"duration_min\",\n",
    "    \"energy\",\n",
    "    \"instrumentalness\",\n",
    "    \"liveness\",\n",
    "    \"loudness\",\n",
    "    \"popularity\",\n",
    "    \"speechiness\",\n",
    "    \"tempo\",\n",
    "]\n",
    "for col in cols:\n",
    "    fig = px.histogram(\n",
    "        data_frame=df,\n",
    "        x=col,\n",
    "        color=\"decade\",\n",
    "        color_discrete_sequence=px.colors.qualitative.Light24,\n",
    "    )\n",
    "    fig.update_traces(opacity=0.7)\n",
    "    fig.update_layout(\n",
    "        bargap=0.1,\n",
    "        bargroupgap=0.05,\n",
    "        barmode=\"stack\",\n",
    "        title={\"text\": f\"Histogram of {col} per decade\", \"font\": {\"size\": 24}},\n",
    "        legend={\"title\": \"Decade\"},\n",
    "    )\n",
    "    fig.update_yaxes(title=\"Count\")\n",
    "    fig.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "decade_mean = df.groupby(\"decade\")[cols].mean()\n",
    "\n",
    "fig = make_subplots(\n",
    "    rows=4,\n",
    "    cols=3,\n",
    "    subplot_titles=(\n",
    "        decade_mean.columns[0],\n",
    "        decade_mean.columns[1],\n",
    "        decade_mean.columns[2],\n",
    "        decade_mean.columns[3],\n",
    "        decade_mean.columns[4],\n",
    "        decade_mean.columns[5],\n",
    "        decade_mean.columns[6],\n",
    "        decade_mean.columns[7],\n",
    "        decade_mean.columns[8],\n",
    "        decade_mean.columns[9],\n",
    "        decade_mean.columns[10],\n",
    "    ),\n",
    "    vertical_spacing=0.1,\n",
    ")\n",
    "\n",
    "fig.add_trace(\n",
    "    go.Bar(\n",
    "        y=decade_mean.index,\n",
    "        x=decade_mean.iloc[:, 0],\n",
    "        name=decade_mean.columns[0],\n",
    "        orientation=\"h\",\n",
    "    ),\n",
    "    row=1,\n",
    "    col=1,\n",
    ")\n",
    "\n",
    "fig.add_trace(\n",
    "    go.Bar(\n",
    "        y=decade_mean.index,\n",
    "        x=decade_mean.iloc[:, 1],\n",
    "        name=decade_mean.columns[1],\n",
    "        orientation=\"h\",\n",
    "    ),\n",
    "    row=1,\n",
    "    col=2,\n",
    ")\n",
    "\n",
    "fig.add_trace(\n",
    "    go.Bar(\n",
    "        y=decade_mean.index,\n",
    "        x=decade_mean.iloc[:, 2],\n",
    "        name=decade_mean.columns[2],\n",
    "        orientation=\"h\",\n",
    "    ),\n",
    "    row=1,\n",
    "    col=3,\n",
    ")\n",
    "\n",
    "fig.add_trace(\n",
    "    go.Bar(\n",
    "        y=decade_mean.index,\n",
    "        x=decade_mean.iloc[:, 3],\n",
    "        name=decade_mean.columns[3],\n",
    "        orientation=\"h\",\n",
    "    ),\n",
    "    row=2,\n",
    "    col=1,\n",
    ")\n",
    "\n",
    "fig.add_trace(\n",
    "    go.Bar(\n",
    "        y=decade_mean.index,\n",
    "        x=decade_mean.iloc[:, 4],\n",
    "        name=decade_mean.columns[4],\n",
    "        orientation=\"h\",\n",
    "    ),\n",
    "    row=2,\n",
    "    col=2,\n",
    ")\n",
    "\n",
    "fig.add_trace(\n",
    "    go.Bar(\n",
    "        y=decade_mean.index,\n",
    "        x=decade_mean.iloc[:, 5],\n",
    "        name=decade_mean.columns[5],\n",
    "        orientation=\"h\",\n",
    "    ),\n",
    "    row=2,\n",
    "    col=3,\n",
    ")\n",
    "\n",
    "fig.add_trace(\n",
    "    go.Bar(\n",
    "        y=decade_mean.index,\n",
    "        x=decade_mean.iloc[:, 6],\n",
    "        name=decade_mean.columns[6],\n",
    "        orientation=\"h\",\n",
    "    ),\n",
    "    row=3,\n",
    "    col=1,\n",
    ")\n",
    "\n",
    "fig.add_trace(\n",
    "    go.Bar(\n",
    "        y=decade_mean.index,\n",
    "        x=decade_mean.iloc[:, 7],\n",
    "        name=decade_mean.columns[7],\n",
    "        orientation=\"h\",\n",
    "    ),\n",
    "    row=3,\n",
    "    col=2,\n",
    ")\n",
    "\n",
    "fig.add_trace(\n",
    "    go.Bar(\n",
    "        y=decade_mean.index,\n",
    "        x=decade_mean.iloc[:, 8],\n",
    "        name=decade_mean.columns[8],\n",
    "        orientation=\"h\",\n",
    "    ),\n",
    "    row=3,\n",
    "    col=3,\n",
    ")\n",
    "\n",
    "fig.add_trace(\n",
    "    go.Bar(\n",
    "        y=decade_mean.index,\n",
    "        x=decade_mean.iloc[:, 9],\n",
    "        name=decade_mean.columns[9],\n",
    "        orientation=\"h\",\n",
    "    ),\n",
    "    row=4,\n",
    "    col=1,\n",
    ")\n",
    "\n",
    "fig.add_trace(\n",
    "    go.Bar(\n",
    "        y=decade_mean.index,\n",
    "        x=decade_mean.iloc[:, 10],\n",
    "        name=decade_mean.columns[10],\n",
    "        orientation=\"h\",\n",
    "    ),\n",
    "    row=4,\n",
    "    col=2,\n",
    ")\n",
    "\n",
    "fig.update_layout(\n",
    "    title={\"text\": \"Mean Musical Values per Decade\", \"font\": {\"size\": 22}},\n",
    "    legend={\n",
    "        \"orientation\": \"v\",\n",
    "        \"yanchor\": \"top\",\n",
    "        \"y\": 0.2,\n",
    "        \"xanchor\": \"right\",\n",
    "        \"x\": 0.9,\n",
    "    },\n",
    "    margin={\"b\": 10, \"r\": 10},\n",
    "    height=980,\n",
    ")\n",
    "\n",
    "fig.show()\n",
    "\n",
    "del decade_mean"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "decade_median = df.groupby(\"decade\")[cols].median()\n",
    "\n",
    "fig = make_subplots(\n",
    "    rows=4,\n",
    "    cols=3,\n",
    "    subplot_titles=(\n",
    "        decade_median.columns[0],\n",
    "        decade_median.columns[1],\n",
    "        decade_median.columns[2],\n",
    "        decade_median.columns[3],\n",
    "        decade_median.columns[4],\n",
    "        decade_median.columns[5],\n",
    "        decade_median.columns[6],\n",
    "        decade_median.columns[7],\n",
    "        decade_median.columns[8],\n",
    "        decade_median.columns[9],\n",
    "        decade_median.columns[10],\n",
    "    ),\n",
    "    vertical_spacing=0.1,\n",
    ")\n",
    "\n",
    "fig.add_trace(\n",
    "    go.Bar(\n",
    "        y=decade_median.index,\n",
    "        x=decade_median.iloc[:, 0],\n",
    "        name=decade_median.columns[0],\n",
    "        orientation=\"h\",\n",
    "    ),\n",
    "    row=1,\n",
    "    col=1,\n",
    ")\n",
    "\n",
    "fig.add_trace(\n",
    "    go.Bar(\n",
    "        y=decade_median.index,\n",
    "        x=decade_median.iloc[:, 1],\n",
    "        name=decade_median.columns[1],\n",
    "        orientation=\"h\",\n",
    "    ),\n",
    "    row=1,\n",
    "    col=2,\n",
    ")\n",
    "\n",
    "fig.add_trace(\n",
    "    go.Bar(\n",
    "        y=decade_median.index,\n",
    "        x=decade_median.iloc[:, 2],\n",
    "        name=decade_median.columns[2],\n",
    "        orientation=\"h\",\n",
    "    ),\n",
    "    row=1,\n",
    "    col=3,\n",
    ")\n",
    "\n",
    "fig.add_trace(\n",
    "    go.Bar(\n",
    "        y=decade_median.index,\n",
    "        x=decade_median.iloc[:, 3],\n",
    "        name=decade_median.columns[3],\n",
    "        orientation=\"h\",\n",
    "    ),\n",
    "    row=2,\n",
    "    col=1,\n",
    ")\n",
    "\n",
    "fig.add_trace(\n",
    "    go.Bar(\n",
    "        y=decade_median.index,\n",
    "        x=decade_median.iloc[:, 4],\n",
    "        name=decade_median.columns[4],\n",
    "        orientation=\"h\",\n",
    "    ),\n",
    "    row=2,\n",
    "    col=2,\n",
    ")\n",
    "\n",
    "fig.add_trace(\n",
    "    go.Bar(\n",
    "        y=decade_median.index,\n",
    "        x=decade_median.iloc[:, 5],\n",
    "        name=decade_median.columns[5],\n",
    "        orientation=\"h\",\n",
    "    ),\n",
    "    row=2,\n",
    "    col=3,\n",
    ")\n",
    "\n",
    "fig.add_trace(\n",
    "    go.Bar(\n",
    "        y=decade_median.index,\n",
    "        x=decade_median.iloc[:, 6],\n",
    "        name=decade_median.columns[6],\n",
    "        orientation=\"h\",\n",
    "    ),\n",
    "    row=3,\n",
    "    col=1,\n",
    ")\n",
    "\n",
    "fig.add_trace(\n",
    "    go.Bar(\n",
    "        y=decade_median.index,\n",
    "        x=decade_median.iloc[:, 7],\n",
    "        name=decade_median.columns[7],\n",
    "        orientation=\"h\",\n",
    "    ),\n",
    "    row=3,\n",
    "    col=2,\n",
    ")\n",
    "\n",
    "fig.add_trace(\n",
    "    go.Bar(\n",
    "        y=decade_median.index,\n",
    "        x=decade_median.iloc[:, 8],\n",
    "        name=decade_median.columns[8],\n",
    "        orientation=\"h\",\n",
    "    ),\n",
    "    row=3,\n",
    "    col=3,\n",
    ")\n",
    "\n",
    "fig.add_trace(\n",
    "    go.Bar(\n",
    "        y=decade_median.index,\n",
    "        x=decade_median.iloc[:, 9],\n",
    "        name=decade_median.columns[9],\n",
    "        orientation=\"h\",\n",
    "    ),\n",
    "    row=4,\n",
    "    col=1,\n",
    ")\n",
    "\n",
    "fig.add_trace(\n",
    "    go.Bar(\n",
    "        y=decade_median.index,\n",
    "        x=decade_median.iloc[:, 10],\n",
    "        name=decade_median.columns[10],\n",
    "        orientation=\"h\",\n",
    "    ),\n",
    "    row=4,\n",
    "    col=2,\n",
    ")\n",
    "\n",
    "fig.update_layout(\n",
    "    title={\"text\": \"Median Musical Values per Decade\", \"font\": {\"size\": 22}},\n",
    "    legend={\n",
    "        \"orientation\": \"v\",\n",
    "        \"yanchor\": \"top\",\n",
    "        \"y\": 0.2,\n",
    "        \"xanchor\": \"right\",\n",
    "        \"x\": 0.9,\n",
    "    },\n",
    "    margin={\"b\": 10, \"r\": 10},\n",
    "    height=980,\n",
    ")\n",
    "\n",
    "fig.show()\n",
    "\n",
    "del decade_median"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "explicit_count = (\n",
    "    df.groupby([\"decade\", \"explicit\"], as_index=False)[\"year\"]\n",
    "    .count()\n",
    "    .rename(columns={\"year\": \"count\"})\n",
    ")\n",
    "key_count = (\n",
    "    df.groupby([\"decade\", \"key\"], as_index=False)[\"year\"]\n",
    "    .count()\n",
    "    .rename(columns={\"year\": \"count\"})\n",
    ")\n",
    "mode_count = (\n",
    "    df.groupby([\"decade\", \"mode\"], as_index=False)[\"year\"]\n",
    "    .count()\n",
    "    .rename(columns={\"year\": \"count\"})\n",
    ")\n",
    "\n",
    "fig = px.histogram(\n",
    "    data_frame=explicit_count,\n",
    "    x=\"decade\",\n",
    "    y=\"count\",\n",
    "    color=\"explicit\",\n",
    "    histfunc=\"sum\",\n",
    "    color_discrete_sequence=px.colors.qualitative.Pastel,\n",
    "    text_auto=True,\n",
    ")\n",
    "fig.update_layout(\n",
    "    title={\"text\": \"Explicit Count per Decade\", \"font\": {\"size\": 24}},\n",
    "    bargap=0.2,\n",
    "    bargroupgap=0.1,\n",
    "    barmode=\"group\",\n",
    "    xaxis_title=\"Decade\",\n",
    "    yaxis_title=\"Count\",\n",
    ")\n",
    "fig.show()\n",
    "\n",
    "fig = px.histogram(\n",
    "    data_frame=mode_count,\n",
    "    x=\"decade\",\n",
    "    y=\"count\",\n",
    "    color=\"mode\",\n",
    "    histfunc=\"sum\",\n",
    "    color_discrete_sequence=px.colors.qualitative.Pastel,\n",
    "    text_auto=True,\n",
    ")\n",
    "fig.update_layout(\n",
    "    title={\"text\": \"Mode Count per Decade\", \"font\": {\"size\": 24}},\n",
    "    bargap=0.2,\n",
    "    bargroupgap=0.1,\n",
    "    barmode=\"group\",\n",
    "    xaxis_title=\"Decade\",\n",
    "    yaxis_title=\"Count\",\n",
    ")\n",
    "fig.show()\n",
    "\n",
    "fig = px.histogram(\n",
    "    data_frame=key_count,\n",
    "    x=\"decade\",\n",
    "    y=\"count\",\n",
    "    color=\"key\",\n",
    "    histfunc=\"sum\",\n",
    "    color_discrete_sequence=px.colors.qualitative.Pastel,\n",
    "    text_auto=True,\n",
    ")\n",
    "fig.update_layout(\n",
    "    title={\"text\": \"Key Count per Decade\", \"font\": {\"size\": 24}},\n",
    "    bargap=0.2,\n",
    "    bargroupgap=0.1,\n",
    "    barmode=\"stack\",\n",
    "    xaxis_title=\"Decade\",\n",
    "    yaxis_title=\"Count\",\n",
    ")\n",
    "fig.show()\n",
    "\n",
    "del (mode_count, key_count, explicit_count)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "cols = [\n",
    "    \"valence\",\n",
    "    \"acousticness\",\n",
    "    \"danceability\",\n",
    "    \"duration_min\",\n",
    "    \"energy\",\n",
    "    \"instrumentalness\",\n",
    "    \"liveness\",\n",
    "    \"loudness\",\n",
    "    \"year\",\n",
    "    \"speechiness\",\n",
    "    \"tempo\",\n",
    "]\n",
    "\n",
    "for col in cols:\n",
    "\n",
    "    fig = px.scatter(\n",
    "        data_frame=df,\n",
    "        x=col,\n",
    "        y=\"popularity\",\n",
    "        trendline=\"ols\",\n",
    "        trendline_color_override=\"#A6E3A1\",\n",
    "    )\n",
    "    fig.update_traces(marker={\"opacity\": 0.3, \"size\": 3, \"color\": \"#B4BEFE\"})\n",
    "    fig.update_layout(title={\"text\": f\"{col} vs popularity\", \"font\": {\"size\": 24}})\n",
    "    fig.show()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Header 1\n",
    "\n",
    "## Header 2\n",
    "\n",
    "### Header 3.1"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "cols = [\n",
    "    \"valence\",\n",
    "    \"acousticness\",\n",
    "    \"danceability\",\n",
    "    \"duration_min\",\n",
    "    \"energy\",\n",
    "    \"instrumentalness\",\n",
    "    \"liveness\",\n",
    "    \"loudness\",\n",
    "    \"year\",\n",
    "    \"speechiness\",\n",
    "    \"tempo\",\n",
    "]\n",
    "\n",
    "plt.figure(figsize=(15, 10))\n",
    "\n",
    "for i, col in enumerate(cols):\n",
    "    ax = plt.subplot(3, 4, i + 1)\n",
    "    sns.regplot(\n",
    "        data=df,\n",
    "        x=\"popularity\",\n",
    "        y=col,\n",
    "        ax=ax,\n",
    "        scatter_kws={\"alpha\": 0.5},\n",
    "        line_kws={\"color\": \"#F38BA8\"},\n",
    "    )\n",
    "\n",
    "plt.tight_layout()\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "cols = [\n",
    "    \"valence\",\n",
    "    \"acousticness\",\n",
    "    \"danceability\",\n",
    "    \"duration_min\",\n",
    "    \"energy\",\n",
    "    \"instrumentalness\",\n",
    "    \"liveness\",\n",
    "    \"loudness\",\n",
    "    \"year\",\n",
    "    \"speechiness\",\n",
    "    \"tempo\",\n",
    "    \"popularity\",\n",
    "]\n",
    "\n",
    "plt.figure(figsize=(10, 7))\n",
    "mask = np.triu(np.ones_like(df[cols].corr()))\n",
    "sns.heatmap(\n",
    "    df[cols].corr(),\n",
    "    annot=True,\n",
    "    fmt=\".2f\",\n",
    "    cmap=\"Blues\",\n",
    "    mask=mask,\n",
    ")\n",
    "plt.grid(visible=False)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "df[\"first_artist\"] = (\n",
    "    df[\"artists\"]\n",
    "    .apply(lambda x: str(x).split(\"x\")[0])\n",
    "    .apply(lambda x: str(x).replace(\"[\", \"\"))\n",
    "    .apply(lambda x: str(x).replace(\"]\", \"\"))\n",
    "    .apply(lambda x: str(x).replace(\"'\", \"\"))\n",
    ")\n",
    "df = df.drop(\"artists\", axis=1)\n",
    "df[\"first_artist\"] = df[\"first_artist\"].apply(lambda x: str(x).split(\",\")[0])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "popularity_check = (\n",
    "    df.groupby([\"first_artist\"], as_index=False)[\"popularity\"]\n",
    "    .agg({\"mean\", \"count\", \"median\"})\n",
    "    .sort_values(by=\"mean\", ascending=False)\n",
    "    .reset_index(drop=True)\n",
    ")\n",
    "\n",
    "popularity_check = popularity_check.drop(16091, axis=0)\n",
    "popularity_check = popularity_check.drop(16086, axis=0)\n",
    "popularity_check = popularity_check.drop(16429, axis=0)\n",
    "\n",
    "to_drop = popularity_check[popularity_check[\"count\"] <= 45].index\n",
    "popularity_check = popularity_check.drop(to_drop)\n",
    "popularity_check = popularity_check.sort_values(by=\"mean\", ascending=False).head(50)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Header 1\n",
    "\n",
    "## Header 2\n",
    "\n",
    "### Header 3.1"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "top_50_artists = pd.DataFrame()\n",
    "\n",
    "for i in popularity_check[\"first_artist\"].unique():\n",
    "    artist = df.query(\"first_artist == @i\")\n",
    "    top_50_artists = pd.concat([top_50_artists, artist], axis=0)\n",
    "\n",
    "top_50_artists = top_50_artists.reset_index(drop=True)\n",
    "top_50_artists.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "plt.figure(figsize=(12, 8))\n",
    "(\n",
    "    top_50_artists[\"first_artist\"]\n",
    "    .value_counts()\n",
    "    .sort_values(ascending=True)\n",
    "    .plot(kind=\"barh\")\n",
    ")\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "top_50_artists[\"decade\"].value_counts().sort_values(ascending=True).plot(kind=\"barh\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "cols = [\n",
    "    \"valence\",\n",
    "    \"acousticness\",\n",
    "    \"danceability\",\n",
    "    \"duration_min\",\n",
    "    \"energy\",\n",
    "    \"instrumentalness\",\n",
    "    \"liveness\",\n",
    "    \"loudness\",\n",
    "    \"year\",\n",
    "    \"speechiness\",\n",
    "    \"tempo\",\n",
    "]\n",
    "\n",
    "plt.figure(figsize=(15, 10))\n",
    "\n",
    "for i, col in enumerate(cols):\n",
    "    ax = plt.subplot(3, 4, i + 1)\n",
    "    sns.kdeplot(data=top_50_artists, x=col, hue=\"first_artist\", legend=False)\n",
    "\n",
    "plt.tight_layout()\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Header 1\n",
    "\n",
    "## Header 2\n",
    "\n",
    "### Header 3.1"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "import pandas as pd\n",
    "import numpy as np\n",
    "import seaborn as sns\n",
    "import matplotlib.pyplot as plt\n",
    "import matplotlib as mpl\n",
    "import mplcatppuccin\n",
    "import plotly.express as px\n",
    "import plotly.graph_objects as go\n",
    "from plotly.subplots import make_subplots\n",
    "import plotly.figure_factory as ff\n",
    "import warnings\n",
    "import plotly.io as pio\n",
    "\n",
    "warnings.filterwarnings('ignore')\n",
    "\n",
    "pio.renderers.default = 'notebook_connected'\n",
    "pio.templates.default = 'plotly_dark'\n",
    "\n",
    "\n",
    "%matplotlib inline\n",
    "%config InlineBackend.figure_format = 'retina'\n",
    "pd.set_option('display.max_columns', None)\n",
    "pd.set_option('display.precision', 2)\n",
    "pd.set_option('display.colheader_justify', 'left')\n",
    "\n",
    "mpl.rc(\n",
    "    'figure',\n",
    "    autolayout=True,\n",
    "    titlesize=18\n",
    ")\n",
    "\n",
    "mpl.style.use(['ggplot', 'mocha'])\n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Header 3.2\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "df = pd.read_csv(\n",
    "    \"data.csv\",\n",
    "    parse_dates=[\"release_date\"],\n",
    ")\n",
    "df.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "map_key = {\n",
    "    0: \"C\",\n",
    "    1: \"C#\",\n",
    "    2: \"D\",\n",
    "    3: \"D#\",\n",
    "    4: \"E\",\n",
    "    5: \"F\",\n",
    "    6: \"F#\",\n",
    "    7: \"G\",\n",
    "    8: \"G#\",\n",
    "    9: \"A\",\n",
    "    10: \"A#\",\n",
    "    11: \"B\",\n",
    "}\n",
    "\n",
    "map_mode = {1: \"Major\", 0: \"Minor\"}\n",
    "\n",
    "df[\"mode\"] = df[\"mode\"].map(map_mode)\n",
    "df[\"key\"] = df[\"key\"].map(map_key)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "check_dups = df[[\"artists\", \"name\"]]\n",
    "dups = check_dups[check_dups.duplicated()].index"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "print(\"Before dropping duplicated:\", df.shape)\n",
    "df = df.drop(dups)\n",
    "print(\"After dropping duplicated:\", df.shape)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Header 1.3\n",
    "\n",
    "## Header 2.3\n",
    "\n",
    "### Header 3.5"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "df[\"duration_ms\"] = df[\"duration_ms\"] / 60_000\n",
    "df = df.rename(columns={\"duration_ms\": \"duration_min\"})\n",
    "df.head()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Header 1.4\n",
    "\n",
    "## Header 2.4\n",
    "\n",
    "### Header 3.5"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "df = df.drop([\"release_date\", \"id\"], axis=1)\n",
    "df.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "def fun_subplots_plotly(df, col):\n",
    "\n",
    "    mean_val = df[col].mean()\n",
    "    median_val = df[col].median()\n",
    "    fig = make_subplots(rows=1, cols=2, column_widths=[0.75, 0.25])\n",
    "\n",
    "    fig.add_trace(\n",
    "        go.Histogram(\n",
    "            x=df[col], name=f\"Histogram {col}\", marker={\"color\": \"#EBA0AC\"}, nbinsx=50\n",
    "        ),\n",
    "        row=1,\n",
    "        col=1,\n",
    "    )\n",
    "\n",
    "    fig.add_shape(\n",
    "        type=\"line\",\n",
    "        xref=\"paper\",\n",
    "        yref=\"y\",\n",
    "        x0=-1,\n",
    "        x1=1,\n",
    "        y0=mean_val,\n",
    "        y1=mean_val,\n",
    "        row=1,\n",
    "        col=2,\n",
    "        line={\"color\": \"#A6E3A1\", \"width\": 3, \"dash\": \"dot\"},\n",
    "    )\n",
    "\n",
    "    fig.add_shape(\n",
    "        type=\"line\",\n",
    "        xref=\"paper\",\n",
    "        yref=\"y\",\n",
    "        x0=-1,\n",
    "        x1=1,\n",
    "        y0=median_val,\n",
    "        y1=median_val,\n",
    "        row=1,\n",
    "        col=2,\n",
    "        line={\"color\": \"#CBA6F7\", \"width\": 3, \"dash\": \"dot\"},\n",
    "    )\n",
    "\n",
    "    fig.add_annotation(\n",
    "        xref=\"paper\",\n",
    "        x=-0.7,\n",
    "        y=mean_val,\n",
    "        showarrow=True,\n",
    "        arrowhead=2,\n",
    "        text=f\"Mean = {mean_val:.2f}\",\n",
    "        row=1,\n",
    "        col=2,\n",
    "    )\n",
    "\n",
    "    fig.add_annotation(\n",
    "        xref=\"paper\",\n",
    "        x=0.7,\n",
    "        y=median_val,\n",
    "        showarrow=True,\n",
    "        arrowhead=2,\n",
    "        text=f\"Median = {median_val:.2f}\",\n",
    "        row=1,\n",
    "        col=2,\n",
    "    )\n",
    "\n",
    "    fig.add_trace(\n",
    "        go.Box(y=df[col], name=f\"Boxplot {col}\", marker={\"color\": \"#F9E2AF\"}),\n",
    "        row=1,\n",
    "        col=2,\n",
    "    )\n",
    "\n",
    "    fig.update_layout(\n",
    "        title={\"text\": f\"Distribution Plot {col}\", \"font\": {\"size\": 24}},\n",
    "        legend={\n",
    "            \"orientation\": \"h\",\n",
    "            \"yanchor\": \"bottom\",\n",
    "            \"y\": 1.02,\n",
    "            \"xanchor\": \"right\",\n",
    "            \"x\": 1,\n",
    "        },\n",
    "    )\n",
    "    fig.update_yaxes(title_text=\"Count\", row=1, col=1)\n",
    "    fig.update_yaxes(title_text=f\"{col}\", row=1, col=2)\n",
    "    fig.update_xaxes(title_text=f\"{col}\", row=1, col=1)\n",
    "    fig.update_xaxes(title_text=\"\", row=1, col=2)\n",
    "    fig.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "music_vals = [\n",
    "    \"valence\",\n",
    "    \"acousticness\",\n",
    "    \"danceability\",\n",
    "    \"duration_min\",\n",
    "    \"energy\",\n",
    "    \"instrumentalness\",\n",
    "    \"liveness\",\n",
    "    \"loudness\",\n",
    "    \"popularity\",\n",
    "    \"speechiness\",\n",
    "    \"tempo\",\n",
    "]\n",
    "\n",
    "for col in music_vals:\n",
    "    fun_subplots_plotly(df, col)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Header 1.2\n",
    "\n",
    "## Header 2.2\n",
    "\n",
    "### Header 3.4"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "bins = pd.IntervalIndex.from_breaks(\n",
    "    [1920, 1930, 1940, 1950, 1960, 1970, 1980, 1990, 2000, 2010, 2020]\n",
    ")\n",
    "\n",
    "df[\"decade\"] = pd.cut(df[\"year\"], bins).astype(\"str\")\n",
    "\n",
    "map_decade = {\n",
    "    \"(1920, 1930]\": \"1920s\",\n",
    "    \"(1930, 1940]\": \"1930s\",\n",
    "    \"(1940, 1950]\": \"1940s\",\n",
    "    \"(1950, 1960]\": \"1950s\",\n",
    "    \"(1960, 1970]\": \"1960s\",\n",
    "    \"(1970, 1980]\": \"1970s\",\n",
    "    \"(1980, 1990]\": \"1980s\",\n",
    "    \"(1990, 2000]\": \"1990s\",\n",
    "    \"(2000, 2010]\": \"2000s\",\n",
    "    \"(2010, 2020]\": \"2010s\",\n",
    "}\n",
    "\n",
    "df[\"decade\"] = df[\"decade\"].map(map_decade)\n",
    "\n",
    "df.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "decade_counts = (\n",
    "    df[\"decade\"].value_counts().reset_index().sort_values(by=\"decade\", ascending=True)\n",
    ")\n",
    "\n",
    "fig = px.bar(\n",
    "    data_frame=decade_counts,\n",
    "    y=\"decade\",\n",
    "    x=\"count\",\n",
    "    color=\"count\",\n",
    "    color_continuous_scale=px.colors.sequential.Sunset,\n",
    "    text_auto=True,\n",
    ")\n",
    "\n",
    "fig.update_layout(\n",
    "    title={\"text\": \"Count of songs per decade\", \"font\": {\"size\": 24}},\n",
    "    coloraxis_colorbar={\n",
    "        \"title\": \"Count\",\n",
    "        \"thicknessmode\": \"pixels\",\n",
    "        \"thickness\": 20,\n",
    "        \"lenmode\": \"pixels\",\n",
    "        \"len\": 500,\n",
    "        \"yanchor\": \"top\",\n",
    "        \"xanchor\": \"right\",\n",
    "        \"y\": 1.15,\n",
    "        \"x\": 0.95,\n",
    "        \"orientation\": \"h\",\n",
    "    },\n",
    "    margin={\"r\": 10},\n",
    ")\n",
    "\n",
    "fig.update_xaxes(title=\"Count\")\n",
    "fig.update_yaxes(title=\"Decades\")\n",
    "fig.show()\n",
    "\n",
    "del decade_counts"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "df = df.query(\"duration_min <= 5\")"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Header 1.2\n",
    "\n",
    "## Header 2.2\n",
    "\n",
    "### Header 3.4"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "decade_counts = (\n",
    "    df[\"decade\"].value_counts().reset_index().sort_values(by=\"decade\", ascending=True)\n",
    ")\n",
    "\n",
    "fig = px.bar(\n",
    "    data_frame=decade_counts,\n",
    "    y=\"decade\",\n",
    "    x=\"count\",\n",
    "    color=\"count\",\n",
    "    color_continuous_scale=px.colors.sequential.Sunset,\n",
    "    text_auto=True,\n",
    ")\n",
    "\n",
    "fig.update_layout(\n",
    "    title={\"text\": \"Count of songs per decade (< 5min)\", \"font\": {\"size\": 24}},\n",
    "    coloraxis_colorbar={\n",
    "        \"title\": \"Count\",\n",
    "        \"thicknessmode\": \"pixels\",\n",
    "        \"thickness\": 20,\n",
    "        \"lenmode\": \"pixels\",\n",
    "        \"len\": 500,\n",
    "        \"yanchor\": \"top\",\n",
    "        \"xanchor\": \"right\",\n",
    "        \"y\": 1.15,\n",
    "        \"x\": 0.95,\n",
    "        \"orientation\": \"h\",\n",
    "    },\n",
    "    margin={\"r\": 10},\n",
    ")\n",
    "\n",
    "fig.update_xaxes(title=\"Count\")\n",
    "fig.update_yaxes(title=\"Decades\")\n",
    "fig.show()\n",
    "\n",
    "del decade_counts"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "cols = [\n",
    "    \"valence\",\n",
    "    \"acousticness\",\n",
    "    \"danceability\",\n",
    "    \"duration_min\",\n",
    "    \"energy\",\n",
    "    \"instrumentalness\",\n",
    "    \"liveness\",\n",
    "    \"loudness\",\n",
    "    \"popularity\",\n",
    "    \"speechiness\",\n",
    "    \"tempo\",\n",
    "]\n",
    "for col in cols:\n",
    "    fig = px.histogram(\n",
    "        data_frame=df,\n",
    "        x=col,\n",
    "        color=\"decade\",\n",
    "        color_discrete_sequence=px.colors.qualitative.Light24,\n",
    "    )\n",
    "    fig.update_traces(opacity=0.7)\n",
    "    fig.update_layout(\n",
    "        bargap=0.1,\n",
    "        bargroupgap=0.05,\n",
    "        barmode=\"stack\",\n",
    "        title={\"text\": f\"Histogram of {col} per decade\", \"font\": {\"size\": 24}},\n",
    "        legend={\"title\": \"Decade\"},\n",
    "    )\n",
    "    fig.update_yaxes(title=\"Count\")\n",
    "    fig.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "decade_mean = df.groupby(\"decade\")[cols].mean()\n",
    "\n",
    "fig = make_subplots(\n",
    "    rows=4,\n",
    "    cols=3,\n",
    "    subplot_titles=(\n",
    "        decade_mean.columns[0],\n",
    "        decade_mean.columns[1],\n",
    "        decade_mean.columns[2],\n",
    "        decade_mean.columns[3],\n",
    "        decade_mean.columns[4],\n",
    "        decade_mean.columns[5],\n",
    "        decade_mean.columns[6],\n",
    "        decade_mean.columns[7],\n",
    "        decade_mean.columns[8],\n",
    "        decade_mean.columns[9],\n",
    "        decade_mean.columns[10],\n",
    "    ),\n",
    "    vertical_spacing=0.1,\n",
    ")\n",
    "\n",
    "fig.add_trace(\n",
    "    go.Bar(\n",
    "        y=decade_mean.index,\n",
    "        x=decade_mean.iloc[:, 0],\n",
    "        name=decade_mean.columns[0],\n",
    "        orientation=\"h\",\n",
    "    ),\n",
    "    row=1,\n",
    "    col=1,\n",
    ")\n",
    "\n",
    "fig.add_trace(\n",
    "    go.Bar(\n",
    "        y=decade_mean.index,\n",
    "        x=decade_mean.iloc[:, 1],\n",
    "        name=decade_mean.columns[1],\n",
    "        orientation=\"h\",\n",
    "    ),\n",
    "    row=1,\n",
    "    col=2,\n",
    ")\n",
    "\n",
    "fig.add_trace(\n",
    "    go.Bar(\n",
    "        y=decade_mean.index,\n",
    "        x=decade_mean.iloc[:, 2],\n",
    "        name=decade_mean.columns[2],\n",
    "        orientation=\"h\",\n",
    "    ),\n",
    "    row=1,\n",
    "    col=3,\n",
    ")\n",
    "\n",
    "fig.add_trace(\n",
    "    go.Bar(\n",
    "        y=decade_mean.index,\n",
    "        x=decade_mean.iloc[:, 3],\n",
    "        name=decade_mean.columns[3],\n",
    "        orientation=\"h\",\n",
    "    ),\n",
    "    row=2,\n",
    "    col=1,\n",
    ")\n",
    "\n",
    "fig.add_trace(\n",
    "    go.Bar(\n",
    "        y=decade_mean.index,\n",
    "        x=decade_mean.iloc[:, 4],\n",
    "        name=decade_mean.columns[4],\n",
    "        orientation=\"h\",\n",
    "    ),\n",
    "    row=2,\n",
    "    col=2,\n",
    ")\n",
    "\n",
    "fig.add_trace(\n",
    "    go.Bar(\n",
    "        y=decade_mean.index,\n",
    "        x=decade_mean.iloc[:, 5],\n",
    "        name=decade_mean.columns[5],\n",
    "        orientation=\"h\",\n",
    "    ),\n",
    "    row=2,\n",
    "    col=3,\n",
    ")\n",
    "\n",
    "fig.add_trace(\n",
    "    go.Bar(\n",
    "        y=decade_mean.index,\n",
    "        x=decade_mean.iloc[:, 6],\n",
    "        name=decade_mean.columns[6],\n",
    "        orientation=\"h\",\n",
    "    ),\n",
    "    row=3,\n",
    "    col=1,\n",
    ")\n",
    "\n",
    "fig.add_trace(\n",
    "    go.Bar(\n",
    "        y=decade_mean.index,\n",
    "        x=decade_mean.iloc[:, 7],\n",
    "        name=decade_mean.columns[7],\n",
    "        orientation=\"h\",\n",
    "    ),\n",
    "    row=3,\n",
    "    col=2,\n",
    ")\n",
    "\n",
    "fig.add_trace(\n",
    "    go.Bar(\n",
    "        y=decade_mean.index,\n",
    "        x=decade_mean.iloc[:, 8],\n",
    "        name=decade_mean.columns[8],\n",
    "        orientation=\"h\",\n",
    "    ),\n",
    "    row=3,\n",
    "    col=3,\n",
    ")\n",
    "\n",
    "fig.add_trace(\n",
    "    go.Bar(\n",
    "        y=decade_mean.index,\n",
    "        x=decade_mean.iloc[:, 9],\n",
    "        name=decade_mean.columns[9],\n",
    "        orientation=\"h\",\n",
    "    ),\n",
    "    row=4,\n",
    "    col=1,\n",
    ")\n",
    "\n",
    "fig.add_trace(\n",
    "    go.Bar(\n",
    "        y=decade_mean.index,\n",
    "        x=decade_mean.iloc[:, 10],\n",
    "        name=decade_mean.columns[10],\n",
    "        orientation=\"h\",\n",
    "    ),\n",
    "    row=4,\n",
    "    col=2,\n",
    ")\n",
    "\n",
    "fig.update_layout(\n",
    "    title={\"text\": \"Mean Musical Values per Decade\", \"font\": {\"size\": 22}},\n",
    "    legend={\n",
    "        \"orientation\": \"v\",\n",
    "        \"yanchor\": \"top\",\n",
    "        \"y\": 0.2,\n",
    "        \"xanchor\": \"right\",\n",
    "        \"x\": 0.9,\n",
    "    },\n",
    "    margin={\"b\": 10, \"r\": 10},\n",
    "    height=980,\n",
    ")\n",
    "\n",
    "fig.show()\n",
    "\n",
    "del decade_mean"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "decade_median = df.groupby(\"decade\")[cols].median()\n",
    "\n",
    "fig = make_subplots(\n",
    "    rows=4,\n",
    "    cols=3,\n",
    "    subplot_titles=(\n",
    "        decade_median.columns[0],\n",
    "        decade_median.columns[1],\n",
    "        decade_median.columns[2],\n",
    "        decade_median.columns[3],\n",
    "        decade_median.columns[4],\n",
    "        decade_median.columns[5],\n",
    "        decade_median.columns[6],\n",
    "        decade_median.columns[7],\n",
    "        decade_median.columns[8],\n",
    "        decade_median.columns[9],\n",
    "        decade_median.columns[10],\n",
    "    ),\n",
    "    vertical_spacing=0.1,\n",
    ")\n",
    "\n",
    "fig.add_trace(\n",
    "    go.Bar(\n",
    "        y=decade_median.index,\n",
    "        x=decade_median.iloc[:, 0],\n",
    "        name=decade_median.columns[0],\n",
    "        orientation=\"h\",\n",
    "    ),\n",
    "    row=1,\n",
    "    col=1,\n",
    ")\n",
    "\n",
    "fig.add_trace(\n",
    "    go.Bar(\n",
    "        y=decade_median.index,\n",
    "        x=decade_median.iloc[:, 1],\n",
    "        name=decade_median.columns[1],\n",
    "        orientation=\"h\",\n",
    "    ),\n",
    "    row=1,\n",
    "    col=2,\n",
    ")\n",
    "\n",
    "fig.add_trace(\n",
    "    go.Bar(\n",
    "        y=decade_median.index,\n",
    "        x=decade_median.iloc[:, 2],\n",
    "        name=decade_median.columns[2],\n",
    "        orientation=\"h\",\n",
    "    ),\n",
    "    row=1,\n",
    "    col=3,\n",
    ")\n",
    "\n",
    "fig.add_trace(\n",
    "    go.Bar(\n",
    "        y=decade_median.index,\n",
    "        x=decade_median.iloc[:, 3],\n",
    "        name=decade_median.columns[3],\n",
    "        orientation=\"h\",\n",
    "    ),\n",
    "    row=2,\n",
    "    col=1,\n",
    ")\n",
    "\n",
    "fig.add_trace(\n",
    "    go.Bar(\n",
    "        y=decade_median.index,\n",
    "        x=decade_median.iloc[:, 4],\n",
    "        name=decade_median.columns[4],\n",
    "        orientation=\"h\",\n",
    "    ),\n",
    "    row=2,\n",
    "    col=2,\n",
    ")\n",
    "\n",
    "fig.add_trace(\n",
    "    go.Bar(\n",
    "        y=decade_median.index,\n",
    "        x=decade_median.iloc[:, 5],\n",
    "        name=decade_median.columns[5],\n",
    "        orientation=\"h\",\n",
    "    ),\n",
    "    row=2,\n",
    "    col=3,\n",
    ")\n",
    "\n",
    "fig.add_trace(\n",
    "    go.Bar(\n",
    "        y=decade_median.index,\n",
    "        x=decade_median.iloc[:, 6],\n",
    "        name=decade_median.columns[6],\n",
    "        orientation=\"h\",\n",
    "    ),\n",
    "    row=3,\n",
    "    col=1,\n",
    ")\n",
    "\n",
    "fig.add_trace(\n",
    "    go.Bar(\n",
    "        y=decade_median.index,\n",
    "        x=decade_median.iloc[:, 7],\n",
    "        name=decade_median.columns[7],\n",
    "        orientation=\"h\",\n",
    "    ),\n",
    "    row=3,\n",
    "    col=2,\n",
    ")\n",
    "\n",
    "fig.add_trace(\n",
    "    go.Bar(\n",
    "        y=decade_median.index,\n",
    "        x=decade_median.iloc[:, 8],\n",
    "        name=decade_median.columns[8],\n",
    "        orientation=\"h\",\n",
    "    ),\n",
    "    row=3,\n",
    "    col=3,\n",
    ")\n",
    "\n",
    "fig.add_trace(\n",
    "    go.Bar(\n",
    "        y=decade_median.index,\n",
    "        x=decade_median.iloc[:, 9],\n",
    "        name=decade_median.columns[9],\n",
    "        orientation=\"h\",\n",
    "    ),\n",
    "    row=4,\n",
    "    col=1,\n",
    ")\n",
    "\n",
    "fig.add_trace(\n",
    "    go.Bar(\n",
    "        y=decade_median.index,\n",
    "        x=decade_median.iloc[:, 10],\n",
    "        name=decade_median.columns[10],\n",
    "        orientation=\"h\",\n",
    "    ),\n",
    "    row=4,\n",
    "    col=2,\n",
    ")\n",
    "\n",
    "fig.update_layout(\n",
    "    title={\"text\": \"Median Musical Values per Decade\", \"font\": {\"size\": 22}},\n",
    "    legend={\n",
    "        \"orientation\": \"v\",\n",
    "        \"yanchor\": \"top\",\n",
    "        \"y\": 0.2,\n",
    "        \"xanchor\": \"right\",\n",
    "        \"x\": 0.9,\n",
    "    },\n",
    "    margin={\"b\": 10, \"r\": 10},\n",
    "    height=980,\n",
    ")\n",
    "\n",
    "fig.show()\n",
    "\n",
    "del decade_median"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "explicit_count = (\n",
    "    df.groupby([\"decade\", \"explicit\"], as_index=False)[\"year\"]\n",
    "    .count()\n",
    "    .rename(columns={\"year\": \"count\"})\n",
    ")\n",
    "key_count = (\n",
    "    df.groupby([\"decade\", \"key\"], as_index=False)[\"year\"]\n",
    "    .count()\n",
    "    .rename(columns={\"year\": \"count\"})\n",
    ")\n",
    "mode_count = (\n",
    "    df.groupby([\"decade\", \"mode\"], as_index=False)[\"year\"]\n",
    "    .count()\n",
    "    .rename(columns={\"year\": \"count\"})\n",
    ")\n",
    "\n",
    "fig = px.histogram(\n",
    "    data_frame=explicit_count,\n",
    "    x=\"decade\",\n",
    "    y=\"count\",\n",
    "    color=\"explicit\",\n",
    "    histfunc=\"sum\",\n",
    "    color_discrete_sequence=px.colors.qualitative.Pastel,\n",
    "    text_auto=True,\n",
    ")\n",
    "fig.update_layout(\n",
    "    title={\"text\": \"Explicit Count per Decade\", \"font\": {\"size\": 24}},\n",
    "    bargap=0.2,\n",
    "    bargroupgap=0.1,\n",
    "    barmode=\"group\",\n",
    "    xaxis_title=\"Decade\",\n",
    "    yaxis_title=\"Count\",\n",
    ")\n",
    "fig.show()\n",
    "\n",
    "fig = px.histogram(\n",
    "    data_frame=mode_count,\n",
    "    x=\"decade\",\n",
    "    y=\"count\",\n",
    "    color=\"mode\",\n",
    "    histfunc=\"sum\",\n",
    "    color_discrete_sequence=px.colors.qualitative.Pastel,\n",
    "    text_auto=True,\n",
    ")\n",
    "fig.update_layout(\n",
    "    title={\"text\": \"Mode Count per Decade\", \"font\": {\"size\": 24}},\n",
    "    bargap=0.2,\n",
    "    bargroupgap=0.1,\n",
    "    barmode=\"group\",\n",
    "    xaxis_title=\"Decade\",\n",
    "    yaxis_title=\"Count\",\n",
    ")\n",
    "fig.show()\n",
    "\n",
    "fig = px.histogram(\n",
    "    data_frame=key_count,\n",
    "    x=\"decade\",\n",
    "    y=\"count\",\n",
    "    color=\"key\",\n",
    "    histfunc=\"sum\",\n",
    "    color_discrete_sequence=px.colors.qualitative.Pastel,\n",
    "    text_auto=True,\n",
    ")\n",
    "fig.update_layout(\n",
    "    title={\"text\": \"Key Count per Decade\", \"font\": {\"size\": 24}},\n",
    "    bargap=0.2,\n",
    "    bargroupgap=0.1,\n",
    "    barmode=\"stack\",\n",
    "    xaxis_title=\"Decade\",\n",
    "    yaxis_title=\"Count\",\n",
    ")\n",
    "fig.show()\n",
    "\n",
    "del (mode_count, key_count, explicit_count)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "cols = [\n",
    "    \"valence\",\n",
    "    \"acousticness\",\n",
    "    \"danceability\",\n",
    "    \"duration_min\",\n",
    "    \"energy\",\n",
    "    \"instrumentalness\",\n",
    "    \"liveness\",\n",
    "    \"loudness\",\n",
    "    \"year\",\n",
    "    \"speechiness\",\n",
    "    \"tempo\",\n",
    "]\n",
    "\n",
    "for col in cols:\n",
    "\n",
    "    fig = px.scatter(\n",
    "        data_frame=df,\n",
    "        x=col,\n",
    "        y=\"popularity\",\n",
    "        trendline=\"ols\",\n",
    "        trendline_color_override=\"#A6E3A1\",\n",
    "    )\n",
    "    fig.update_traces(marker={\"opacity\": 0.3, \"size\": 3, \"color\": \"#B4BEFE\"})\n",
    "    fig.update_layout(title={\"text\": f\"{col} vs popularity\", \"font\": {\"size\": 24}})\n",
    "    fig.show()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Header 1\n",
    "\n",
    "## Header 2\n",
    "\n",
    "### Header 3.1"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "cols = [\n",
    "    \"valence\",\n",
    "    \"acousticness\",\n",
    "    \"danceability\",\n",
    "    \"duration_min\",\n",
    "    \"energy\",\n",
    "    \"instrumentalness\",\n",
    "    \"liveness\",\n",
    "    \"loudness\",\n",
    "    \"year\",\n",
    "    \"speechiness\",\n",
    "    \"tempo\",\n",
    "]\n",
    "\n",
    "plt.figure(figsize=(15, 10))\n",
    "\n",
    "for i, col in enumerate(cols):\n",
    "    ax = plt.subplot(3, 4, i + 1)\n",
    "    sns.regplot(\n",
    "        data=df,\n",
    "        x=\"popularity\",\n",
    "        y=col,\n",
    "        ax=ax,\n",
    "        scatter_kws={\"alpha\": 0.5},\n",
    "        line_kws={\"color\": \"#F38BA8\"},\n",
    "    )\n",
    "\n",
    "plt.tight_layout()\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "cols = [\n",
    "    \"valence\",\n",
    "    \"acousticness\",\n",
    "    \"danceability\",\n",
    "    \"duration_min\",\n",
    "    \"energy\",\n",
    "    \"instrumentalness\",\n",
    "    \"liveness\",\n",
    "    \"loudness\",\n",
    "    \"year\",\n",
    "    \"speechiness\",\n",
    "    \"tempo\",\n",
    "    \"popularity\",\n",
    "]\n",
    "\n",
    "plt.figure(figsize=(10, 7))\n",
    "mask = np.triu(np.ones_like(df[cols].corr()))\n",
    "sns.heatmap(\n",
    "    df[cols].corr(),\n",
    "    annot=True,\n",
    "    fmt=\".2f\",\n",
    "    cmap=\"Blues\",\n",
    "    mask=mask,\n",
    ")\n",
    "plt.grid(visible=False)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "df[\"first_artist\"] = (\n",
    "    df[\"artists\"]\n",
    "    .apply(lambda x: str(x).split(\"x\")[0])\n",
    "    .apply(lambda x: str(x).replace(\"[\", \"\"))\n",
    "    .apply(lambda x: str(x).replace(\"]\", \"\"))\n",
    "    .apply(lambda x: str(x).replace(\"'\", \"\"))\n",
    ")\n",
    "df = df.drop(\"artists\", axis=1)\n",
    "df[\"first_artist\"] = df[\"first_artist\"].apply(lambda x: str(x).split(\",\")[0])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "popularity_check = (\n",
    "    df.groupby([\"first_artist\"], as_index=False)[\"popularity\"]\n",
    "    .agg({\"mean\", \"count\", \"median\"})\n",
    "    .sort_values(by=\"mean\", ascending=False)\n",
    "    .reset_index(drop=True)\n",
    ")\n",
    "\n",
    "popularity_check = popularity_check.drop(16091, axis=0)\n",
    "popularity_check = popularity_check.drop(16086, axis=0)\n",
    "popularity_check = popularity_check.drop(16429, axis=0)\n",
    "\n",
    "to_drop = popularity_check[popularity_check[\"count\"] <= 45].index\n",
    "popularity_check = popularity_check.drop(to_drop)\n",
    "popularity_check = popularity_check.sort_values(by=\"mean\", ascending=False).head(50)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Header 1\n",
    "\n",
    "## Header 2\n",
    "\n",
    "### Header 3.1"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "top_50_artists = pd.DataFrame()\n",
    "\n",
    "for i in popularity_check[\"first_artist\"].unique():\n",
    "    artist = df.query(\"first_artist == @i\")\n",
    "    top_50_artists = pd.concat([top_50_artists, artist], axis=0)\n",
    "\n",
    "top_50_artists = top_50_artists.reset_index(drop=True)\n",
    "top_50_artists.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "plt.figure(figsize=(12, 8))\n",
    "(\n",
    "    top_50_artists[\"first_artist\"]\n",
    "    .value_counts()\n",
    "    .sort_values(ascending=True)\n",
    "    .plot(kind=\"barh\")\n",
    ")\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "top_50_artists[\"decade\"].value_counts().sort_values(ascending=True).plot(kind=\"barh\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "cols = [\n",
    "    \"valence\",\n",
    "    \"acousticness\",\n",
    "    \"danceability\",\n",
    "    \"duration_min\",\n",
    "    \"energy\",\n",
    "    \"instrumentalness\",\n",
    "    \"liveness\",\n",
    "    \"loudness\",\n",
    "    \"year\",\n",
    "    \"speechiness\",\n",
    "    \"tempo\",\n",
    "]\n",
    "\n",
    "plt.figure(figsize=(15, 10))\n",
    "\n",
    "for i, col in enumerate(cols):\n",
    "    ax = plt.subplot(3, 4, i + 1)\n",
    "    sns.kdeplot(data=top_50_artists, x=col, hue=\"first_artist\", legend=False)\n",
    "\n",
    "plt.tight_layout()\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Header 1\n",
    "\n",
    "## Header 2\n",
    "\n",
    "### Header 3.1"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "import pandas as pd\n",
    "import numpy as np\n",
    "import seaborn as sns\n",
    "import matplotlib.pyplot as plt\n",
    "import matplotlib as mpl\n",
    "import mplcatppuccin\n",
    "import plotly.express as px\n",
    "import plotly.graph_objects as go\n",
    "from plotly.subplots import make_subplots\n",
    "import plotly.figure_factory as ff\n",
    "import warnings\n",
    "import plotly.io as pio\n",
    "\n",
    "warnings.filterwarnings('ignore')\n",
    "\n",
    "pio.renderers.default = 'notebook_connected'\n",
    "pio.templates.default = 'plotly_dark'\n",
    "\n",
    "\n",
    "%matplotlib inline\n",
    "%config InlineBackend.figure_format = 'retina'\n",
    "pd.set_option('display.max_columns', None)\n",
    "pd.set_option('display.precision', 2)\n",
    "pd.set_option('display.colheader_justify', 'left')\n",
    "\n",
    "mpl.rc(\n",
    "    'figure',\n",
    "    autolayout=True,\n",
    "    titlesize=18\n",
    ")\n",
    "\n",
    "mpl.style.use(['ggplot', 'mocha'])\n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Header 3.2\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "df = pd.read_csv(\n",
    "    \"data.csv\",\n",
    "    parse_dates=[\"release_date\"],\n",
    ")\n",
    "df.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "map_key = {\n",
    "    0: \"C\",\n",
    "    1: \"C#\",\n",
    "    2: \"D\",\n",
    "    3: \"D#\",\n",
    "    4: \"E\",\n",
    "    5: \"F\",\n",
    "    6: \"F#\",\n",
    "    7: \"G\",\n",
    "    8: \"G#\",\n",
    "    9: \"A\",\n",
    "    10: \"A#\",\n",
    "    11: \"B\",\n",
    "}\n",
    "\n",
    "map_mode = {1: \"Major\", 0: \"Minor\"}\n",
    "\n",
    "df[\"mode\"] = df[\"mode\"].map(map_mode)\n",
    "df[\"key\"] = df[\"key\"].map(map_key)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "check_dups = df[[\"artists\", \"name\"]]\n",
    "dups = check_dups[check_dups.duplicated()].index"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "print(\"Before dropping duplicated:\", df.shape)\n",
    "df = df.drop(dups)\n",
    "print(\"After dropping duplicated:\", df.shape)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Header 1.3\n",
    "\n",
    "## Header 2.3\n",
    "\n",
    "### Header 3.5"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "df[\"duration_ms\"] = df[\"duration_ms\"] / 60_000\n",
    "df = df.rename(columns={\"duration_ms\": \"duration_min\"})\n",
    "df.head()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Header 1.4\n",
    "\n",
    "## Header 2.4\n",
    "\n",
    "### Header 3.5"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "df = df.drop([\"release_date\", \"id\"], axis=1)\n",
    "df.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "def fun_subplots_plotly(df, col):\n",
    "\n",
    "    mean_val = df[col].mean()\n",
    "    median_val = df[col].median()\n",
    "    fig = make_subplots(rows=1, cols=2, column_widths=[0.75, 0.25])\n",
    "\n",
    "    fig.add_trace(\n",
    "        go.Histogram(\n",
    "            x=df[col], name=f\"Histogram {col}\", marker={\"color\": \"#EBA0AC\"}, nbinsx=50\n",
    "        ),\n",
    "        row=1,\n",
    "        col=1,\n",
    "    )\n",
    "\n",
    "    fig.add_shape(\n",
    "        type=\"line\",\n",
    "        xref=\"paper\",\n",
    "        yref=\"y\",\n",
    "        x0=-1,\n",
    "        x1=1,\n",
    "        y0=mean_val,\n",
    "        y1=mean_val,\n",
    "        row=1,\n",
    "        col=2,\n",
    "        line={\"color\": \"#A6E3A1\", \"width\": 3, \"dash\": \"dot\"},\n",
    "    )\n",
    "\n",
    "    fig.add_shape(\n",
    "        type=\"line\",\n",
    "        xref=\"paper\",\n",
    "        yref=\"y\",\n",
    "        x0=-1,\n",
    "        x1=1,\n",
    "        y0=median_val,\n",
    "        y1=median_val,\n",
    "        row=1,\n",
    "        col=2,\n",
    "        line={\"color\": \"#CBA6F7\", \"width\": 3, \"dash\": \"dot\"},\n",
    "    )\n",
    "\n",
    "    fig.add_annotation(\n",
    "        xref=\"paper\",\n",
    "        x=-0.7,\n",
    "        y=mean_val,\n",
    "        showarrow=True,\n",
    "        arrowhead=2,\n",
    "        text=f\"Mean = {mean_val:.2f}\",\n",
    "        row=1,\n",
    "        col=2,\n",
    "    )\n",
    "\n",
    "    fig.add_annotation(\n",
    "        xref=\"paper\",\n",
    "        x=0.7,\n",
    "        y=median_val,\n",
    "        showarrow=True,\n",
    "        arrowhead=2,\n",
    "        text=f\"Median = {median_val:.2f}\",\n",
    "        row=1,\n",
    "        col=2,\n",
    "    )\n",
    "\n",
    "    fig.add_trace(\n",
    "        go.Box(y=df[col], name=f\"Boxplot {col}\", marker={\"color\": \"#F9E2AF\"}),\n",
    "        row=1,\n",
    "        col=2,\n",
    "    )\n",
    "\n",
    "    fig.update_layout(\n",
    "        title={\"text\": f\"Distribution Plot {col}\", \"font\": {\"size\": 24}},\n",
    "        legend={\n",
    "            \"orientation\": \"h\",\n",
    "            \"yanchor\": \"bottom\",\n",
    "            \"y\": 1.02,\n",
    "            \"xanchor\": \"right\",\n",
    "            \"x\": 1,\n",
    "        },\n",
    "    )\n",
    "    fig.update_yaxes(title_text=\"Count\", row=1, col=1)\n",
    "    fig.update_yaxes(title_text=f\"{col}\", row=1, col=2)\n",
    "    fig.update_xaxes(title_text=f\"{col}\", row=1, col=1)\n",
    "    fig.update_xaxes(title_text=\"\", row=1, col=2)\n",
    "    fig.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "music_vals = [\n",
    "    \"valence\",\n",
    "    \"acousticness\",\n",
    "    \"danceability\",\n",
    "    \"duration_min\",\n",
    "    \"energy\",\n",
    "    \"instrumentalness\",\n",
    "    \"liveness\",\n",
    "    \"loudness\",\n",
    "    \"popularity\",\n",
    "    \"speechiness\",\n",
    "    \"tempo\",\n",
    "]\n",
    "\n",
    "for col in music_vals:\n",
    "    fun_subplots_plotly(df, col)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Header 1.2\n",
    "\n",
    "## Header 2.2\n",
    "\n",
    "### Header 3.4"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "bins = pd.IntervalIndex.from_breaks(\n",
    "    [1920, 1930, 1940, 1950, 1960, 1970, 1980, 1990, 2000, 2010, 2020]\n",
    ")\n",
    "\n",
    "df[\"decade\"] = pd.cut(df[\"year\"], bins).astype(\"str\")\n",
    "\n",
    "map_decade = {\n",
    "    \"(1920, 1930]\": \"1920s\",\n",
    "    \"(1930, 1940]\": \"1930s\",\n",
    "    \"(1940, 1950]\": \"1940s\",\n",
    "    \"(1950, 1960]\": \"1950s\",\n",
    "    \"(1960, 1970]\": \"1960s\",\n",
    "    \"(1970, 1980]\": \"1970s\",\n",
    "    \"(1980, 1990]\": \"1980s\",\n",
    "    \"(1990, 2000]\": \"1990s\",\n",
    "    \"(2000, 2010]\": \"2000s\",\n",
    "    \"(2010, 2020]\": \"2010s\",\n",
    "}\n",
    "\n",
    "df[\"decade\"] = df[\"decade\"].map(map_decade)\n",
    "\n",
    "df.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "decade_counts = (\n",
    "    df[\"decade\"].value_counts().reset_index().sort_values(by=\"decade\", ascending=True)\n",
    ")\n",
    "\n",
    "fig = px.bar(\n",
    "    data_frame=decade_counts,\n",
    "    y=\"decade\",\n",
    "    x=\"count\",\n",
    "    color=\"count\",\n",
    "    color_continuous_scale=px.colors.sequential.Sunset,\n",
    "    text_auto=True,\n",
    ")\n",
    "\n",
    "fig.update_layout(\n",
    "    title={\"text\": \"Count of songs per decade\", \"font\": {\"size\": 24}},\n",
    "    coloraxis_colorbar={\n",
    "        \"title\": \"Count\",\n",
    "        \"thicknessmode\": \"pixels\",\n",
    "        \"thickness\": 20,\n",
    "        \"lenmode\": \"pixels\",\n",
    "        \"len\": 500,\n",
    "        \"yanchor\": \"top\",\n",
    "        \"xanchor\": \"right\",\n",
    "        \"y\": 1.15,\n",
    "        \"x\": 0.95,\n",
    "        \"orientation\": \"h\",\n",
    "    },\n",
    "    margin={\"r\": 10},\n",
    ")\n",
    "\n",
    "fig.update_xaxes(title=\"Count\")\n",
    "fig.update_yaxes(title=\"Decades\")\n",
    "fig.show()\n",
    "\n",
    "del decade_counts"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "df = df.query(\"duration_min <= 5\")"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Header 1.2\n",
    "\n",
    "## Header 2.2\n",
    "\n",
    "### Header 3.4"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "decade_counts = (\n",
    "    df[\"decade\"].value_counts().reset_index().sort_values(by=\"decade\", ascending=True)\n",
    ")\n",
    "\n",
    "fig = px.bar(\n",
    "    data_frame=decade_counts,\n",
    "    y=\"decade\",\n",
    "    x=\"count\",\n",
    "    color=\"count\",\n",
    "    color_continuous_scale=px.colors.sequential.Sunset,\n",
    "    text_auto=True,\n",
    ")\n",
    "\n",
    "fig.update_layout(\n",
    "    title={\"text\": \"Count of songs per decade (< 5min)\", \"font\": {\"size\": 24}},\n",
    "    coloraxis_colorbar={\n",
    "        \"title\": \"Count\",\n",
    "        \"thicknessmode\": \"pixels\",\n",
    "        \"thickness\": 20,\n",
    "        \"lenmode\": \"pixels\",\n",
    "        \"len\": 500,\n",
    "        \"yanchor\": \"top\",\n",
    "        \"xanchor\": \"right\",\n",
    "        \"y\": 1.15,\n",
    "        \"x\": 0.95,\n",
    "        \"orientation\": \"h\",\n",
    "    },\n",
    "    margin={\"r\": 10},\n",
    ")\n",
    "\n",
    "fig.update_xaxes(title=\"Count\")\n",
    "fig.update_yaxes(title=\"Decades\")\n",
    "fig.show()\n",
    "\n",
    "del decade_counts"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "cols = [\n",
    "    \"valence\",\n",
    "    \"acousticness\",\n",
    "    \"danceability\",\n",
    "    \"duration_min\",\n",
    "    \"energy\",\n",
    "    \"instrumentalness\",\n",
    "    \"liveness\",\n",
    "    \"loudness\",\n",
    "    \"popularity\",\n",
    "    \"speechiness\",\n",
    "    \"tempo\",\n",
    "]\n",
    "for col in cols:\n",
    "    fig = px.histogram(\n",
    "        data_frame=df,\n",
    "        x=col,\n",
    "        color=\"decade\",\n",
    "        color_discrete_sequence=px.colors.qualitative.Light24,\n",
    "    )\n",
    "    fig.update_traces(opacity=0.7)\n",
    "    fig.update_layout(\n",
    "        bargap=0.1,\n",
    "        bargroupgap=0.05,\n",
    "        barmode=\"stack\",\n",
    "        title={\"text\": f\"Histogram of {col} per decade\", \"font\": {\"size\": 24}},\n",
    "        legend={\"title\": \"Decade\"},\n",
    "    )\n",
    "    fig.update_yaxes(title=\"Count\")\n",
    "    fig.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "decade_mean = df.groupby(\"decade\")[cols].mean()\n",
    "\n",
    "fig = make_subplots(\n",
    "    rows=4,\n",
    "    cols=3,\n",
    "    subplot_titles=(\n",
    "        decade_mean.columns[0],\n",
    "        decade_mean.columns[1],\n",
    "        decade_mean.columns[2],\n",
    "        decade_mean.columns[3],\n",
    "        decade_mean.columns[4],\n",
    "        decade_mean.columns[5],\n",
    "        decade_mean.columns[6],\n",
    "        decade_mean.columns[7],\n",
    "        decade_mean.columns[8],\n",
    "        decade_mean.columns[9],\n",
    "        decade_mean.columns[10],\n",
    "    ),\n",
    "    vertical_spacing=0.1,\n",
    ")\n",
    "\n",
    "fig.add_trace(\n",
    "    go.Bar(\n",
    "        y=decade_mean.index,\n",
    "        x=decade_mean.iloc[:, 0],\n",
    "        name=decade_mean.columns[0],\n",
    "        orientation=\"h\",\n",
    "    ),\n",
    "    row=1,\n",
    "    col=1,\n",
    ")\n",
    "\n",
    "fig.add_trace(\n",
    "    go.Bar(\n",
    "        y=decade_mean.index,\n",
    "        x=decade_mean.iloc[:, 1],\n",
    "        name=decade_mean.columns[1],\n",
    "        orientation=\"h\",\n",
    "    ),\n",
    "    row=1,\n",
    "    col=2,\n",
    ")\n",
    "\n",
    "fig.add_trace(\n",
    "    go.Bar(\n",
    "        y=decade_mean.index,\n",
    "        x=decade_mean.iloc[:, 2],\n",
    "        name=decade_mean.columns[2],\n",
    "        orientation=\"h\",\n",
    "    ),\n",
    "    row=1,\n",
    "    col=3,\n",
    ")\n",
    "\n",
    "fig.add_trace(\n",
    "    go.Bar(\n",
    "        y=decade_mean.index,\n",
    "        x=decade_mean.iloc[:, 3],\n",
    "        name=decade_mean.columns[3],\n",
    "        orientation=\"h\",\n",
    "    ),\n",
    "    row=2,\n",
    "    col=1,\n",
    ")\n",
    "\n",
    "fig.add_trace(\n",
    "    go.Bar(\n",
    "        y=decade_mean.index,\n",
    "        x=decade_mean.iloc[:, 4],\n",
    "        name=decade_mean.columns[4],\n",
    "        orientation=\"h\",\n",
    "    ),\n",
    "    row=2,\n",
    "    col=2,\n",
    ")\n",
    "\n",
    "fig.add_trace(\n",
    "    go.Bar(\n",
    "        y=decade_mean.index,\n",
    "        x=decade_mean.iloc[:, 5],\n",
    "        name=decade_mean.columns[5],\n",
    "        orientation=\"h\",\n",
    "    ),\n",
    "    row=2,\n",
    "    col=3,\n",
    ")\n",
    "\n",
    "fig.add_trace(\n",
    "    go.Bar(\n",
    "        y=decade_mean.index,\n",
    "        x=decade_mean.iloc[:, 6],\n",
    "        name=decade_mean.columns[6],\n",
    "        orientation=\"h\",\n",
    "    ),\n",
    "    row=3,\n",
    "    col=1,\n",
    ")\n",
    "\n",
    "fig.add_trace(\n",
    "    go.Bar(\n",
    "        y=decade_mean.index,\n",
    "        x=decade_mean.iloc[:, 7],\n",
    "        name=decade_mean.columns[7],\n",
    "        orientation=\"h\",\n",
    "    ),\n",
    "    row=3,\n",
    "    col=2,\n",
    ")\n",
    "\n",
    "fig.add_trace(\n",
    "    go.Bar(\n",
    "        y=decade_mean.index,\n",
    "        x=decade_mean.iloc[:, 8],\n",
    "        name=decade_mean.columns[8],\n",
    "        orientation=\"h\",\n",
    "    ),\n",
    "    row=3,\n",
    "    col=3,\n",
    ")\n",
    "\n",
    "fig.add_trace(\n",
    "    go.Bar(\n",
    "        y=decade_mean.index,\n",
    "        x=decade_mean.iloc[:, 9],\n",
    "        name=decade_mean.columns[9],\n",
    "        orientation=\"h\",\n",
    "    ),\n",
    "    row=4,\n",
    "    col=1,\n",
    ")\n",
    "\n",
    "fig.add_trace(\n",
    "    go.Bar(\n",
    "        y=decade_mean.index,\n",
    "        x=decade_mean.iloc[:, 10],\n",
    "        name=decade_mean.columns[10],\n",
    "        orientation=\"h\",\n",
    "    ),\n",
    "    row=4,\n",
    "    col=2,\n",
    ")\n",
    "\n",
    "fig.update_layout(\n",
    "    title={\"text\": \"Mean Musical Values per Decade\", \"font\": {\"size\": 22}},\n",
    "    legend={\n",
    "        \"orientation\": \"v\",\n",
    "        \"yanchor\": \"top\",\n",
    "        \"y\": 0.2,\n",
    "        \"xanchor\": \"right\",\n",
    "        \"x\": 0.9,\n",
    "    },\n",
    "    margin={\"b\": 10, \"r\": 10},\n",
    "    height=980,\n",
    ")\n",
    "\n",
    "fig.show()\n",
    "\n",
    "del decade_mean"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "decade_median = df.groupby(\"decade\")[cols].median()\n",
    "\n",
    "fig = make_subplots(\n",
    "    rows=4,\n",
    "    cols=3,\n",
    "    subplot_titles=(\n",
    "        decade_median.columns[0],\n",
    "        decade_median.columns[1],\n",
    "        decade_median.columns[2],\n",
    "        decade_median.columns[3],\n",
    "        decade_median.columns[4],\n",
    "        decade_median.columns[5],\n",
    "        decade_median.columns[6],\n",
    "        decade_median.columns[7],\n",
    "        decade_median.columns[8],\n",
    "        decade_median.columns[9],\n",
    "        decade_median.columns[10],\n",
    "    ),\n",
    "    vertical_spacing=0.1,\n",
    ")\n",
    "\n",
    "fig.add_trace(\n",
    "    go.Bar(\n",
    "        y=decade_median.index,\n",
    "        x=decade_median.iloc[:, 0],\n",
    "        name=decade_median.columns[0],\n",
    "        orientation=\"h\",\n",
    "    ),\n",
    "    row=1,\n",
    "    col=1,\n",
    ")\n",
    "\n",
    "fig.add_trace(\n",
    "    go.Bar(\n",
    "        y=decade_median.index,\n",
    "        x=decade_median.iloc[:, 1],\n",
    "        name=decade_median.columns[1],\n",
    "        orientation=\"h\",\n",
    "    ),\n",
    "    row=1,\n",
    "    col=2,\n",
    ")\n",
    "\n",
    "fig.add_trace(\n",
    "    go.Bar(\n",
    "        y=decade_median.index,\n",
    "        x=decade_median.iloc[:, 2],\n",
    "        name=decade_median.columns[2],\n",
    "        orientation=\"h\",\n",
    "    ),\n",
    "    row=1,\n",
    "    col=3,\n",
    ")\n",
    "\n",
    "fig.add_trace(\n",
    "    go.Bar(\n",
    "        y=decade_median.index,\n",
    "        x=decade_median.iloc[:, 3],\n",
    "        name=decade_median.columns[3],\n",
    "        orientation=\"h\",\n",
    "    ),\n",
    "    row=2,\n",
    "    col=1,\n",
    ")\n",
    "\n",
    "fig.add_trace(\n",
    "    go.Bar(\n",
    "        y=decade_median.index,\n",
    "        x=decade_median.iloc[:, 4],\n",
    "        name=decade_median.columns[4],\n",
    "        orientation=\"h\",\n",
    "    ),\n",
    "    row=2,\n",
    "    col=2,\n",
    ")\n",
    "\n",
    "fig.add_trace(\n",
    "    go.Bar(\n",
    "        y=decade_median.index,\n",
    "        x=decade_median.iloc[:, 5],\n",
    "        name=decade_median.columns[5],\n",
    "        orientation=\"h\",\n",
    "    ),\n",
    "    row=2,\n",
    "    col=3,\n",
    ")\n",
    "\n",
    "fig.add_trace(\n",
    "    go.Bar(\n",
    "        y=decade_median.index,\n",
    "        x=decade_median.iloc[:, 6],\n",
    "        name=decade_median.columns[6],\n",
    "        orientation=\"h\",\n",
    "    ),\n",
    "    row=3,\n",
    "    col=1,\n",
    ")\n",
    "\n",
    "fig.add_trace(\n",
    "    go.Bar(\n",
    "        y=decade_median.index,\n",
    "        x=decade_median.iloc[:, 7],\n",
    "        name=decade_median.columns[7],\n",
    "        orientation=\"h\",\n",
    "    ),\n",
    "    row=3,\n",
    "    col=2,\n",
    ")\n",
    "\n",
    "fig.add_trace(\n",
    "    go.Bar(\n",
    "        y=decade_median.index,\n",
    "        x=decade_median.iloc[:, 8],\n",
    "        name=decade_median.columns[8],\n",
    "        orientation=\"h\",\n",
    "    ),\n",
    "    row=3,\n",
    "    col=3,\n",
    ")\n",
    "\n",
    "fig.add_trace(\n",
    "    go.Bar(\n",
    "        y=decade_median.index,\n",
    "        x=decade_median.iloc[:, 9],\n",
    "        name=decade_median.columns[9],\n",
    "        orientation=\"h\",\n",
    "    ),\n",
    "    row=4,\n",
    "    col=1,\n",
    ")\n",
    "\n",
    "fig.add_trace(\n",
    "    go.Bar(\n",
    "        y=decade_median.index,\n",
    "        x=decade_median.iloc[:, 10],\n",
    "        name=decade_median.columns[10],\n",
    "        orientation=\"h\",\n",
    "    ),\n",
    "    row=4,\n",
    "    col=2,\n",
    ")\n",
    "\n",
    "fig.update_layout(\n",
    "    title={\"text\": \"Median Musical Values per Decade\", \"font\": {\"size\": 22}},\n",
    "    legend={\n",
    "        \"orientation\": \"v\",\n",
    "        \"yanchor\": \"top\",\n",
    "        \"y\": 0.2,\n",
    "        \"xanchor\": \"right\",\n",
    "        \"x\": 0.9,\n",
    "    },\n",
    "    margin={\"b\": 10, \"r\": 10},\n",
    "    height=980,\n",
    ")\n",
    "\n",
    "fig.show()\n",
    "\n",
    "del decade_median"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "explicit_count = (\n",
    "    df.groupby([\"decade\", \"explicit\"], as_index=False)[\"year\"]\n",
    "    .count()\n",
    "    .rename(columns={\"year\": \"count\"})\n",
    ")\n",
    "key_count = (\n",
    "    df.groupby([\"decade\", \"key\"], as_index=False)[\"year\"]\n",
    "    .count()\n",
    "    .rename(columns={\"year\": \"count\"})\n",
    ")\n",
    "mode_count = (\n",
    "    df.groupby([\"decade\", \"mode\"], as_index=False)[\"year\"]\n",
    "    .count()\n",
    "    .rename(columns={\"year\": \"count\"})\n",
    ")\n",
    "\n",
    "fig = px.histogram(\n",
    "    data_frame=explicit_count,\n",
    "    x=\"decade\",\n",
    "    y=\"count\",\n",
    "    color=\"explicit\",\n",
    "    histfunc=\"sum\",\n",
    "    color_discrete_sequence=px.colors.qualitative.Pastel,\n",
    "    text_auto=True,\n",
    ")\n",
    "fig.update_layout(\n",
    "    title={\"text\": \"Explicit Count per Decade\", \"font\": {\"size\": 24}},\n",
    "    bargap=0.2,\n",
    "    bargroupgap=0.1,\n",
    "    barmode=\"group\",\n",
    "    xaxis_title=\"Decade\",\n",
    "    yaxis_title=\"Count\",\n",
    ")\n",
    "fig.show()\n",
    "\n",
    "fig = px.histogram(\n",
    "    data_frame=mode_count,\n",
    "    x=\"decade\",\n",
    "    y=\"count\",\n",
    "    color=\"mode\",\n",
    "    histfunc=\"sum\",\n",
    "    color_discrete_sequence=px.colors.qualitative.Pastel,\n",
    "    text_auto=True,\n",
    ")\n",
    "fig.update_layout(\n",
    "    title={\"text\": \"Mode Count per Decade\", \"font\": {\"size\": 24}},\n",
    "    bargap=0.2,\n",
    "    bargroupgap=0.1,\n",
    "    barmode=\"group\",\n",
    "    xaxis_title=\"Decade\",\n",
    "    yaxis_title=\"Count\",\n",
    ")\n",
    "fig.show()\n",
    "\n",
    "fig = px.histogram(\n",
    "    data_frame=key_count,\n",
    "    x=\"decade\",\n",
    "    y=\"count\",\n",
    "    color=\"key\",\n",
    "    histfunc=\"sum\",\n",
    "    color_discrete_sequence=px.colors.qualitative.Pastel,\n",
    "    text_auto=True,\n",
    ")\n",
    "fig.update_layout(\n",
    "    title={\"text\": \"Key Count per Decade\", \"font\": {\"size\": 24}},\n",
    "    bargap=0.2,\n",
    "    bargroupgap=0.1,\n",
    "    barmode=\"stack\",\n",
    "    xaxis_title=\"Decade\",\n",
    "    yaxis_title=\"Count\",\n",
    ")\n",
    "fig.show()\n",
    "\n",
    "del (mode_count, key_count, explicit_count)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "cols = [\n",
    "    \"valence\",\n",
    "    \"acousticness\",\n",
    "    \"danceability\",\n",
    "    \"duration_min\",\n",
    "    \"energy\",\n",
    "    \"instrumentalness\",\n",
    "    \"liveness\",\n",
    "    \"loudness\",\n",
    "    \"year\",\n",
    "    \"speechiness\",\n",
    "    \"tempo\",\n",
    "]\n",
    "\n",
    "for col in cols:\n",
    "\n",
    "    fig = px.scatter(\n",
    "        data_frame=df,\n",
    "        x=col,\n",
    "        y=\"popularity\",\n",
    "        trendline=\"ols\",\n",
    "        trendline_color_override=\"#A6E3A1\",\n",
    "    )\n",
    "    fig.update_traces(marker={\"opacity\": 0.3, \"size\": 3, \"color\": \"#B4BEFE\"})\n",
    "    fig.update_layout(title={\"text\": f\"{col} vs popularity\", \"font\": {\"size\": 24}})\n",
    "    fig.show()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Header 1\n",
    "\n",
    "## Header 2\n",
    "\n",
    "### Header 3.1"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "cols = [\n",
    "    \"valence\",\n",
    "    \"acousticness\",\n",
    "    \"danceability\",\n",
    "    \"duration_min\",\n",
    "    \"energy\",\n",
    "    \"instrumentalness\",\n",
    "    \"liveness\",\n",
    "    \"loudness\",\n",
    "    \"year\",\n",
    "    \"speechiness\",\n",
    "    \"tempo\",\n",
    "]\n",
    "\n",
    "plt.figure(figsize=(15, 10))\n",
    "\n",
    "for i, col in enumerate(cols):\n",
    "    ax = plt.subplot(3, 4, i + 1)\n",
    "    sns.regplot(\n",
    "        data=df,\n",
    "        x=\"popularity\",\n",
    "        y=col,\n",
    "        ax=ax,\n",
    "        scatter_kws={\"alpha\": 0.5},\n",
    "        line_kws={\"color\": \"#F38BA8\"},\n",
    "    )\n",
    "\n",
    "plt.tight_layout()\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "cols = [\n",
    "    \"valence\",\n",
    "    \"acousticness\",\n",
    "    \"danceability\",\n",
    "    \"duration_min\",\n",
    "    \"energy\",\n",
    "    \"instrumentalness\",\n",
    "    \"liveness\",\n",
    "    \"loudness\",\n",
    "    \"year\",\n",
    "    \"speechiness\",\n",
    "    \"tempo\",\n",
    "    \"popularity\",\n",
    "]\n",
    "\n",
    "plt.figure(figsize=(10, 7))\n",
    "mask = np.triu(np.ones_like(df[cols].corr()))\n",
    "sns.heatmap(\n",
    "    df[cols].corr(),\n",
    "    annot=True,\n",
    "    fmt=\".2f\",\n",
    "    cmap=\"Blues\",\n",
    "    mask=mask,\n",
    ")\n",
    "plt.grid(visible=False)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "df[\"first_artist\"] = (\n",
    "    df[\"artists\"]\n",
    "    .apply(lambda x: str(x).split(\"x\")[0])\n",
    "    .apply(lambda x: str(x).replace(\"[\", \"\"))\n",
    "    .apply(lambda x: str(x).replace(\"]\", \"\"))\n",
    "    .apply(lambda x: str(x).replace(\"'\", \"\"))\n",
    ")\n",
    "df = df.drop(\"artists\", axis=1)\n",
    "df[\"first_artist\"] = df[\"first_artist\"].apply(lambda x: str(x).split(\",\")[0])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "popularity_check = (\n",
    "    df.groupby([\"first_artist\"], as_index=False)[\"popularity\"]\n",
    "    .agg({\"mean\", \"count\", \"median\"})\n",
    "    .sort_values(by=\"mean\", ascending=False)\n",
    "    .reset_index(drop=True)\n",
    ")\n",
    "\n",
    "popularity_check = popularity_check.drop(16091, axis=0)\n",
    "popularity_check = popularity_check.drop(16086, axis=0)\n",
    "popularity_check = popularity_check.drop(16429, axis=0)\n",
    "\n",
    "to_drop = popularity_check[popularity_check[\"count\"] <= 45].index\n",
    "popularity_check = popularity_check.drop(to_drop)\n",
    "popularity_check = popularity_check.sort_values(by=\"mean\", ascending=False).head(50)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Header 1\n",
    "\n",
    "## Header 2\n",
    "\n",
    "### Header 3.1"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "top_50_artists = pd.DataFrame()\n",
    "\n",
    "for i in popularity_check[\"first_artist\"].unique():\n",
    "    artist = df.query(\"first_artist == @i\")\n",
    "    top_50_artists = pd.concat([top_50_artists, artist], axis=0)\n",
    "\n",
    "top_50_artists = top_50_artists.reset_index(drop=True)\n",
    "top_50_artists.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "plt.figure(figsize=(12, 8))\n",
    "(\n",
    "    top_50_artists[\"first_artist\"]\n",
    "    .value_counts()\n",
    "    .sort_values(ascending=True)\n",
    "    .plot(kind=\"barh\")\n",
    ")\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "top_50_artists[\"decade\"].value_counts().sort_values(ascending=True).plot(kind=\"barh\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "cols = [\n",
    "    \"valence\",\n",
    "    \"acousticness\",\n",
    "    \"danceability\",\n",
    "    \"duration_min\",\n",
    "    \"energy\",\n",
    "    \"instrumentalness\",\n",
    "    \"liveness\",\n",
    "    \"loudness\",\n",
    "    \"year\",\n",
    "    \"speechiness\",\n",
    "    \"tempo\",\n",
    "]\n",
    "\n",
    "plt.figure(figsize=(15, 10))\n",
    "\n",
    "for i, col in enumerate(cols):\n",
    "    ax = plt.subplot(3, 4, i + 1)\n",
    "    sns.kdeplot(data=top_50_artists, x=col, hue=\"first_artist\", legend=False)\n",
    "\n",
    "plt.tight_layout()\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Header 1\n",
    "\n",
    "## Header 2\n",
    "\n",
    "### Header 3.1"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "bins = pd.IntervalIndex.from_breaks(\n",
    "    [1920, 1930, 1940, 1950, 1960, 1970, 1980, 1990, 2000, 2010, 2020]\n",
    ")\n",
    "\n",
    "df[\"decade\"] = pd.cut(df[\"year\"], bins).astype(\"str\")\n",
    "\n",
    "map_decade = {\n",
    "    \"(1920, 1930]\": \"1920s\",\n",
    "    \"(1930, 1940]\": \"1930s\",\n",
    "    \"(1940, 1950]\": \"1940s\",\n",
    "    \"(1950, 1960]\": \"1950s\",\n",
    "    \"(1960, 1970]\": \"1960s\",\n",
    "    \"(1970, 1980]\": \"1970s\",\n",
    "    \"(1980, 1990]\": \"1980s\",\n",
    "    \"(1990, 2000]\": \"1990s\",\n",
    "    \"(2000, 2010]\": \"2000s\",\n",
    "    \"(2010, 2020]\": \"2010s\",\n",
    "}\n",
    "\n",
    "df[\"decade\"] = df[\"decade\"].map(map_decade)\n",
    "\n",
    "df.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "decade_counts = (\n",
    "    df[\"decade\"].value_counts().reset_index().sort_values(by=\"decade\", ascending=True)\n",
    ")\n",
    "\n",
    "fig = px.bar(\n",
    "    data_frame=decade_counts,\n",
    "    y=\"decade\",\n",
    "    x=\"count\",\n",
    "    color=\"count\",\n",
    "    color_continuous_scale=px.colors.sequential.Sunset,\n",
    "    text_auto=True,\n",
    ")\n",
    "\n",
    "fig.update_layout(\n",
    "    title={\"text\": \"Count of songs per decade\", \"font\": {\"size\": 24}},\n",
    "    coloraxis_colorbar={\n",
    "        \"title\": \"Count\",\n",
    "        \"thicknessmode\": \"pixels\",\n",
    "        \"thickness\": 20,\n",
    "        \"lenmode\": \"pixels\",\n",
    "        \"len\": 500,\n",
    "        \"yanchor\": \"top\",\n",
    "        \"xanchor\": \"right\",\n",
    "        \"y\": 1.15,\n",
    "        \"x\": 0.95,\n",
    "        \"orientation\": \"h\",\n",
    "    },\n",
    "    margin={\"r\": 10},\n",
    ")\n",
    "\n",
    "fig.update_xaxes(title=\"Count\")\n",
    "fig.update_yaxes(title=\"Decades\")\n",
    "fig.show()\n",
    "\n",
    "del decade_counts"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "df = df.query(\"duration_min <= 5\")"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Header 1.2\n",
    "\n",
    "## Header 2.2\n",
    "\n",
    "### Header 3.4"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "decade_counts = (\n",
    "    df[\"decade\"].value_counts().reset_index().sort_values(by=\"decade\", ascending=True)\n",
    ")\n",
    "\n",
    "fig = px.bar(\n",
    "    data_frame=decade_counts,\n",
    "    y=\"decade\",\n",
    "    x=\"count\",\n",
    "    color=\"count\",\n",
    "    color_continuous_scale=px.colors.sequential.Sunset,\n",
    "    text_auto=True,\n",
    ")\n",
    "\n",
    "fig.update_layout(\n",
    "    title={\"text\": \"Count of songs per decade (< 5min)\", \"font\": {\"size\": 24}},\n",
    "    coloraxis_colorbar={\n",
    "        \"title\": \"Count\",\n",
    "        \"thicknessmode\": \"pixels\",\n",
    "        \"thickness\": 20,\n",
    "        \"lenmode\": \"pixels\",\n",
    "        \"len\": 500,\n",
    "        \"yanchor\": \"top\",\n",
    "        \"xanchor\": \"right\",\n",
    "        \"y\": 1.15,\n",
    "        \"x\": 0.95,\n",
    "        \"orientation\": \"h\",\n",
    "    },\n",
    "    margin={\"r\": 10},\n",
    ")\n",
    "\n",
    "fig.update_xaxes(title=\"Count\")\n",
    "fig.update_yaxes(title=\"Decades\")\n",
    "fig.show()\n",
    "\n",
    "del decade_counts"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "cols = [\n",
    "    \"valence\",\n",
    "    \"acousticness\",\n",
    "    \"danceability\",\n",
    "    \"duration_min\",\n",
    "    \"energy\",\n",
    "    \"instrumentalness\",\n",
    "    \"liveness\",\n",
    "    \"loudness\",\n",
    "    \"popularity\",\n",
    "    \"speechiness\",\n",
    "    \"tempo\",\n",
    "]\n",
    "for col in cols:\n",
    "    fig = px.histogram(\n",
    "        data_frame=df,\n",
    "        x=col,\n",
    "        color=\"decade\",\n",
    "        color_discrete_sequence=px.colors.qualitative.Light24,\n",
    "    )\n",
    "    fig.update_traces(opacity=0.7)\n",
    "    fig.update_layout(\n",
    "        bargap=0.1,\n",
    "        bargroupgap=0.05,\n",
    "        barmode=\"stack\",\n",
    "        title={\"text\": f\"Histogram of {col} per decade\", \"font\": {\"size\": 24}},\n",
    "        legend={\"title\": \"Decade\"},\n",
    "    )\n",
    "    fig.update_yaxes(title=\"Count\")\n",
    "    fig.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "decade_mean = df.groupby(\"decade\")[cols].mean()\n",
    "\n",
    "fig = make_subplots(\n",
    "    rows=4,\n",
    "    cols=3,\n",
    "    subplot_titles=(\n",
    "        decade_mean.columns[0],\n",
    "        decade_mean.columns[1],\n",
    "        decade_mean.columns[2],\n",
    "        decade_mean.columns[3],\n",
    "        decade_mean.columns[4],\n",
    "        decade_mean.columns[5],\n",
    "        decade_mean.columns[6],\n",
    "        decade_mean.columns[7],\n",
    "        decade_mean.columns[8],\n",
    "        decade_mean.columns[9],\n",
    "        decade_mean.columns[10],\n",
    "    ),\n",
    "    vertical_spacing=0.1,\n",
    ")\n",
    "\n",
    "fig.add_trace(\n",
    "    go.Bar(\n",
    "        y=decade_mean.index,\n",
    "        x=decade_mean.iloc[:, 0],\n",
    "        name=decade_mean.columns[0],\n",
    "        orientation=\"h\",\n",
    "    ),\n",
    "    row=1,\n",
    "    col=1,\n",
    ")\n",
    "\n",
    "fig.add_trace(\n",
    "    go.Bar(\n",
    "        y=decade_mean.index,\n",
    "        x=decade_mean.iloc[:, 1],\n",
    "        name=decade_mean.columns[1],\n",
    "        orientation=\"h\",\n",
    "    ),\n",
    "    row=1,\n",
    "    col=2,\n",
    ")\n",
    "\n",
    "fig.add_trace(\n",
    "    go.Bar(\n",
    "        y=decade_mean.index,\n",
    "        x=decade_mean.iloc[:, 2],\n",
    "        name=decade_mean.columns[2],\n",
    "        orientation=\"h\",\n",
    "    ),\n",
    "    row=1,\n",
    "    col=3,\n",
    ")\n",
    "\n",
    "fig.add_trace(\n",
    "    go.Bar(\n",
    "        y=decade_mean.index,\n",
    "        x=decade_mean.iloc[:, 3],\n",
    "        name=decade_mean.columns[3],\n",
    "        orientation=\"h\",\n",
    "    ),\n",
    "    row=2,\n",
    "    col=1,\n",
    ")\n",
    "\n",
    "fig.add_trace(\n",
    "    go.Bar(\n",
    "        y=decade_mean.index,\n",
    "        x=decade_mean.iloc[:, 4],\n",
    "        name=decade_mean.columns[4],\n",
    "        orientation=\"h\",\n",
    "    ),\n",
    "    row=2,\n",
    "    col=2,\n",
    ")\n",
    "\n",
    "fig.add_trace(\n",
    "    go.Bar(\n",
    "        y=decade_mean.index,\n",
    "        x=decade_mean.iloc[:, 5],\n",
    "        name=decade_mean.columns[5],\n",
    "        orientation=\"h\",\n",
    "    ),\n",
    "    row=2,\n",
    "    col=3,\n",
    ")\n",
    "\n",
    "fig.add_trace(\n",
    "    go.Bar(\n",
    "        y=decade_mean.index,\n",
    "        x=decade_mean.iloc[:, 6],\n",
    "        name=decade_mean.columns[6],\n",
    "        orientation=\"h\",\n",
    "    ),\n",
    "    row=3,\n",
    "    col=1,\n",
    ")\n",
    "\n",
    "fig.add_trace(\n",
    "    go.Bar(\n",
    "        y=decade_mean.index,\n",
    "        x=decade_mean.iloc[:, 7],\n",
    "        name=decade_mean.columns[7],\n",
    "        orientation=\"h\",\n",
    "    ),\n",
    "    row=3,\n",
    "    col=2,\n",
    ")\n",
    "\n",
    "fig.add_trace(\n",
    "    go.Bar(\n",
    "        y=decade_mean.index,\n",
    "        x=decade_mean.iloc[:, 8],\n",
    "        name=decade_mean.columns[8],\n",
    "        orientation=\"h\",\n",
    "    ),\n",
    "    row=3,\n",
    "    col=3,\n",
    ")\n",
    "\n",
    "fig.add_trace(\n",
    "    go.Bar(\n",
    "        y=decade_mean.index,\n",
    "        x=decade_mean.iloc[:, 9],\n",
    "        name=decade_mean.columns[9],\n",
    "        orientation=\"h\",\n",
    "    ),\n",
    "    row=4,\n",
    "    col=1,\n",
    ")\n",
    "\n",
    "fig.add_trace(\n",
    "    go.Bar(\n",
    "        y=decade_mean.index,\n",
    "        x=decade_mean.iloc[:, 10],\n",
    "        name=decade_mean.columns[10],\n",
    "        orientation=\"h\",\n",
    "    ),\n",
    "    row=4,\n",
    "    col=2,\n",
    ")\n",
    "\n",
    "fig.update_layout(\n",
    "    title={\"text\": \"Mean Musical Values per Decade\", \"font\": {\"size\": 22}},\n",
    "    legend={\n",
    "        \"orientation\": \"v\",\n",
    "        \"yanchor\": \"top\",\n",
    "        \"y\": 0.2,\n",
    "        \"xanchor\": \"right\",\n",
    "        \"x\": 0.9,\n",
    "    },\n",
    "    margin={\"b\": 10, \"r\": 10},\n",
    "    height=980,\n",
    ")\n",
    "\n",
    "fig.show()\n",
    "\n",
    "del decade_mean"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "decade_median = df.groupby(\"decade\")[cols].median()\n",
    "\n",
    "fig = make_subplots(\n",
    "    rows=4,\n",
    "    cols=3,\n",
    "    subplot_titles=(\n",
    "        decade_median.columns[0],\n",
    "        decade_median.columns[1],\n",
    "        decade_median.columns[2],\n",
    "        decade_median.columns[3],\n",
    "        decade_median.columns[4],\n",
    "        decade_median.columns[5],\n",
    "        decade_median.columns[6],\n",
    "        decade_median.columns[7],\n",
    "        decade_median.columns[8],\n",
    "        decade_median.columns[9],\n",
    "        decade_median.columns[10],\n",
    "    ),\n",
    "    vertical_spacing=0.1,\n",
    ")\n",
    "\n",
    "fig.add_trace(\n",
    "    go.Bar(\n",
    "        y=decade_median.index,\n",
    "        x=decade_median.iloc[:, 0],\n",
    "        name=decade_median.columns[0],\n",
    "        orientation=\"h\",\n",
    "    ),\n",
    "    row=1,\n",
    "    col=1,\n",
    ")\n",
    "\n",
    "fig.add_trace(\n",
    "    go.Bar(\n",
    "        y=decade_median.index,\n",
    "        x=decade_median.iloc[:, 1],\n",
    "        name=decade_median.columns[1],\n",
    "        orientation=\"h\",\n",
    "    ),\n",
    "    row=1,\n",
    "    col=2,\n",
    ")\n",
    "\n",
    "fig.add_trace(\n",
    "    go.Bar(\n",
    "        y=decade_median.index,\n",
    "        x=decade_median.iloc[:, 2],\n",
    "        name=decade_median.columns[2],\n",
    "        orientation=\"h\",\n",
    "    ),\n",
    "    row=1,\n",
    "    col=3,\n",
    ")\n",
    "\n",
    "fig.add_trace(\n",
    "    go.Bar(\n",
    "        y=decade_median.index,\n",
    "        x=decade_median.iloc[:, 3],\n",
    "        name=decade_median.columns[3],\n",
    "        orientation=\"h\",\n",
    "    ),\n",
    "    row=2,\n",
    "    col=1,\n",
    ")\n",
    "\n",
    "fig.add_trace(\n",
    "    go.Bar(\n",
    "        y=decade_median.index,\n",
    "        x=decade_median.iloc[:, 4],\n",
    "        name=decade_median.columns[4],\n",
    "        orientation=\"h\",\n",
    "    ),\n",
    "    row=2,\n",
    "    col=2,\n",
    ")\n",
    "\n",
    "fig.add_trace(\n",
    "    go.Bar(\n",
    "        y=decade_median.index,\n",
    "        x=decade_median.iloc[:, 5],\n",
    "        name=decade_median.columns[5],\n",
    "        orientation=\"h\",\n",
    "    ),\n",
    "    row=2,\n",
    "    col=3,\n",
    ")\n",
    "\n",
    "fig.add_trace(\n",
    "    go.Bar(\n",
    "        y=decade_median.index,\n",
    "        x=decade_median.iloc[:, 6],\n",
    "        name=decade_median.columns[6],\n",
    "        orientation=\"h\",\n",
    "    ),\n",
    "    row=3,\n",
    "    col=1,\n",
    ")\n",
    "\n",
    "fig.add_trace(\n",
    "    go.Bar(\n",
    "        y=decade_median.index,\n",
    "        x=decade_median.iloc[:, 7],\n",
    "        name=decade_median.columns[7],\n",
    "        orientation=\"h\",\n",
    "    ),\n",
    "    row=3,\n",
    "    col=2,\n",
    ")\n",
    "\n",
    "fig.add_trace(\n",
    "    go.Bar(\n",
    "        y=decade_median.index,\n",
    "        x=decade_median.iloc[:, 8],\n",
    "        name=decade_median.columns[8],\n",
    "        orientation=\"h\",\n",
    "    ),\n",
    "    row=3,\n",
    "    col=3,\n",
    ")\n",
    "\n",
    "fig.add_trace(\n",
    "    go.Bar(\n",
    "        y=decade_median.index,\n",
    "        x=decade_median.iloc[:, 9],\n",
    "        name=decade_median.columns[9],\n",
    "        orientation=\"h\",\n",
    "    ),\n",
    "    row=4,\n",
    "    col=1,\n",
    ")\n",
    "\n",
    "fig.add_trace(\n",
    "    go.Bar(\n",
    "        y=decade_median.index,\n",
    "        x=decade_median.iloc[:, 10],\n",
    "        name=decade_median.columns[10],\n",
    "        orientation=\"h\",\n",
    "    ),\n",
    "    row=4,\n",
    "    col=2,\n",
    ")\n",
    "\n",
    "fig.update_layout(\n",
    "    title={\"text\": \"Median Musical Values per Decade\", \"font\": {\"size\": 22}},\n",
    "    legend={\n",
    "        \"orientation\": \"v\",\n",
    "        \"yanchor\": \"top\",\n",
    "        \"y\": 0.2,\n",
    "        \"xanchor\": \"right\",\n",
    "        \"x\": 0.9,\n",
    "    },\n",
    "    margin={\"b\": 10, \"r\": 10},\n",
    "    height=980,\n",
    ")\n",
    "\n",
    "fig.show()\n",
    "\n",
    "del decade_median"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "explicit_count = (\n",
    "    df.groupby([\"decade\", \"explicit\"], as_index=False)[\"year\"]\n",
    "    .count()\n",
    "    .rename(columns={\"year\": \"count\"})\n",
    ")\n",
    "key_count = (\n",
    "    df.groupby([\"decade\", \"key\"], as_index=False)[\"year\"]\n",
    "    .count()\n",
    "    .rename(columns={\"year\": \"count\"})\n",
    ")\n",
    "mode_count = (\n",
    "    df.groupby([\"decade\", \"mode\"], as_index=False)[\"year\"]\n",
    "    .count()\n",
    "    .rename(columns={\"year\": \"count\"})\n",
    ")\n",
    "\n",
    "fig = px.histogram(\n",
    "    data_frame=explicit_count,\n",
    "    x=\"decade\",\n",
    "    y=\"count\",\n",
    "    color=\"explicit\",\n",
    "    histfunc=\"sum\",\n",
    "    color_discrete_sequence=px.colors.qualitative.Pastel,\n",
    "    text_auto=True,\n",
    ")\n",
    "fig.update_layout(\n",
    "    title={\"text\": \"Explicit Count per Decade\", \"font\": {\"size\": 24}},\n",
    "    bargap=0.2,\n",
    "    bargroupgap=0.1,\n",
    "    barmode=\"group\",\n",
    "    xaxis_title=\"Decade\",\n",
    "    yaxis_title=\"Count\",\n",
    ")\n",
    "fig.show()\n",
    "\n",
    "fig = px.histogram(\n",
    "    data_frame=mode_count,\n",
    "    x=\"decade\",\n",
    "    y=\"count\",\n",
    "    color=\"mode\",\n",
    "    histfunc=\"sum\",\n",
    "    color_discrete_sequence=px.colors.qualitative.Pastel,\n",
    "    text_auto=True,\n",
    ")\n",
    "fig.update_layout(\n",
    "    title={\"text\": \"Mode Count per Decade\", \"font\": {\"size\": 24}},\n",
    "    bargap=0.2,\n",
    "    bargroupgap=0.1,\n",
    "    barmode=\"group\",\n",
    "    xaxis_title=\"Decade\",\n",
    "    yaxis_title=\"Count\",\n",
    ")\n",
    "fig.show()\n",
    "\n",
    "fig = px.histogram(\n",
    "    data_frame=key_count,\n",
    "    x=\"decade\",\n",
    "    y=\"count\",\n",
    "    color=\"key\",\n",
    "    histfunc=\"sum\",\n",
    "    color_discrete_sequence=px.colors.qualitative.Pastel,\n",
    "    text_auto=True,\n",
    ")\n",
    "fig.update_layout(\n",
    "    title={\"text\": \"Key Count per Decade\", \"font\": {\"size\": 24}},\n",
    "    bargap=0.2,\n",
    "    bargroupgap=0.1,\n",
    "    barmode=\"stack\",\n",
    "    xaxis_title=\"Decade\",\n",
    "    yaxis_title=\"Count\",\n",
    ")\n",
    "fig.show()\n",
    "\n",
    "del (mode_count, key_count, explicit_count)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "cols = [\n",
    "    \"valence\",\n",
    "    \"acousticness\",\n",
    "    \"danceability\",\n",
    "    \"duration_min\",\n",
    "    \"energy\",\n",
    "    \"instrumentalness\",\n",
    "    \"liveness\",\n",
    "    \"loudness\",\n",
    "    \"year\",\n",
    "    \"speechiness\",\n",
    "    \"tempo\",\n",
    "]\n",
    "\n",
    "for col in cols:\n",
    "\n",
    "    fig = px.scatter(\n",
    "        data_frame=df,\n",
    "        x=col,\n",
    "        y=\"popularity\",\n",
    "        trendline=\"ols\",\n",
    "        trendline_color_override=\"#A6E3A1\",\n",
    "    )\n",
    "    fig.update_traces(marker={\"opacity\": 0.3, \"size\": 3, \"color\": \"#B4BEFE\"})\n",
    "    fig.update_layout(title={\"text\": f\"{col} vs popularity\", \"font\": {\"size\": 24}})\n",
    "    fig.show()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Header 1\n",
    "\n",
    "## Header 2\n",
    "\n",
    "### Header 3.1"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "cols = [\n",
    "    \"valence\",\n",
    "    \"acousticness\",\n",
    "    \"danceability\",\n",
    "    \"duration_min\",\n",
    "    \"energy\",\n",
    "    \"instrumentalness\",\n",
    "    \"liveness\",\n",
    "    \"loudness\",\n",
    "    \"year\",\n",
    "    \"speechiness\",\n",
    "    \"tempo\",\n",
    "]\n",
    "\n",
    "plt.figure(figsize=(15, 10))\n",
    "\n",
    "for i, col in enumerate(cols):\n",
    "    ax = plt.subplot(3, 4, i + 1)\n",
    "    sns.regplot(\n",
    "        data=df,\n",
    "        x=\"popularity\",\n",
    "        y=col,\n",
    "        ax=ax,\n",
    "        scatter_kws={\"alpha\": 0.5},\n",
    "        line_kws={\"color\": \"#F38BA8\"},\n",
    "    )\n",
    "\n",
    "plt.tight_layout()\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "cols = [\n",
    "    \"valence\",\n",
    "    \"acousticness\",\n",
    "    \"danceability\",\n",
    "    \"duration_min\",\n",
    "    \"energy\",\n",
    "    \"instrumentalness\",\n",
    "    \"liveness\",\n",
    "    \"loudness\",\n",
    "    \"year\",\n",
    "    \"speechiness\",\n",
    "    \"tempo\",\n",
    "    \"popularity\",\n",
    "]\n",
    "\n",
    "plt.figure(figsize=(10, 7))\n",
    "mask = np.triu(np.ones_like(df[cols].corr()))\n",
    "sns.heatmap(\n",
    "    df[cols].corr(),\n",
    "    annot=True,\n",
    "    fmt=\".2f\",\n",
    "    cmap=\"Blues\",\n",
    "    mask=mask,\n",
    ")\n",
    "plt.grid(visible=False)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "df[\"first_artist\"] = (\n",
    "    df[\"artists\"]\n",
    "    .apply(lambda x: str(x).split(\"x\")[0])\n",
    "    .apply(lambda x: str(x).replace(\"[\", \"\"))\n",
    "    .apply(lambda x: str(x).replace(\"]\", \"\"))\n",
    "    .apply(lambda x: str(x).replace(\"'\", \"\"))\n",
    ")\n",
    "df = df.drop(\"artists\", axis=1)\n",
    "df[\"first_artist\"] = df[\"first_artist\"].apply(lambda x: str(x).split(\",\")[0])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "popularity_check = (\n",
    "    df.groupby([\"first_artist\"], as_index=False)[\"popularity\"]\n",
    "    .agg({\"mean\", \"count\", \"median\"})\n",
    "    .sort_values(by=\"mean\", ascending=False)\n",
    "    .reset_index(drop=True)\n",
    ")\n",
    "\n",
    "popularity_check = popularity_check.drop(16091, axis=0)\n",
    "popularity_check = popularity_check.drop(16086, axis=0)\n",
    "popularity_check = popularity_check.drop(16429, axis=0)\n",
    "\n",
    "to_drop = popularity_check[popularity_check[\"count\"] <= 45].index\n",
    "popularity_check = popularity_check.drop(to_drop)\n",
    "popularity_check = popularity_check.sort_values(by=\"mean\", ascending=False).head(50)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Header 1\n",
    "\n",
    "## Header 2\n",
    "\n",
    "### Header 3.1"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "top_50_artists = pd.DataFrame()\n",
    "\n",
    "for i in popularity_check[\"first_artist\"].unique():\n",
    "    artist = df.query(\"first_artist == @i\")\n",
    "    top_50_artists = pd.concat([top_50_artists, artist], axis=0)\n",
    "\n",
    "top_50_artists = top_50_artists.reset_index(drop=True)\n",
    "top_50_artists.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "plt.figure(figsize=(12, 8))\n",
    "(\n",
    "    top_50_artists[\"first_artist\"]\n",
    "    .value_counts()\n",
    "    .sort_values(ascending=True)\n",
    "    .plot(kind=\"barh\")\n",
    ")\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "top_50_artists[\"decade\"].value_counts().sort_values(ascending=True).plot(kind=\"barh\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "cols = [\n",
    "    \"valence\",\n",
    "    \"acousticness\",\n",
    "    \"danceability\",\n",
    "    \"duration_min\",\n",
    "    \"energy\",\n",
    "    \"instrumentalness\",\n",
    "    \"liveness\",\n",
    "    \"loudness\",\n",
    "    \"year\",\n",
    "    \"speechiness\",\n",
    "    \"tempo\",\n",
    "]\n",
    "\n",
    "plt.figure(figsize=(15, 10))\n",
    "\n",
    "for i, col in enumerate(cols):\n",
    "    ax = plt.subplot(3, 4, i + 1)\n",
    "    sns.kdeplot(data=top_50_artists, x=col, hue=\"first_artist\", legend=False)\n",
    "\n",
    "plt.tight_layout()\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Header 1\n",
    "\n",
    "## Header 2\n",
    "\n",
    "### Header 3.1"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "import pandas as pd\n",
    "import numpy as np\n",
    "import seaborn as sns\n",
    "import matplotlib.pyplot as plt\n",
    "import matplotlib as mpl\n",
    "import mplcatppuccin\n",
    "import plotly.express as px\n",
    "import plotly.graph_objects as go\n",
    "from plotly.subplots import make_subplots\n",
    "import plotly.figure_factory as ff\n",
    "import warnings\n",
    "import plotly.io as pio\n",
    "\n",
    "warnings.filterwarnings('ignore')\n",
    "\n",
    "pio.renderers.default = 'notebook_connected'\n",
    "pio.templates.default = 'plotly_dark'\n",
    "\n",
    "\n",
    "%matplotlib inline\n",
    "%config InlineBackend.figure_format = 'retina'\n",
    "pd.set_option('display.max_columns', None)\n",
    "pd.set_option('display.precision', 2)\n",
    "pd.set_option('display.colheader_justify', 'left')\n",
    "\n",
    "mpl.rc(\n",
    "    'figure',\n",
    "    autolayout=True,\n",
    "    titlesize=18\n",
    ")\n",
    "\n",
    "mpl.style.use(['ggplot', 'mocha'])\n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Header 3.2\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "df = pd.read_csv(\n",
    "    \"data.csv\",\n",
    "    parse_dates=[\"release_date\"],\n",
    ")\n",
    "df.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "map_key = {\n",
    "    0: \"C\",\n",
    "    1: \"C#\",\n",
    "    2: \"D\",\n",
    "    3: \"D#\",\n",
    "    4: \"E\",\n",
    "    5: \"F\",\n",
    "    6: \"F#\",\n",
    "    7: \"G\",\n",
    "    8: \"G#\",\n",
    "    9: \"A\",\n",
    "    10: \"A#\",\n",
    "    11: \"B\",\n",
    "}\n",
    "\n",
    "map_mode = {1: \"Major\", 0: \"Minor\"}\n",
    "\n",
    "df[\"mode\"] = df[\"mode\"].map(map_mode)\n",
    "df[\"key\"] = df[\"key\"].map(map_key)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "check_dups = df[[\"artists\", \"name\"]]\n",
    "dups = check_dups[check_dups.duplicated()].index"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "print(\"Before dropping duplicated:\", df.shape)\n",
    "df = df.drop(dups)\n",
    "print(\"After dropping duplicated:\", df.shape)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Header 1.3\n",
    "\n",
    "## Header 2.3\n",
    "\n",
    "### Header 3.5"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "df[\"duration_ms\"] = df[\"duration_ms\"] / 60_000\n",
    "df = df.rename(columns={\"duration_ms\": \"duration_min\"})\n",
    "df.head()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Header 1.4\n",
    "\n",
    "## Header 2.4\n",
    "\n",
    "### Header 3.5"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "df = df.drop([\"release_date\", \"id\"], axis=1)\n",
    "df.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "def fun_subplots_plotly(df, col):\n",
    "\n",
    "    mean_val = df[col].mean()\n",
    "    median_val = df[col].median()\n",
    "    fig = make_subplots(rows=1, cols=2, column_widths=[0.75, 0.25])\n",
    "\n",
    "    fig.add_trace(\n",
    "        go.Histogram(\n",
    "            x=df[col], name=f\"Histogram {col}\", marker={\"color\": \"#EBA0AC\"}, nbinsx=50\n",
    "        ),\n",
    "        row=1,\n",
    "        col=1,\n",
    "    )\n",
    "\n",
    "    fig.add_shape(\n",
    "        type=\"line\",\n",
    "        xref=\"paper\",\n",
    "        yref=\"y\",\n",
    "        x0=-1,\n",
    "        x1=1,\n",
    "        y0=mean_val,\n",
    "        y1=mean_val,\n",
    "        row=1,\n",
    "        col=2,\n",
    "        line={\"color\": \"#A6E3A1\", \"width\": 3, \"dash\": \"dot\"},\n",
    "    )\n",
    "\n",
    "    fig.add_shape(\n",
    "        type=\"line\",\n",
    "        xref=\"paper\",\n",
    "        yref=\"y\",\n",
    "        x0=-1,\n",
    "        x1=1,\n",
    "        y0=median_val,\n",
    "        y1=median_val,\n",
    "        row=1,\n",
    "        col=2,\n",
    "        line={\"color\": \"#CBA6F7\", \"width\": 3, \"dash\": \"dot\"},\n",
    "    )\n",
    "\n",
    "    fig.add_annotation(\n",
    "        xref=\"paper\",\n",
    "        x=-0.7,\n",
    "        y=mean_val,\n",
    "        showarrow=True,\n",
    "        arrowhead=2,\n",
    "        text=f\"Mean = {mean_val:.2f}\",\n",
    "        row=1,\n",
    "        col=2,\n",
    "    )\n",
    "\n",
    "    fig.add_annotation(\n",
    "        xref=\"paper\",\n",
    "        x=0.7,\n",
    "        y=median_val,\n",
    "        showarrow=True,\n",
    "        arrowhead=2,\n",
    "        text=f\"Median = {median_val:.2f}\",\n",
    "        row=1,\n",
    "        col=2,\n",
    "    )\n",
    "\n",
    "    fig.add_trace(\n",
    "        go.Box(y=df[col], name=f\"Boxplot {col}\", marker={\"color\": \"#F9E2AF\"}),\n",
    "        row=1,\n",
    "        col=2,\n",
    "    )\n",
    "\n",
    "    fig.update_layout(\n",
    "        title={\"text\": f\"Distribution Plot {col}\", \"font\": {\"size\": 24}},\n",
    "        legend={\n",
    "            \"orientation\": \"h\",\n",
    "            \"yanchor\": \"bottom\",\n",
    "            \"y\": 1.02,\n",
    "            \"xanchor\": \"right\",\n",
    "            \"x\": 1,\n",
    "        },\n",
    "    )\n",
    "    fig.update_yaxes(title_text=\"Count\", row=1, col=1)\n",
    "    fig.update_yaxes(title_text=f\"{col}\", row=1, col=2)\n",
    "    fig.update_xaxes(title_text=f\"{col}\", row=1, col=1)\n",
    "    fig.update_xaxes(title_text=\"\", row=1, col=2)\n",
    "    fig.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "music_vals = [\n",
    "    \"valence\",\n",
    "    \"acousticness\",\n",
    "    \"danceability\",\n",
    "    \"duration_min\",\n",
    "    \"energy\",\n",
    "    \"instrumentalness\",\n",
    "    \"liveness\",\n",
    "    \"loudness\",\n",
    "    \"popularity\",\n",
    "    \"speechiness\",\n",
    "    \"tempo\",\n",
    "]\n",
    "\n",
    "for col in music_vals:\n",
    "    fun_subplots_plotly(df, col)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Header 1.2\n",
    "\n",
    "## Header 2.2\n",
    "\n",
    "### Header 3.4"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Header 1\n",
    "\n",
    "## Header 2\n",
    "\n",
    "### Header 3.1"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Header 1\n",
    "\n",
    "## Header 2\n",
    "\n",
    "### Header 3.1"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Header 1\n",
    "\n",
    "## Header 2\n",
    "\n",
    "### Header 3.1"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Header 1\n",
    "\n",
    "## Header 2\n",
    "\n",
    "### Header 3.1"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "import pandas as pd\n",
    "import numpy as np\n",
    "import seaborn as sns\n",
    "import matplotlib.pyplot as plt\n",
    "import matplotlib as mpl\n",
    "import mplcatppuccin\n",
    "import plotly.express as px\n",
    "import plotly.graph_objects as go\n",
    "from plotly.subplots import make_subplots\n",
    "import plotly.figure_factory as ff\n",
    "import warnings\n",
    "import plotly.io as pio\n",
    "\n",
    "warnings.filterwarnings('ignore')\n",
    "\n",
    "pio.renderers.default = 'notebook_connected'\n",
    "pio.templates.default = 'plotly_dark'\n",
    "\n",
    "\n",
    "%matplotlib inline\n",
    "%config InlineBackend.figure_format = 'retina'\n",
    "pd.set_option('display.max_columns', None)\n",
    "pd.set_option('display.precision', 2)\n",
    "pd.set_option('display.colheader_justify', 'left')\n",
    "\n",
    "mpl.rc(\n",
    "    'figure',\n",
    "    autolayout=True,\n",
    "    titlesize=18\n",
    ")\n",
    "\n",
    "mpl.style.use(['ggplot', 'mocha'])\n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Header 3.2\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "df = pd.read_csv(\n",
    "    \"data.csv\",\n",
    "    parse_dates=[\"release_date\"],\n",
    ")\n",
    "df.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "map_key = {\n",
    "    0: \"C\",\n",
    "    1: \"C#\",\n",
    "    2: \"D\",\n",
    "    3: \"D#\",\n",
    "    4: \"E\",\n",
    "    5: \"F\",\n",
    "    6: \"F#\",\n",
    "    7: \"G\",\n",
    "    8: \"G#\",\n",
    "    9: \"A\",\n",
    "    10: \"A#\",\n",
    "    11: \"B\",\n",
    "}\n",
    "\n",
    "map_mode = {1: \"Major\", 0: \"Minor\"}\n",
    "\n",
    "df[\"mode\"] = df[\"mode\"].map(map_mode)\n",
    "df[\"key\"] = df[\"key\"].map(map_key)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "check_dups = df[[\"artists\", \"name\"]]\n",
    "dups = check_dups[check_dups.duplicated()].index"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "print(\"Before dropping duplicated:\", df.shape)\n",
    "df = df.drop(dups)\n",
    "print(\"After dropping duplicated:\", df.shape)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Header 1.3\n",
    "\n",
    "## Header 2.3\n",
    "\n",
    "### Header 3.5"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "df[\"duration_ms\"] = df[\"duration_ms\"] / 60_000\n",
    "df = df.rename(columns={\"duration_ms\": \"duration_min\"})\n",
    "df.head()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Header 1.4\n",
    "\n",
    "## Header 2.4\n",
    "\n",
    "### Header 3.5"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "df = df.drop([\"release_date\", \"id\"], axis=1)\n",
    "df.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "def fun_subplots_plotly(df, col):\n",
    "\n",
    "    mean_val = df[col].mean()\n",
    "    median_val = df[col].median()\n",
    "    fig = make_subplots(rows=1, cols=2, column_widths=[0.75, 0.25])\n",
    "\n",
    "    fig.add_trace(\n",
    "        go.Histogram(\n",
    "            x=df[col], name=f\"Histogram {col}\", marker={\"color\": \"#EBA0AC\"}, nbinsx=50\n",
    "        ),\n",
    "        row=1,\n",
    "        col=1,\n",
    "    )\n",
    "\n",
    "    fig.add_shape(\n",
    "        type=\"line\",\n",
    "        xref=\"paper\",\n",
    "        yref=\"y\",\n",
    "        x0=-1,\n",
    "        x1=1,\n",
    "        y0=mean_val,\n",
    "        y1=mean_val,\n",
    "        row=1,\n",
    "        col=2,\n",
    "        line={\"color\": \"#A6E3A1\", \"width\": 3, \"dash\": \"dot\"},\n",
    "    )\n",
    "\n",
    "    fig.add_shape(\n",
    "        type=\"line\",\n",
    "        xref=\"paper\",\n",
    "        yref=\"y\",\n",
    "        x0=-1,\n",
    "        x1=1,\n",
    "        y0=median_val,\n",
    "        y1=median_val,\n",
    "        row=1,\n",
    "        col=2,\n",
    "        line={\"color\": \"#CBA6F7\", \"width\": 3, \"dash\": \"dot\"},\n",
    "    )\n",
    "\n",
    "    fig.add_annotation(\n",
    "        xref=\"paper\",\n",
    "        x=-0.7,\n",
    "        y=mean_val,\n",
    "        showarrow=True,\n",
    "        arrowhead=2,\n",
    "        text=f\"Mean = {mean_val:.2f}\",\n",
    "        row=1,\n",
    "        col=2,\n",
    "    )\n",
    "\n",
    "    fig.add_annotation(\n",
    "        xref=\"paper\",\n",
    "        x=0.7,\n",
    "        y=median_val,\n",
    "        showarrow=True,\n",
    "        arrowhead=2,\n",
    "        text=f\"Median = {median_val:.2f}\",\n",
    "        row=1,\n",
    "        col=2,\n",
    "    )\n",
    "\n",
    "    fig.add_trace(\n",
    "        go.Box(y=df[col], name=f\"Boxplot {col}\", marker={\"color\": \"#F9E2AF\"}),\n",
    "        row=1,\n",
    "        col=2,\n",
    "    )\n",
    "\n",
    "    fig.update_layout(\n",
    "        title={\"text\": f\"Distribution Plot {col}\", \"font\": {\"size\": 24}},\n",
    "        legend={\n",
    "            \"orientation\": \"h\",\n",
    "            \"yanchor\": \"bottom\",\n",
    "            \"y\": 1.02,\n",
    "            \"xanchor\": \"right\",\n",
    "            \"x\": 1,\n",
    "        },\n",
    "    )\n",
    "    fig.update_yaxes(title_text=\"Count\", row=1, col=1)\n",
    "    fig.update_yaxes(title_text=f\"{col}\", row=1, col=2)\n",
    "    fig.update_xaxes(title_text=f\"{col}\", row=1, col=1)\n",
    "    fig.update_xaxes(title_text=\"\", row=1, col=2)\n",
    "    fig.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "music_vals = [\n",
    "    \"valence\",\n",
    "    \"acousticness\",\n",
    "    \"danceability\",\n",
    "    \"duration_min\",\n",
    "    \"energy\",\n",
    "    \"instrumentalness\",\n",
    "    \"liveness\",\n",
    "    \"loudness\",\n",
    "    \"popularity\",\n",
    "    \"speechiness\",\n",
    "    \"tempo\",\n",
    "]\n",
    "\n",
    "for col in music_vals:\n",
    "    fun_subplots_plotly(df, col)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Header 1.2\n",
    "\n",
    "## Header 2.2\n",
    "\n",
    "### Header 3.4"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "bins = pd.IntervalIndex.from_breaks(\n",
    "    [1920, 1930, 1940, 1950, 1960, 1970, 1980, 1990, 2000, 2010, 2020]\n",
    ")\n",
    "\n",
    "df[\"decade\"] = pd.cut(df[\"year\"], bins).astype(\"str\")\n",
    "\n",
    "map_decade = {\n",
    "    \"(1920, 1930]\": \"1920s\",\n",
    "    \"(1930, 1940]\": \"1930s\",\n",
    "    \"(1940, 1950]\": \"1940s\",\n",
    "    \"(1950, 1960]\": \"1950s\",\n",
    "    \"(1960, 1970]\": \"1960s\",\n",
    "    \"(1970, 1980]\": \"1970s\",\n",
    "    \"(1980, 1990]\": \"1980s\",\n",
    "    \"(1990, 2000]\": \"1990s\",\n",
    "    \"(2000, 2010]\": \"2000s\",\n",
    "    \"(2010, 2020]\": \"2010s\",\n",
    "}\n",
    "\n",
    "df[\"decade\"] = df[\"decade\"].map(map_decade)\n",
    "\n",
    "df.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "decade_counts = (\n",
    "    df[\"decade\"].value_counts().reset_index().sort_values(by=\"decade\", ascending=True)\n",
    ")\n",
    "\n",
    "fig = px.bar(\n",
    "    data_frame=decade_counts,\n",
    "    y=\"decade\",\n",
    "    x=\"count\",\n",
    "    color=\"count\",\n",
    "    color_continuous_scale=px.colors.sequential.Sunset,\n",
    "    text_auto=True,\n",
    ")\n",
    "\n",
    "fig.update_layout(\n",
    "    title={\"text\": \"Count of songs per decade\", \"font\": {\"size\": 24}},\n",
    "    coloraxis_colorbar={\n",
    "        \"title\": \"Count\",\n",
    "        \"thicknessmode\": \"pixels\",\n",
    "        \"thickness\": 20,\n",
    "        \"lenmode\": \"pixels\",\n",
    "        \"len\": 500,\n",
    "        \"yanchor\": \"top\",\n",
    "        \"xanchor\": \"right\",\n",
    "        \"y\": 1.15,\n",
    "        \"x\": 0.95,\n",
    "        \"orientation\": \"h\",\n",
    "    },\n",
    "    margin={\"r\": 10},\n",
    ")\n",
    "\n",
    "fig.update_xaxes(title=\"Count\")\n",
    "fig.update_yaxes(title=\"Decades\")\n",
    "fig.show()\n",
    "\n",
    "del decade_counts"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "df = df.query(\"duration_min <= 5\")"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Header 1.2\n",
    "\n",
    "## Header 2.2\n",
    "\n",
    "### Header 3.4"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "decade_counts = (\n",
    "    df[\"decade\"].value_counts().reset_index().sort_values(by=\"decade\", ascending=True)\n",
    ")\n",
    "\n",
    "fig = px.bar(\n",
    "    data_frame=decade_counts,\n",
    "    y=\"decade\",\n",
    "    x=\"count\",\n",
    "    color=\"count\",\n",
    "    color_continuous_scale=px.colors.sequential.Sunset,\n",
    "    text_auto=True,\n",
    ")\n",
    "\n",
    "fig.update_layout(\n",
    "    title={\"text\": \"Count of songs per decade (< 5min)\", \"font\": {\"size\": 24}},\n",
    "    coloraxis_colorbar={\n",
    "        \"title\": \"Count\",\n",
    "        \"thicknessmode\": \"pixels\",\n",
    "        \"thickness\": 20,\n",
    "        \"lenmode\": \"pixels\",\n",
    "        \"len\": 500,\n",
    "        \"yanchor\": \"top\",\n",
    "        \"xanchor\": \"right\",\n",
    "        \"y\": 1.15,\n",
    "        \"x\": 0.95,\n",
    "        \"orientation\": \"h\",\n",
    "    },\n",
    "    margin={\"r\": 10},\n",
    ")\n",
    "\n",
    "fig.update_xaxes(title=\"Count\")\n",
    "fig.update_yaxes(title=\"Decades\")\n",
    "fig.show()\n",
    "\n",
    "del decade_counts"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "cols = [\n",
    "    \"valence\",\n",
    "    \"acousticness\",\n",
    "    \"danceability\",\n",
    "    \"duration_min\",\n",
    "    \"energy\",\n",
    "    \"instrumentalness\",\n",
    "    \"liveness\",\n",
    "    \"loudness\",\n",
    "    \"popularity\",\n",
    "    \"speechiness\",\n",
    "    \"tempo\",\n",
    "]\n",
    "for col in cols:\n",
    "    fig = px.histogram(\n",
    "        data_frame=df,\n",
    "        x=col,\n",
    "        color=\"decade\",\n",
    "        color_discrete_sequence=px.colors.qualitative.Light24,\n",
    "    )\n",
    "    fig.update_traces(opacity=0.7)\n",
    "    fig.update_layout(\n",
    "        bargap=0.1,\n",
    "        bargroupgap=0.05,\n",
    "        barmode=\"stack\",\n",
    "        title={\"text\": f\"Histogram of {col} per decade\", \"font\": {\"size\": 24}},\n",
    "        legend={\"title\": \"Decade\"},\n",
    "    )\n",
    "    fig.update_yaxes(title=\"Count\")\n",
    "    fig.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "decade_mean = df.groupby(\"decade\")[cols].mean()\n",
    "\n",
    "fig = make_subplots(\n",
    "    rows=4,\n",
    "    cols=3,\n",
    "    subplot_titles=(\n",
    "        decade_mean.columns[0],\n",
    "        decade_mean.columns[1],\n",
    "        decade_mean.columns[2],\n",
    "        decade_mean.columns[3],\n",
    "        decade_mean.columns[4],\n",
    "        decade_mean.columns[5],\n",
    "        decade_mean.columns[6],\n",
    "        decade_mean.columns[7],\n",
    "        decade_mean.columns[8],\n",
    "        decade_mean.columns[9],\n",
    "        decade_mean.columns[10],\n",
    "    ),\n",
    "    vertical_spacing=0.1,\n",
    ")\n",
    "\n",
    "fig.add_trace(\n",
    "    go.Bar(\n",
    "        y=decade_mean.index,\n",
    "        x=decade_mean.iloc[:, 0],\n",
    "        name=decade_mean.columns[0],\n",
    "        orientation=\"h\",\n",
    "    ),\n",
    "    row=1,\n",
    "    col=1,\n",
    ")\n",
    "\n",
    "fig.add_trace(\n",
    "    go.Bar(\n",
    "        y=decade_mean.index,\n",
    "        x=decade_mean.iloc[:, 1],\n",
    "        name=decade_mean.columns[1],\n",
    "        orientation=\"h\",\n",
    "    ),\n",
    "    row=1,\n",
    "    col=2,\n",
    ")\n",
    "\n",
    "fig.add_trace(\n",
    "    go.Bar(\n",
    "        y=decade_mean.index,\n",
    "        x=decade_mean.iloc[:, 2],\n",
    "        name=decade_mean.columns[2],\n",
    "        orientation=\"h\",\n",
    "    ),\n",
    "    row=1,\n",
    "    col=3,\n",
    ")\n",
    "\n",
    "fig.add_trace(\n",
    "    go.Bar(\n",
    "        y=decade_mean.index,\n",
    "        x=decade_mean.iloc[:, 3],\n",
    "        name=decade_mean.columns[3],\n",
    "        orientation=\"h\",\n",
    "    ),\n",
    "    row=2,\n",
    "    col=1,\n",
    ")\n",
    "\n",
    "fig.add_trace(\n",
    "    go.Bar(\n",
    "        y=decade_mean.index,\n",
    "        x=decade_mean.iloc[:, 4],\n",
    "        name=decade_mean.columns[4],\n",
    "        orientation=\"h\",\n",
    "    ),\n",
    "    row=2,\n",
    "    col=2,\n",
    ")\n",
    "\n",
    "fig.add_trace(\n",
    "    go.Bar(\n",
    "        y=decade_mean.index,\n",
    "        x=decade_mean.iloc[:, 5],\n",
    "        name=decade_mean.columns[5],\n",
    "        orientation=\"h\",\n",
    "    ),\n",
    "    row=2,\n",
    "    col=3,\n",
    ")\n",
    "\n",
    "fig.add_trace(\n",
    "    go.Bar(\n",
    "        y=decade_mean.index,\n",
    "        x=decade_mean.iloc[:, 6],\n",
    "        name=decade_mean.columns[6],\n",
    "        orientation=\"h\",\n",
    "    ),\n",
    "    row=3,\n",
    "    col=1,\n",
    ")\n",
    "\n",
    "fig.add_trace(\n",
    "    go.Bar(\n",
    "        y=decade_mean.index,\n",
    "        x=decade_mean.iloc[:, 7],\n",
    "        name=decade_mean.columns[7],\n",
    "        orientation=\"h\",\n",
    "    ),\n",
    "    row=3,\n",
    "    col=2,\n",
    ")\n",
    "\n",
    "fig.add_trace(\n",
    "    go.Bar(\n",
    "        y=decade_mean.index,\n",
    "        x=decade_mean.iloc[:, 8],\n",
    "        name=decade_mean.columns[8],\n",
    "        orientation=\"h\",\n",
    "    ),\n",
    "    row=3,\n",
    "    col=3,\n",
    ")\n",
    "\n",
    "fig.add_trace(\n",
    "    go.Bar(\n",
    "        y=decade_mean.index,\n",
    "        x=decade_mean.iloc[:, 9],\n",
    "        name=decade_mean.columns[9],\n",
    "        orientation=\"h\",\n",
    "    ),\n",
    "    row=4,\n",
    "    col=1,\n",
    ")\n",
    "\n",
    "fig.add_trace(\n",
    "    go.Bar(\n",
    "        y=decade_mean.index,\n",
    "        x=decade_mean.iloc[:, 10],\n",
    "        name=decade_mean.columns[10],\n",
    "        orientation=\"h\",\n",
    "    ),\n",
    "    row=4,\n",
    "    col=2,\n",
    ")\n",
    "\n",
    "fig.update_layout(\n",
    "    title={\"text\": \"Mean Musical Values per Decade\", \"font\": {\"size\": 22}},\n",
    "    legend={\n",
    "        \"orientation\": \"v\",\n",
    "        \"yanchor\": \"top\",\n",
    "        \"y\": 0.2,\n",
    "        \"xanchor\": \"right\",\n",
    "        \"x\": 0.9,\n",
    "    },\n",
    "    margin={\"b\": 10, \"r\": 10},\n",
    "    height=980,\n",
    ")\n",
    "\n",
    "fig.show()\n",
    "\n",
    "del decade_mean"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "decade_median = df.groupby(\"decade\")[cols].median()\n",
    "\n",
    "fig = make_subplots(\n",
    "    rows=4,\n",
    "    cols=3,\n",
    "    subplot_titles=(\n",
    "        decade_median.columns[0],\n",
    "        decade_median.columns[1],\n",
    "        decade_median.columns[2],\n",
    "        decade_median.columns[3],\n",
    "        decade_median.columns[4],\n",
    "        decade_median.columns[5],\n",
    "        decade_median.columns[6],\n",
    "        decade_median.columns[7],\n",
    "        decade_median.columns[8],\n",
    "        decade_median.columns[9],\n",
    "        decade_median.columns[10],\n",
    "    ),\n",
    "    vertical_spacing=0.1,\n",
    ")\n",
    "\n",
    "fig.add_trace(\n",
    "    go.Bar(\n",
    "        y=decade_median.index,\n",
    "        x=decade_median.iloc[:, 0],\n",
    "        name=decade_median.columns[0],\n",
    "        orientation=\"h\",\n",
    "    ),\n",
    "    row=1,\n",
    "    col=1,\n",
    ")\n",
    "\n",
    "fig.add_trace(\n",
    "    go.Bar(\n",
    "        y=decade_median.index,\n",
    "        x=decade_median.iloc[:, 1],\n",
    "        name=decade_median.columns[1],\n",
    "        orientation=\"h\",\n",
    "    ),\n",
    "    row=1,\n",
    "    col=2,\n",
    ")\n",
    "\n",
    "fig.add_trace(\n",
    "    go.Bar(\n",
    "        y=decade_median.index,\n",
    "        x=decade_median.iloc[:, 2],\n",
    "        name=decade_median.columns[2],\n",
    "        orientation=\"h\",\n",
    "    ),\n",
    "    row=1,\n",
    "    col=3,\n",
    ")\n",
    "\n",
    "fig.add_trace(\n",
    "    go.Bar(\n",
    "        y=decade_median.index,\n",
    "        x=decade_median.iloc[:, 3],\n",
    "        name=decade_median.columns[3],\n",
    "        orientation=\"h\",\n",
    "    ),\n",
    "    row=2,\n",
    "    col=1,\n",
    ")\n",
    "\n",
    "fig.add_trace(\n",
    "    go.Bar(\n",
    "        y=decade_median.index,\n",
    "        x=decade_median.iloc[:, 4],\n",
    "        name=decade_median.columns[4],\n",
    "        orientation=\"h\",\n",
    "    ),\n",
    "    row=2,\n",
    "    col=2,\n",
    ")\n",
    "\n",
    "fig.add_trace(\n",
    "    go.Bar(\n",
    "        y=decade_median.index,\n",
    "        x=decade_median.iloc[:, 5],\n",
    "        name=decade_median.columns[5],\n",
    "        orientation=\"h\",\n",
    "    ),\n",
    "    row=2,\n",
    "    col=3,\n",
    ")\n",
    "\n",
    "fig.add_trace(\n",
    "    go.Bar(\n",
    "        y=decade_median.index,\n",
    "        x=decade_median.iloc[:, 6],\n",
    "        name=decade_median.columns[6],\n",
    "        orientation=\"h\",\n",
    "    ),\n",
    "    row=3,\n",
    "    col=1,\n",
    ")\n",
    "\n",
    "fig.add_trace(\n",
    "    go.Bar(\n",
    "        y=decade_median.index,\n",
    "        x=decade_median.iloc[:, 7],\n",
    "        name=decade_median.columns[7],\n",
    "        orientation=\"h\",\n",
    "    ),\n",
    "    row=3,\n",
    "    col=2,\n",
    ")\n",
    "\n",
    "fig.add_trace(\n",
    "    go.Bar(\n",
    "        y=decade_median.index,\n",
    "        x=decade_median.iloc[:, 8],\n",
    "        name=decade_median.columns[8],\n",
    "        orientation=\"h\",\n",
    "    ),\n",
    "    row=3,\n",
    "    col=3,\n",
    ")\n",
    "\n",
    "fig.add_trace(\n",
    "    go.Bar(\n",
    "        y=decade_median.index,\n",
    "        x=decade_median.iloc[:, 9],\n",
    "        name=decade_median.columns[9],\n",
    "        orientation=\"h\",\n",
    "    ),\n",
    "    row=4,\n",
    "    col=1,\n",
    ")\n",
    "\n",
    "fig.add_trace(\n",
    "    go.Bar(\n",
    "        y=decade_median.index,\n",
    "        x=decade_median.iloc[:, 10],\n",
    "        name=decade_median.columns[10],\n",
    "        orientation=\"h\",\n",
    "    ),\n",
    "    row=4,\n",
    "    col=2,\n",
    ")\n",
    "\n",
    "fig.update_layout(\n",
    "    title={\"text\": \"Median Musical Values per Decade\", \"font\": {\"size\": 22}},\n",
    "    legend={\n",
    "        \"orientation\": \"v\",\n",
    "        \"yanchor\": \"top\",\n",
    "        \"y\": 0.2,\n",
    "        \"xanchor\": \"right\",\n",
    "        \"x\": 0.9,\n",
    "    },\n",
    "    margin={\"b\": 10, \"r\": 10},\n",
    "    height=980,\n",
    ")\n",
    "\n",
    "fig.show()\n",
    "\n",
    "del decade_median"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "explicit_count = (\n",
    "    df.groupby([\"decade\", \"explicit\"], as_index=False)[\"year\"]\n",
    "    .count()\n",
    "    .rename(columns={\"year\": \"count\"})\n",
    ")\n",
    "key_count = (\n",
    "    df.groupby([\"decade\", \"key\"], as_index=False)[\"year\"]\n",
    "    .count()\n",
    "    .rename(columns={\"year\": \"count\"})\n",
    ")\n",
    "mode_count = (\n",
    "    df.groupby([\"decade\", \"mode\"], as_index=False)[\"year\"]\n",
    "    .count()\n",
    "    .rename(columns={\"year\": \"count\"})\n",
    ")\n",
    "\n",
    "fig = px.histogram(\n",
    "    data_frame=explicit_count,\n",
    "    x=\"decade\",\n",
    "    y=\"count\",\n",
    "    color=\"explicit\",\n",
    "    histfunc=\"sum\",\n",
    "    color_discrete_sequence=px.colors.qualitative.Pastel,\n",
    "    text_auto=True,\n",
    ")\n",
    "fig.update_layout(\n",
    "    title={\"text\": \"Explicit Count per Decade\", \"font\": {\"size\": 24}},\n",
    "    bargap=0.2,\n",
    "    bargroupgap=0.1,\n",
    "    barmode=\"group\",\n",
    "    xaxis_title=\"Decade\",\n",
    "    yaxis_title=\"Count\",\n",
    ")\n",
    "fig.show()\n",
    "\n",
    "fig = px.histogram(\n",
    "    data_frame=mode_count,\n",
    "    x=\"decade\",\n",
    "    y=\"count\",\n",
    "    color=\"mode\",\n",
    "    histfunc=\"sum\",\n",
    "    color_discrete_sequence=px.colors.qualitative.Pastel,\n",
    "    text_auto=True,\n",
    ")\n",
    "fig.update_layout(\n",
    "    title={\"text\": \"Mode Count per Decade\", \"font\": {\"size\": 24}},\n",
    "    bargap=0.2,\n",
    "    bargroupgap=0.1,\n",
    "    barmode=\"group\",\n",
    "    xaxis_title=\"Decade\",\n",
    "    yaxis_title=\"Count\",\n",
    ")\n",
    "fig.show()\n",
    "\n",
    "fig = px.histogram(\n",
    "    data_frame=key_count,\n",
    "    x=\"decade\",\n",
    "    y=\"count\",\n",
    "    color=\"key\",\n",
    "    histfunc=\"sum\",\n",
    "    color_discrete_sequence=px.colors.qualitative.Pastel,\n",
    "    text_auto=True,\n",
    ")\n",
    "fig.update_layout(\n",
    "    title={\"text\": \"Key Count per Decade\", \"font\": {\"size\": 24}},\n",
    "    bargap=0.2,\n",
    "    bargroupgap=0.1,\n",
    "    barmode=\"stack\",\n",
    "    xaxis_title=\"Decade\",\n",
    "    yaxis_title=\"Count\",\n",
    ")\n",
    "fig.show()\n",
    "\n",
    "del (mode_count, key_count, explicit_count)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "cols = [\n",
    "    \"valence\",\n",
    "    \"acousticness\",\n",
    "    \"danceability\",\n",
    "    \"duration_min\",\n",
    "    \"energy\",\n",
    "    \"instrumentalness\",\n",
    "    \"liveness\",\n",
    "    \"loudness\",\n",
    "    \"year\",\n",
    "    \"speechiness\",\n",
    "    \"tempo\",\n",
    "]\n",
    "\n",
    "for col in cols:\n",
    "\n",
    "    fig = px.scatter(\n",
    "        data_frame=df,\n",
    "        x=col,\n",
    "        y=\"popularity\",\n",
    "        trendline=\"ols\",\n",
    "        trendline_color_override=\"#A6E3A1\",\n",
    "    )\n",
    "    fig.update_traces(marker={\"opacity\": 0.3, \"size\": 3, \"color\": \"#B4BEFE\"})\n",
    "    fig.update_layout(title={\"text\": f\"{col} vs popularity\", \"font\": {\"size\": 24}})\n",
    "    fig.show()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Header 1\n",
    "\n",
    "## Header 2\n",
    "\n",
    "### Header 3.1"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "cols = [\n",
    "    \"valence\",\n",
    "    \"acousticness\",\n",
    "    \"danceability\",\n",
    "    \"duration_min\",\n",
    "    \"energy\",\n",
    "    \"instrumentalness\",\n",
    "    \"liveness\",\n",
    "    \"loudness\",\n",
    "    \"year\",\n",
    "    \"speechiness\",\n",
    "    \"tempo\",\n",
    "]\n",
    "\n",
    "plt.figure(figsize=(15, 10))\n",
    "\n",
    "for i, col in enumerate(cols):\n",
    "    ax = plt.subplot(3, 4, i + 1)\n",
    "    sns.regplot(\n",
    "        data=df,\n",
    "        x=\"popularity\",\n",
    "        y=col,\n",
    "        ax=ax,\n",
    "        scatter_kws={\"alpha\": 0.5},\n",
    "        line_kws={\"color\": \"#F38BA8\"},\n",
    "    )\n",
    "\n",
    "plt.tight_layout()\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "cols = [\n",
    "    \"valence\",\n",
    "    \"acousticness\",\n",
    "    \"danceability\",\n",
    "    \"duration_min\",\n",
    "    \"energy\",\n",
    "    \"instrumentalness\",\n",
    "    \"liveness\",\n",
    "    \"loudness\",\n",
    "    \"year\",\n",
    "    \"speechiness\",\n",
    "    \"tempo\",\n",
    "    \"popularity\",\n",
    "]\n",
    "\n",
    "plt.figure(figsize=(10, 7))\n",
    "mask = np.triu(np.ones_like(df[cols].corr()))\n",
    "sns.heatmap(\n",
    "    df[cols].corr(),\n",
    "    annot=True,\n",
    "    fmt=\".2f\",\n",
    "    cmap=\"Blues\",\n",
    "    mask=mask,\n",
    ")\n",
    "plt.grid(visible=False)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "df[\"first_artist\"] = (\n",
    "    df[\"artists\"]\n",
    "    .apply(lambda x: str(x).split(\"x\")[0])\n",
    "    .apply(lambda x: str(x).replace(\"[\", \"\"))\n",
    "    .apply(lambda x: str(x).replace(\"]\", \"\"))\n",
    "    .apply(lambda x: str(x).replace(\"'\", \"\"))\n",
    ")\n",
    "df = df.drop(\"artists\", axis=1)\n",
    "df[\"first_artist\"] = df[\"first_artist\"].apply(lambda x: str(x).split(\",\")[0])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "popularity_check = (\n",
    "    df.groupby([\"first_artist\"], as_index=False)[\"popularity\"]\n",
    "    .agg({\"mean\", \"count\", \"median\"})\n",
    "    .sort_values(by=\"mean\", ascending=False)\n",
    "    .reset_index(drop=True)\n",
    ")\n",
    "\n",
    "popularity_check = popularity_check.drop(16091, axis=0)\n",
    "popularity_check = popularity_check.drop(16086, axis=0)\n",
    "popularity_check = popularity_check.drop(16429, axis=0)\n",
    "\n",
    "to_drop = popularity_check[popularity_check[\"count\"] <= 45].index\n",
    "popularity_check = popularity_check.drop(to_drop)\n",
    "popularity_check = popularity_check.sort_values(by=\"mean\", ascending=False).head(50)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Header 1\n",
    "\n",
    "## Header 2\n",
    "\n",
    "### Header 3.1"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "top_50_artists = pd.DataFrame()\n",
    "\n",
    "for i in popularity_check[\"first_artist\"].unique():\n",
    "    artist = df.query(\"first_artist == @i\")\n",
    "    top_50_artists = pd.concat([top_50_artists, artist], axis=0)\n",
    "\n",
    "top_50_artists = top_50_artists.reset_index(drop=True)\n",
    "top_50_artists.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "plt.figure(figsize=(12, 8))\n",
    "(\n",
    "    top_50_artists[\"first_artist\"]\n",
    "    .value_counts()\n",
    "    .sort_values(ascending=True)\n",
    "    .plot(kind=\"barh\")\n",
    ")\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "top_50_artists[\"decade\"].value_counts().sort_values(ascending=True).plot(kind=\"barh\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "cols = [\n",
    "    \"valence\",\n",
    "    \"acousticness\",\n",
    "    \"danceability\",\n",
    "    \"duration_min\",\n",
    "    \"energy\",\n",
    "    \"instrumentalness\",\n",
    "    \"liveness\",\n",
    "    \"loudness\",\n",
    "    \"year\",\n",
    "    \"speechiness\",\n",
    "    \"tempo\",\n",
    "]\n",
    "\n",
    "plt.figure(figsize=(15, 10))\n",
    "\n",
    "for i, col in enumerate(cols):\n",
    "    ax = plt.subplot(3, 4, i + 1)\n",
    "    sns.kdeplot(data=top_50_artists, x=col, hue=\"first_artist\", legend=False)\n",
    "\n",
    "plt.tight_layout()\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Header 1\n",
    "\n",
    "## Header 2\n",
    "\n",
    "### Header 3.1"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "import pandas as pd\n",
    "import numpy as np\n",
    "import seaborn as sns\n",
    "import matplotlib.pyplot as plt\n",
    "import matplotlib as mpl\n",
    "import mplcatppuccin\n",
    "import plotly.express as px\n",
    "import plotly.graph_objects as go\n",
    "from plotly.subplots import make_subplots\n",
    "import plotly.figure_factory as ff\n",
    "import warnings\n",
    "import plotly.io as pio\n",
    "\n",
    "warnings.filterwarnings('ignore')\n",
    "\n",
    "pio.renderers.default = 'notebook_connected'\n",
    "pio.templates.default = 'plotly_dark'\n",
    "\n",
    "\n",
    "%matplotlib inline\n",
    "%config InlineBackend.figure_format = 'retina'\n",
    "pd.set_option('display.max_columns', None)\n",
    "pd.set_option('display.precision', 2)\n",
    "pd.set_option('display.colheader_justify', 'left')\n",
    "\n",
    "mpl.rc(\n",
    "    'figure',\n",
    "    autolayout=True,\n",
    "    titlesize=18\n",
    ")\n",
    "\n",
    "mpl.style.use(['ggplot', 'mocha'])\n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Header 3.2\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "df = pd.read_csv(\n",
    "    \"data.csv\",\n",
    "    parse_dates=[\"release_date\"],\n",
    ")\n",
    "df.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "map_key = {\n",
    "    0: \"C\",\n",
    "    1: \"C#\",\n",
    "    2: \"D\",\n",
    "    3: \"D#\",\n",
    "    4: \"E\",\n",
    "    5: \"F\",\n",
    "    6: \"F#\",\n",
    "    7: \"G\",\n",
    "    8: \"G#\",\n",
    "    9: \"A\",\n",
    "    10: \"A#\",\n",
    "    11: \"B\",\n",
    "}\n",
    "\n",
    "map_mode = {1: \"Major\", 0: \"Minor\"}\n",
    "\n",
    "df[\"mode\"] = df[\"mode\"].map(map_mode)\n",
    "df[\"key\"] = df[\"key\"].map(map_key)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "check_dups = df[[\"artists\", \"name\"]]\n",
    "dups = check_dups[check_dups.duplicated()].index"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "print(\"Before dropping duplicated:\", df.shape)\n",
    "df = df.drop(dups)\n",
    "print(\"After dropping duplicated:\", df.shape)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Header 1.3\n",
    "\n",
    "## Header 2.3\n",
    "\n",
    "### Header 3.5"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "df[\"duration_ms\"] = df[\"duration_ms\"] / 60_000\n",
    "df = df.rename(columns={\"duration_ms\": \"duration_min\"})\n",
    "df.head()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Header 1.4\n",
    "\n",
    "## Header 2.4\n",
    "\n",
    "### Header 3.5"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "df = df.drop([\"release_date\", \"id\"], axis=1)\n",
    "df.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "def fun_subplots_plotly(df, col):\n",
    "\n",
    "    mean_val = df[col].mean()\n",
    "    median_val = df[col].median()\n",
    "    fig = make_subplots(rows=1, cols=2, column_widths=[0.75, 0.25])\n",
    "\n",
    "    fig.add_trace(\n",
    "        go.Histogram(\n",
    "            x=df[col], name=f\"Histogram {col}\", marker={\"color\": \"#EBA0AC\"}, nbinsx=50\n",
    "        ),\n",
    "        row=1,\n",
    "        col=1,\n",
    "    )\n",
    "\n",
    "    fig.add_shape(\n",
    "        type=\"line\",\n",
    "        xref=\"paper\",\n",
    "        yref=\"y\",\n",
    "        x0=-1,\n",
    "        x1=1,\n",
    "        y0=mean_val,\n",
    "        y1=mean_val,\n",
    "        row=1,\n",
    "        col=2,\n",
    "        line={\"color\": \"#A6E3A1\", \"width\": 3, \"dash\": \"dot\"},\n",
    "    )\n",
    "\n",
    "    fig.add_shape(\n",
    "        type=\"line\",\n",
    "        xref=\"paper\",\n",
    "        yref=\"y\",\n",
    "        x0=-1,\n",
    "        x1=1,\n",
    "        y0=median_val,\n",
    "        y1=median_val,\n",
    "        row=1,\n",
    "        col=2,\n",
    "        line={\"color\": \"#CBA6F7\", \"width\": 3, \"dash\": \"dot\"},\n",
    "    )\n",
    "\n",
    "    fig.add_annotation(\n",
    "        xref=\"paper\",\n",
    "        x=-0.7,\n",
    "        y=mean_val,\n",
    "        showarrow=True,\n",
    "        arrowhead=2,\n",
    "        text=f\"Mean = {mean_val:.2f}\",\n",
    "        row=1,\n",
    "        col=2,\n",
    "    )\n",
    "\n",
    "    fig.add_annotation(\n",
    "        xref=\"paper\",\n",
    "        x=0.7,\n",
    "        y=median_val,\n",
    "        showarrow=True,\n",
    "        arrowhead=2,\n",
    "        text=f\"Median = {median_val:.2f}\",\n",
    "        row=1,\n",
    "        col=2,\n",
    "    )\n",
    "\n",
    "    fig.add_trace(\n",
    "        go.Box(y=df[col], name=f\"Boxplot {col}\", marker={\"color\": \"#F9E2AF\"}),\n",
    "        row=1,\n",
    "        col=2,\n",
    "    )\n",
    "\n",
    "    fig.update_layout(\n",
    "        title={\"text\": f\"Distribution Plot {col}\", \"font\": {\"size\": 24}},\n",
    "        legend={\n",
    "            \"orientation\": \"h\",\n",
    "            \"yanchor\": \"bottom\",\n",
    "            \"y\": 1.02,\n",
    "            \"xanchor\": \"right\",\n",
    "            \"x\": 1,\n",
    "        },\n",
    "    )\n",
    "    fig.update_yaxes(title_text=\"Count\", row=1, col=1)\n",
    "    fig.update_yaxes(title_text=f\"{col}\", row=1, col=2)\n",
    "    fig.update_xaxes(title_text=f\"{col}\", row=1, col=1)\n",
    "    fig.update_xaxes(title_text=\"\", row=1, col=2)\n",
    "    fig.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "music_vals = [\n",
    "    \"valence\",\n",
    "    \"acousticness\",\n",
    "    \"danceability\",\n",
    "    \"duration_min\",\n",
    "    \"energy\",\n",
    "    \"instrumentalness\",\n",
    "    \"liveness\",\n",
    "    \"loudness\",\n",
    "    \"popularity\",\n",
    "    \"speechiness\",\n",
    "    \"tempo\",\n",
    "]\n",
    "\n",
    "for col in music_vals:\n",
    "    fun_subplots_plotly(df, col)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Header 1.2\n",
    "\n",
    "## Header 2.2\n",
    "\n",
    "### Header 3.4"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "bins = pd.IntervalIndex.from_breaks(\n",
    "    [1920, 1930, 1940, 1950, 1960, 1970, 1980, 1990, 2000, 2010, 2020]\n",
    ")\n",
    "\n",
    "df[\"decade\"] = pd.cut(df[\"year\"], bins).astype(\"str\")\n",
    "\n",
    "map_decade = {\n",
    "    \"(1920, 1930]\": \"1920s\",\n",
    "    \"(1930, 1940]\": \"1930s\",\n",
    "    \"(1940, 1950]\": \"1940s\",\n",
    "    \"(1950, 1960]\": \"1950s\",\n",
    "    \"(1960, 1970]\": \"1960s\",\n",
    "    \"(1970, 1980]\": \"1970s\",\n",
    "    \"(1980, 1990]\": \"1980s\",\n",
    "    \"(1990, 2000]\": \"1990s\",\n",
    "    \"(2000, 2010]\": \"2000s\",\n",
    "    \"(2010, 2020]\": \"2010s\",\n",
    "}\n",
    "\n",
    "df[\"decade\"] = df[\"decade\"].map(map_decade)\n",
    "\n",
    "df.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "decade_counts = (\n",
    "    df[\"decade\"].value_counts().reset_index().sort_values(by=\"decade\", ascending=True)\n",
    ")\n",
    "\n",
    "fig = px.bar(\n",
    "    data_frame=decade_counts,\n",
    "    y=\"decade\",\n",
    "    x=\"count\",\n",
    "    color=\"count\",\n",
    "    color_continuous_scale=px.colors.sequential.Sunset,\n",
    "    text_auto=True,\n",
    ")\n",
    "\n",
    "fig.update_layout(\n",
    "    title={\"text\": \"Count of songs per decade\", \"font\": {\"size\": 24}},\n",
    "    coloraxis_colorbar={\n",
    "        \"title\": \"Count\",\n",
    "        \"thicknessmode\": \"pixels\",\n",
    "        \"thickness\": 20,\n",
    "        \"lenmode\": \"pixels\",\n",
    "        \"len\": 500,\n",
    "        \"yanchor\": \"top\",\n",
    "        \"xanchor\": \"right\",\n",
    "        \"y\": 1.15,\n",
    "        \"x\": 0.95,\n",
    "        \"orientation\": \"h\",\n",
    "    },\n",
    "    margin={\"r\": 10},\n",
    ")\n",
    "\n",
    "fig.update_xaxes(title=\"Count\")\n",
    "fig.update_yaxes(title=\"Decades\")\n",
    "fig.show()\n",
    "\n",
    "del decade_counts"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "df = df.query(\"duration_min <= 5\")"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Header 1.2\n",
    "\n",
    "## Header 2.2\n",
    "\n",
    "### Header 3.4"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "decade_counts = (\n",
    "    df[\"decade\"].value_counts().reset_index().sort_values(by=\"decade\", ascending=True)\n",
    ")\n",
    "\n",
    "fig = px.bar(\n",
    "    data_frame=decade_counts,\n",
    "    y=\"decade\",\n",
    "    x=\"count\",\n",
    "    color=\"count\",\n",
    "    color_continuous_scale=px.colors.sequential.Sunset,\n",
    "    text_auto=True,\n",
    ")\n",
    "\n",
    "fig.update_layout(\n",
    "    title={\"text\": \"Count of songs per decade (< 5min)\", \"font\": {\"size\": 24}},\n",
    "    coloraxis_colorbar={\n",
    "        \"title\": \"Count\",\n",
    "        \"thicknessmode\": \"pixels\",\n",
    "        \"thickness\": 20,\n",
    "        \"lenmode\": \"pixels\",\n",
    "        \"len\": 500,\n",
    "        \"yanchor\": \"top\",\n",
    "        \"xanchor\": \"right\",\n",
    "        \"y\": 1.15,\n",
    "        \"x\": 0.95,\n",
    "        \"orientation\": \"h\",\n",
    "    },\n",
    "    margin={\"r\": 10},\n",
    ")\n",
    "\n",
    "fig.update_xaxes(title=\"Count\")\n",
    "fig.update_yaxes(title=\"Decades\")\n",
    "fig.show()\n",
    "\n",
    "del decade_counts"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "cols = [\n",
    "    \"valence\",\n",
    "    \"acousticness\",\n",
    "    \"danceability\",\n",
    "    \"duration_min\",\n",
    "    \"energy\",\n",
    "    \"instrumentalness\",\n",
    "    \"liveness\",\n",
    "    \"loudness\",\n",
    "    \"popularity\",\n",
    "    \"speechiness\",\n",
    "    \"tempo\",\n",
    "]\n",
    "for col in cols:\n",
    "    fig = px.histogram(\n",
    "        data_frame=df,\n",
    "        x=col,\n",
    "        color=\"decade\",\n",
    "        color_discrete_sequence=px.colors.qualitative.Light24,\n",
    "    )\n",
    "    fig.update_traces(opacity=0.7)\n",
    "    fig.update_layout(\n",
    "        bargap=0.1,\n",
    "        bargroupgap=0.05,\n",
    "        barmode=\"stack\",\n",
    "        title={\"text\": f\"Histogram of {col} per decade\", \"font\": {\"size\": 24}},\n",
    "        legend={\"title\": \"Decade\"},\n",
    "    )\n",
    "    fig.update_yaxes(title=\"Count\")\n",
    "    fig.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "decade_mean = df.groupby(\"decade\")[cols].mean()\n",
    "\n",
    "fig = make_subplots(\n",
    "    rows=4,\n",
    "    cols=3,\n",
    "    subplot_titles=(\n",
    "        decade_mean.columns[0],\n",
    "        decade_mean.columns[1],\n",
    "        decade_mean.columns[2],\n",
    "        decade_mean.columns[3],\n",
    "        decade_mean.columns[4],\n",
    "        decade_mean.columns[5],\n",
    "        decade_mean.columns[6],\n",
    "        decade_mean.columns[7],\n",
    "        decade_mean.columns[8],\n",
    "        decade_mean.columns[9],\n",
    "        decade_mean.columns[10],\n",
    "    ),\n",
    "    vertical_spacing=0.1,\n",
    ")\n",
    "\n",
    "fig.add_trace(\n",
    "    go.Bar(\n",
    "        y=decade_mean.index,\n",
    "        x=decade_mean.iloc[:, 0],\n",
    "        name=decade_mean.columns[0],\n",
    "        orientation=\"h\",\n",
    "    ),\n",
    "    row=1,\n",
    "    col=1,\n",
    ")\n",
    "\n",
    "fig.add_trace(\n",
    "    go.Bar(\n",
    "        y=decade_mean.index,\n",
    "        x=decade_mean.iloc[:, 1],\n",
    "        name=decade_mean.columns[1],\n",
    "        orientation=\"h\",\n",
    "    ),\n",
    "    row=1,\n",
    "    col=2,\n",
    ")\n",
    "\n",
    "fig.add_trace(\n",
    "    go.Bar(\n",
    "        y=decade_mean.index,\n",
    "        x=decade_mean.iloc[:, 2],\n",
    "        name=decade_mean.columns[2],\n",
    "        orientation=\"h\",\n",
    "    ),\n",
    "    row=1,\n",
    "    col=3,\n",
    ")\n",
    "\n",
    "fig.add_trace(\n",
    "    go.Bar(\n",
    "        y=decade_mean.index,\n",
    "        x=decade_mean.iloc[:, 3],\n",
    "        name=decade_mean.columns[3],\n",
    "        orientation=\"h\",\n",
    "    ),\n",
    "    row=2,\n",
    "    col=1,\n",
    ")\n",
    "\n",
    "fig.add_trace(\n",
    "    go.Bar(\n",
    "        y=decade_mean.index,\n",
    "        x=decade_mean.iloc[:, 4],\n",
    "        name=decade_mean.columns[4],\n",
    "        orientation=\"h\",\n",
    "    ),\n",
    "    row=2,\n",
    "    col=2,\n",
    ")\n",
    "\n",
    "fig.add_trace(\n",
    "    go.Bar(\n",
    "        y=decade_mean.index,\n",
    "        x=decade_mean.iloc[:, 5],\n",
    "        name=decade_mean.columns[5],\n",
    "        orientation=\"h\",\n",
    "    ),\n",
    "    row=2,\n",
    "    col=3,\n",
    ")\n",
    "\n",
    "fig.add_trace(\n",
    "    go.Bar(\n",
    "        y=decade_mean.index,\n",
    "        x=decade_mean.iloc[:, 6],\n",
    "        name=decade_mean.columns[6],\n",
    "        orientation=\"h\",\n",
    "    ),\n",
    "    row=3,\n",
    "    col=1,\n",
    ")\n",
    "\n",
    "fig.add_trace(\n",
    "    go.Bar(\n",
    "        y=decade_mean.index,\n",
    "        x=decade_mean.iloc[:, 7],\n",
    "        name=decade_mean.columns[7],\n",
    "        orientation=\"h\",\n",
    "    ),\n",
    "    row=3,\n",
    "    col=2,\n",
    ")\n",
    "\n",
    "fig.add_trace(\n",
    "    go.Bar(\n",
    "        y=decade_mean.index,\n",
    "        x=decade_mean.iloc[:, 8],\n",
    "        name=decade_mean.columns[8],\n",
    "        orientation=\"h\",\n",
    "    ),\n",
    "    row=3,\n",
    "    col=3,\n",
    ")\n",
    "\n",
    "fig.add_trace(\n",
    "    go.Bar(\n",
    "        y=decade_mean.index,\n",
    "        x=decade_mean.iloc[:, 9],\n",
    "        name=decade_mean.columns[9],\n",
    "        orientation=\"h\",\n",
    "    ),\n",
    "    row=4,\n",
    "    col=1,\n",
    ")\n",
    "\n",
    "fig.add_trace(\n",
    "    go.Bar(\n",
    "        y=decade_mean.index,\n",
    "        x=decade_mean.iloc[:, 10],\n",
    "        name=decade_mean.columns[10],\n",
    "        orientation=\"h\",\n",
    "    ),\n",
    "    row=4,\n",
    "    col=2,\n",
    ")\n",
    "\n",
    "fig.update_layout(\n",
    "    title={\"text\": \"Mean Musical Values per Decade\", \"font\": {\"size\": 22}},\n",
    "    legend={\n",
    "        \"orientation\": \"v\",\n",
    "        \"yanchor\": \"top\",\n",
    "        \"y\": 0.2,\n",
    "        \"xanchor\": \"right\",\n",
    "        \"x\": 0.9,\n",
    "    },\n",
    "    margin={\"b\": 10, \"r\": 10},\n",
    "    height=980,\n",
    ")\n",
    "\n",
    "fig.show()\n",
    "\n",
    "del decade_mean"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "decade_median = df.groupby(\"decade\")[cols].median()\n",
    "\n",
    "fig = make_subplots(\n",
    "    rows=4,\n",
    "    cols=3,\n",
    "    subplot_titles=(\n",
    "        decade_median.columns[0],\n",
    "        decade_median.columns[1],\n",
    "        decade_median.columns[2],\n",
    "        decade_median.columns[3],\n",
    "        decade_median.columns[4],\n",
    "        decade_median.columns[5],\n",
    "        decade_median.columns[6],\n",
    "        decade_median.columns[7],\n",
    "        decade_median.columns[8],\n",
    "        decade_median.columns[9],\n",
    "        decade_median.columns[10],\n",
    "    ),\n",
    "    vertical_spacing=0.1,\n",
    ")\n",
    "\n",
    "fig.add_trace(\n",
    "    go.Bar(\n",
    "        y=decade_median.index,\n",
    "        x=decade_median.iloc[:, 0],\n",
    "        name=decade_median.columns[0],\n",
    "        orientation=\"h\",\n",
    "    ),\n",
    "    row=1,\n",
    "    col=1,\n",
    ")\n",
    "\n",
    "fig.add_trace(\n",
    "    go.Bar(\n",
    "        y=decade_median.index,\n",
    "        x=decade_median.iloc[:, 1],\n",
    "        name=decade_median.columns[1],\n",
    "        orientation=\"h\",\n",
    "    ),\n",
    "    row=1,\n",
    "    col=2,\n",
    ")\n",
    "\n",
    "fig.add_trace(\n",
    "    go.Bar(\n",
    "        y=decade_median.index,\n",
    "        x=decade_median.iloc[:, 2],\n",
    "        name=decade_median.columns[2],\n",
    "        orientation=\"h\",\n",
    "    ),\n",
    "    row=1,\n",
    "    col=3,\n",
    ")\n",
    "\n",
    "fig.add_trace(\n",
    "    go.Bar(\n",
    "        y=decade_median.index,\n",
    "        x=decade_median.iloc[:, 3],\n",
    "        name=decade_median.columns[3],\n",
    "        orientation=\"h\",\n",
    "    ),\n",
    "    row=2,\n",
    "    col=1,\n",
    ")\n",
    "\n",
    "fig.add_trace(\n",
    "    go.Bar(\n",
    "        y=decade_median.index,\n",
    "        x=decade_median.iloc[:, 4],\n",
    "        name=decade_median.columns[4],\n",
    "        orientation=\"h\",\n",
    "    ),\n",
    "    row=2,\n",
    "    col=2,\n",
    ")\n",
    "\n",
    "fig.add_trace(\n",
    "    go.Bar(\n",
    "        y=decade_median.index,\n",
    "        x=decade_median.iloc[:, 5],\n",
    "        name=decade_median.columns[5],\n",
    "        orientation=\"h\",\n",
    "    ),\n",
    "    row=2,\n",
    "    col=3,\n",
    ")\n",
    "\n",
    "fig.add_trace(\n",
    "    go.Bar(\n",
    "        y=decade_median.index,\n",
    "        x=decade_median.iloc[:, 6],\n",
    "        name=decade_median.columns[6],\n",
    "        orientation=\"h\",\n",
    "    ),\n",
    "    row=3,\n",
    "    col=1,\n",
    ")\n",
    "\n",
    "fig.add_trace(\n",
    "    go.Bar(\n",
    "        y=decade_median.index,\n",
    "        x=decade_median.iloc[:, 7],\n",
    "        name=decade_median.columns[7],\n",
    "        orientation=\"h\",\n",
    "    ),\n",
    "    row=3,\n",
    "    col=2,\n",
    ")\n",
    "\n",
    "fig.add_trace(\n",
    "    go.Bar(\n",
    "        y=decade_median.index,\n",
    "        x=decade_median.iloc[:, 8],\n",
    "        name=decade_median.columns[8],\n",
    "        orientation=\"h\",\n",
    "    ),\n",
    "    row=3,\n",
    "    col=3,\n",
    ")\n",
    "\n",
    "fig.add_trace(\n",
    "    go.Bar(\n",
    "        y=decade_median.index,\n",
    "        x=decade_median.iloc[:, 9],\n",
    "        name=decade_median.columns[9],\n",
    "        orientation=\"h\",\n",
    "    ),\n",
    "    row=4,\n",
    "    col=1,\n",
    ")\n",
    "\n",
    "fig.add_trace(\n",
    "    go.Bar(\n",
    "        y=decade_median.index,\n",
    "        x=decade_median.iloc[:, 10],\n",
    "        name=decade_median.columns[10],\n",
    "        orientation=\"h\",\n",
    "    ),\n",
    "    row=4,\n",
    "    col=2,\n",
    ")\n",
    "\n",
    "fig.update_layout(\n",
    "    title={\"text\": \"Median Musical Values per Decade\", \"font\": {\"size\": 22}},\n",
    "    legend={\n",
    "        \"orientation\": \"v\",\n",
    "        \"yanchor\": \"top\",\n",
    "        \"y\": 0.2,\n",
    "        \"xanchor\": \"right\",\n",
    "        \"x\": 0.9,\n",
    "    },\n",
    "    margin={\"b\": 10, \"r\": 10},\n",
    "    height=980,\n",
    ")\n",
    "\n",
    "fig.show()\n",
    "\n",
    "del decade_median"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "explicit_count = (\n",
    "    df.groupby([\"decade\", \"explicit\"], as_index=False)[\"year\"]\n",
    "    .count()\n",
    "    .rename(columns={\"year\": \"count\"})\n",
    ")\n",
    "key_count = (\n",
    "    df.groupby([\"decade\", \"key\"], as_index=False)[\"year\"]\n",
    "    .count()\n",
    "    .rename(columns={\"year\": \"count\"})\n",
    ")\n",
    "mode_count = (\n",
    "    df.groupby([\"decade\", \"mode\"], as_index=False)[\"year\"]\n",
    "    .count()\n",
    "    .rename(columns={\"year\": \"count\"})\n",
    ")\n",
    "\n",
    "fig = px.histogram(\n",
    "    data_frame=explicit_count,\n",
    "    x=\"decade\",\n",
    "    y=\"count\",\n",
    "    color=\"explicit\",\n",
    "    histfunc=\"sum\",\n",
    "    color_discrete_sequence=px.colors.qualitative.Pastel,\n",
    "    text_auto=True,\n",
    ")\n",
    "fig.update_layout(\n",
    "    title={\"text\": \"Explicit Count per Decade\", \"font\": {\"size\": 24}},\n",
    "    bargap=0.2,\n",
    "    bargroupgap=0.1,\n",
    "    barmode=\"group\",\n",
    "    xaxis_title=\"Decade\",\n",
    "    yaxis_title=\"Count\",\n",
    ")\n",
    "fig.show()\n",
    "\n",
    "fig = px.histogram(\n",
    "    data_frame=mode_count,\n",
    "    x=\"decade\",\n",
    "    y=\"count\",\n",
    "    color=\"mode\",\n",
    "    histfunc=\"sum\",\n",
    "    color_discrete_sequence=px.colors.qualitative.Pastel,\n",
    "    text_auto=True,\n",
    ")\n",
    "fig.update_layout(\n",
    "    title={\"text\": \"Mode Count per Decade\", \"font\": {\"size\": 24}},\n",
    "    bargap=0.2,\n",
    "    bargroupgap=0.1,\n",
    "    barmode=\"group\",\n",
    "    xaxis_title=\"Decade\",\n",
    "    yaxis_title=\"Count\",\n",
    ")\n",
    "fig.show()\n",
    "\n",
    "fig = px.histogram(\n",
    "    data_frame=key_count,\n",
    "    x=\"decade\",\n",
    "    y=\"count\",\n",
    "    color=\"key\",\n",
    "    histfunc=\"sum\",\n",
    "    color_discrete_sequence=px.colors.qualitative.Pastel,\n",
    "    text_auto=True,\n",
    ")\n",
    "fig.update_layout(\n",
    "    title={\"text\": \"Key Count per Decade\", \"font\": {\"size\": 24}},\n",
    "    bargap=0.2,\n",
    "    bargroupgap=0.1,\n",
    "    barmode=\"stack\",\n",
    "    xaxis_title=\"Decade\",\n",
    "    yaxis_title=\"Count\",\n",
    ")\n",
    "fig.show()\n",
    "\n",
    "del (mode_count, key_count, explicit_count)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "cols = [\n",
    "    \"valence\",\n",
    "    \"acousticness\",\n",
    "    \"danceability\",\n",
    "    \"duration_min\",\n",
    "    \"energy\",\n",
    "    \"instrumentalness\",\n",
    "    \"liveness\",\n",
    "    \"loudness\",\n",
    "    \"year\",\n",
    "    \"speechiness\",\n",
    "    \"tempo\",\n",
    "]\n",
    "\n",
    "for col in cols:\n",
    "\n",
    "    fig = px.scatter(\n",
    "        data_frame=df,\n",
    "        x=col,\n",
    "        y=\"popularity\",\n",
    "        trendline=\"ols\",\n",
    "        trendline_color_override=\"#A6E3A1\",\n",
    "    )\n",
    "    fig.update_traces(marker={\"opacity\": 0.3, \"size\": 3, \"color\": \"#B4BEFE\"})\n",
    "    fig.update_layout(title={\"text\": f\"{col} vs popularity\", \"font\": {\"size\": 24}})\n",
    "    fig.show()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Header 1\n",
    "\n",
    "## Header 2\n",
    "\n",
    "### Header 3.1"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "cols = [\n",
    "    \"valence\",\n",
    "    \"acousticness\",\n",
    "    \"danceability\",\n",
    "    \"duration_min\",\n",
    "    \"energy\",\n",
    "    \"instrumentalness\",\n",
    "    \"liveness\",\n",
    "    \"loudness\",\n",
    "    \"year\",\n",
    "    \"speechiness\",\n",
    "    \"tempo\",\n",
    "]\n",
    "\n",
    "plt.figure(figsize=(15, 10))\n",
    "\n",
    "for i, col in enumerate(cols):\n",
    "    ax = plt.subplot(3, 4, i + 1)\n",
    "    sns.regplot(\n",
    "        data=df,\n",
    "        x=\"popularity\",\n",
    "        y=col,\n",
    "        ax=ax,\n",
    "        scatter_kws={\"alpha\": 0.5},\n",
    "        line_kws={\"color\": \"#F38BA8\"},\n",
    "    )\n",
    "\n",
    "plt.tight_layout()\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "cols = [\n",
    "    \"valence\",\n",
    "    \"acousticness\",\n",
    "    \"danceability\",\n",
    "    \"duration_min\",\n",
    "    \"energy\",\n",
    "    \"instrumentalness\",\n",
    "    \"liveness\",\n",
    "    \"loudness\",\n",
    "    \"year\",\n",
    "    \"speechiness\",\n",
    "    \"tempo\",\n",
    "    \"popularity\",\n",
    "]\n",
    "\n",
    "plt.figure(figsize=(10, 7))\n",
    "mask = np.triu(np.ones_like(df[cols].corr()))\n",
    "sns.heatmap(\n",
    "    df[cols].corr(),\n",
    "    annot=True,\n",
    "    fmt=\".2f\",\n",
    "    cmap=\"Blues\",\n",
    "    mask=mask,\n",
    ")\n",
    "plt.grid(visible=False)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "df[\"first_artist\"] = (\n",
    "    df[\"artists\"]\n",
    "    .apply(lambda x: str(x).split(\"x\")[0])\n",
    "    .apply(lambda x: str(x).replace(\"[\", \"\"))\n",
    "    .apply(lambda x: str(x).replace(\"]\", \"\"))\n",
    "    .apply(lambda x: str(x).replace(\"'\", \"\"))\n",
    ")\n",
    "df = df.drop(\"artists\", axis=1)\n",
    "df[\"first_artist\"] = df[\"first_artist\"].apply(lambda x: str(x).split(\",\")[0])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "popularity_check = (\n",
    "    df.groupby([\"first_artist\"], as_index=False)[\"popularity\"]\n",
    "    .agg({\"mean\", \"count\", \"median\"})\n",
    "    .sort_values(by=\"mean\", ascending=False)\n",
    "    .reset_index(drop=True)\n",
    ")\n",
    "\n",
    "popularity_check = popularity_check.drop(16091, axis=0)\n",
    "popularity_check = popularity_check.drop(16086, axis=0)\n",
    "popularity_check = popularity_check.drop(16429, axis=0)\n",
    "\n",
    "to_drop = popularity_check[popularity_check[\"count\"] <= 45].index\n",
    "popularity_check = popularity_check.drop(to_drop)\n",
    "popularity_check = popularity_check.sort_values(by=\"mean\", ascending=False).head(50)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Header 1\n",
    "\n",
    "## Header 2\n",
    "\n",
    "### Header 3.1"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "top_50_artists = pd.DataFrame()\n",
    "\n",
    "for i in popularity_check[\"first_artist\"].unique():\n",
    "    artist = df.query(\"first_artist == @i\")\n",
    "    top_50_artists = pd.concat([top_50_artists, artist], axis=0)\n",
    "\n",
    "top_50_artists = top_50_artists.reset_index(drop=True)\n",
    "top_50_artists.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "plt.figure(figsize=(12, 8))\n",
    "(\n",
    "    top_50_artists[\"first_artist\"]\n",
    "    .value_counts()\n",
    "    .sort_values(ascending=True)\n",
    "    .plot(kind=\"barh\")\n",
    ")\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "top_50_artists[\"decade\"].value_counts().sort_values(ascending=True).plot(kind=\"barh\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "cols = [\n",
    "    \"valence\",\n",
    "    \"acousticness\",\n",
    "    \"danceability\",\n",
    "    \"duration_min\",\n",
    "    \"energy\",\n",
    "    \"instrumentalness\",\n",
    "    \"liveness\",\n",
    "    \"loudness\",\n",
    "    \"year\",\n",
    "    \"speechiness\",\n",
    "    \"tempo\",\n",
    "]\n",
    "\n",
    "plt.figure(figsize=(15, 10))\n",
    "\n",
    "for i, col in enumerate(cols):\n",
    "    ax = plt.subplot(3, 4, i + 1)\n",
    "    sns.kdeplot(data=top_50_artists, x=col, hue=\"first_artist\", legend=False)\n",
    "\n",
    "plt.tight_layout()\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Header 1\n",
    "\n",
    "## Header 2\n",
    "\n",
    "### Header 3.1"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "import pandas as pd\n",
    "import numpy as np\n",
    "import seaborn as sns\n",
    "import matplotlib.pyplot as plt\n",
    "import matplotlib as mpl\n",
    "import mplcatppuccin\n",
    "import plotly.express as px\n",
    "import plotly.graph_objects as go\n",
    "from plotly.subplots import make_subplots\n",
    "import plotly.figure_factory as ff\n",
    "import warnings\n",
    "import plotly.io as pio\n",
    "\n",
    "warnings.filterwarnings('ignore')\n",
    "\n",
    "pio.renderers.default = 'notebook_connected'\n",
    "pio.templates.default = 'plotly_dark'\n",
    "\n",
    "\n",
    "%matplotlib inline\n",
    "%config InlineBackend.figure_format = 'retina'\n",
    "pd.set_option('display.max_columns', None)\n",
    "pd.set_option('display.precision', 2)\n",
    "pd.set_option('display.colheader_justify', 'left')\n",
    "\n",
    "mpl.rc(\n",
    "    'figure',\n",
    "    autolayout=True,\n",
    "    titlesize=18\n",
    ")\n",
    "\n",
    "mpl.style.use(['ggplot', 'mocha'])\n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Header 3.2\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "df = pd.read_csv(\n",
    "    \"data.csv\",\n",
    "    parse_dates=[\"release_date\"],\n",
    ")\n",
    "df.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "map_key = {\n",
    "    0: \"C\",\n",
    "    1: \"C#\",\n",
    "    2: \"D\",\n",
    "    3: \"D#\",\n",
    "    4: \"E\",\n",
    "    5: \"F\",\n",
    "    6: \"F#\",\n",
    "    7: \"G\",\n",
    "    8: \"G#\",\n",
    "    9: \"A\",\n",
    "    10: \"A#\",\n",
    "    11: \"B\",\n",
    "}\n",
    "\n",
    "map_mode = {1: \"Major\", 0: \"Minor\"}\n",
    "\n",
    "df[\"mode\"] = df[\"mode\"].map(map_mode)\n",
    "df[\"key\"] = df[\"key\"].map(map_key)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "check_dups = df[[\"artists\", \"name\"]]\n",
    "dups = check_dups[check_dups.duplicated()].index"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "print(\"Before dropping duplicated:\", df.shape)\n",
    "df = df.drop(dups)\n",
    "print(\"After dropping duplicated:\", df.shape)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Header 1.3\n",
    "\n",
    "## Header 2.3\n",
    "\n",
    "### Header 3.5"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "df[\"duration_ms\"] = df[\"duration_ms\"] / 60_000\n",
    "df = df.rename(columns={\"duration_ms\": \"duration_min\"})\n",
    "df.head()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Header 1.4\n",
    "\n",
    "## Header 2.4\n",
    "\n",
    "### Header 3.5"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "df = df.drop([\"release_date\", \"id\"], axis=1)\n",
    "df.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "def fun_subplots_plotly(df, col):\n",
    "\n",
    "    mean_val = df[col].mean()\n",
    "    median_val = df[col].median()\n",
    "    fig = make_subplots(rows=1, cols=2, column_widths=[0.75, 0.25])\n",
    "\n",
    "    fig.add_trace(\n",
    "        go.Histogram(\n",
    "            x=df[col], name=f\"Histogram {col}\", marker={\"color\": \"#EBA0AC\"}, nbinsx=50\n",
    "        ),\n",
    "        row=1,\n",
    "        col=1,\n",
    "    )\n",
    "\n",
    "    fig.add_shape(\n",
    "        type=\"line\",\n",
    "        xref=\"paper\",\n",
    "        yref=\"y\",\n",
    "        x0=-1,\n",
    "        x1=1,\n",
    "        y0=mean_val,\n",
    "        y1=mean_val,\n",
    "        row=1,\n",
    "        col=2,\n",
    "        line={\"color\": \"#A6E3A1\", \"width\": 3, \"dash\": \"dot\"},\n",
    "    )\n",
    "\n",
    "    fig.add_shape(\n",
    "        type=\"line\",\n",
    "        xref=\"paper\",\n",
    "        yref=\"y\",\n",
    "        x0=-1,\n",
    "        x1=1,\n",
    "        y0=median_val,\n",
    "        y1=median_val,\n",
    "        row=1,\n",
    "        col=2,\n",
    "        line={\"color\": \"#CBA6F7\", \"width\": 3, \"dash\": \"dot\"},\n",
    "    )\n",
    "\n",
    "    fig.add_annotation(\n",
    "        xref=\"paper\",\n",
    "        x=-0.7,\n",
    "        y=mean_val,\n",
    "        showarrow=True,\n",
    "        arrowhead=2,\n",
    "        text=f\"Mean = {mean_val:.2f}\",\n",
    "        row=1,\n",
    "        col=2,\n",
    "    )\n",
    "\n",
    "    fig.add_annotation(\n",
    "        xref=\"paper\",\n",
    "        x=0.7,\n",
    "        y=median_val,\n",
    "        showarrow=True,\n",
    "        arrowhead=2,\n",
    "        text=f\"Median = {median_val:.2f}\",\n",
    "        row=1,\n",
    "        col=2,\n",
    "    )\n",
    "\n",
    "    fig.add_trace(\n",
    "        go.Box(y=df[col], name=f\"Boxplot {col}\", marker={\"color\": \"#F9E2AF\"}),\n",
    "        row=1,\n",
    "        col=2,\n",
    "    )\n",
    "\n",
    "    fig.update_layout(\n",
    "        title={\"text\": f\"Distribution Plot {col}\", \"font\": {\"size\": 24}},\n",
    "        legend={\n",
    "            \"orientation\": \"h\",\n",
    "            \"yanchor\": \"bottom\",\n",
    "            \"y\": 1.02,\n",
    "            \"xanchor\": \"right\",\n",
    "            \"x\": 1,\n",
    "        },\n",
    "    )\n",
    "    fig.update_yaxes(title_text=\"Count\", row=1, col=1)\n",
    "    fig.update_yaxes(title_text=f\"{col}\", row=1, col=2)\n",
    "    fig.update_xaxes(title_text=f\"{col}\", row=1, col=1)\n",
    "    fig.update_xaxes(title_text=\"\", row=1, col=2)\n",
    "    fig.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "music_vals = [\n",
    "    \"valence\",\n",
    "    \"acousticness\",\n",
    "    \"danceability\",\n",
    "    \"duration_min\",\n",
    "    \"energy\",\n",
    "    \"instrumentalness\",\n",
    "    \"liveness\",\n",
    "    \"loudness\",\n",
    "    \"popularity\",\n",
    "    \"speechiness\",\n",
    "    \"tempo\",\n",
    "]\n",
    "\n",
    "for col in music_vals:\n",
    "    fun_subplots_plotly(df, col)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Header 1.2\n",
    "\n",
    "## Header 2.2\n",
    "\n",
    "### Header 3.4"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "bins = pd.IntervalIndex.from_breaks(\n",
    "    [1920, 1930, 1940, 1950, 1960, 1970, 1980, 1990, 2000, 2010, 2020]\n",
    ")\n",
    "\n",
    "df[\"decade\"] = pd.cut(df[\"year\"], bins).astype(\"str\")\n",
    "\n",
    "map_decade = {\n",
    "    \"(1920, 1930]\": \"1920s\",\n",
    "    \"(1930, 1940]\": \"1930s\",\n",
    "    \"(1940, 1950]\": \"1940s\",\n",
    "    \"(1950, 1960]\": \"1950s\",\n",
    "    \"(1960, 1970]\": \"1960s\",\n",
    "    \"(1970, 1980]\": \"1970s\",\n",
    "    \"(1980, 1990]\": \"1980s\",\n",
    "    \"(1990, 2000]\": \"1990s\",\n",
    "    \"(2000, 2010]\": \"2000s\",\n",
    "    \"(2010, 2020]\": \"2010s\",\n",
    "}\n",
    "\n",
    "df[\"decade\"] = df[\"decade\"].map(map_decade)\n",
    "\n",
    "df.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "decade_counts = (\n",
    "    df[\"decade\"].value_counts().reset_index().sort_values(by=\"decade\", ascending=True)\n",
    ")\n",
    "\n",
    "fig = px.bar(\n",
    "    data_frame=decade_counts,\n",
    "    y=\"decade\",\n",
    "    x=\"count\",\n",
    "    color=\"count\",\n",
    "    color_continuous_scale=px.colors.sequential.Sunset,\n",
    "    text_auto=True,\n",
    ")\n",
    "\n",
    "fig.update_layout(\n",
    "    title={\"text\": \"Count of songs per decade\", \"font\": {\"size\": 24}},\n",
    "    coloraxis_colorbar={\n",
    "        \"title\": \"Count\",\n",
    "        \"thicknessmode\": \"pixels\",\n",
    "        \"thickness\": 20,\n",
    "        \"lenmode\": \"pixels\",\n",
    "        \"len\": 500,\n",
    "        \"yanchor\": \"top\",\n",
    "        \"xanchor\": \"right\",\n",
    "        \"y\": 1.15,\n",
    "        \"x\": 0.95,\n",
    "        \"orientation\": \"h\",\n",
    "    },\n",
    "    margin={\"r\": 10},\n",
    ")\n",
    "\n",
    "fig.update_xaxes(title=\"Count\")\n",
    "fig.update_yaxes(title=\"Decades\")\n",
    "fig.show()\n",
    "\n",
    "del decade_counts"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "df = df.query(\"duration_min <= 5\")"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Header 1.2\n",
    "\n",
    "## Header 2.2\n",
    "\n",
    "### Header 3.4"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "decade_counts = (\n",
    "    df[\"decade\"].value_counts().reset_index().sort_values(by=\"decade\", ascending=True)\n",
    ")\n",
    "\n",
    "fig = px.bar(\n",
    "    data_frame=decade_counts,\n",
    "    y=\"decade\",\n",
    "    x=\"count\",\n",
    "    color=\"count\",\n",
    "    color_continuous_scale=px.colors.sequential.Sunset,\n",
    "    text_auto=True,\n",
    ")\n",
    "\n",
    "fig.update_layout(\n",
    "    title={\"text\": \"Count of songs per decade (< 5min)\", \"font\": {\"size\": 24}},\n",
    "    coloraxis_colorbar={\n",
    "        \"title\": \"Count\",\n",
    "        \"thicknessmode\": \"pixels\",\n",
    "        \"thickness\": 20,\n",
    "        \"lenmode\": \"pixels\",\n",
    "        \"len\": 500,\n",
    "        \"yanchor\": \"top\",\n",
    "        \"xanchor\": \"right\",\n",
    "        \"y\": 1.15,\n",
    "        \"x\": 0.95,\n",
    "        \"orientation\": \"h\",\n",
    "    },\n",
    "    margin={\"r\": 10},\n",
    ")\n",
    "\n",
    "fig.update_xaxes(title=\"Count\")\n",
    "fig.update_yaxes(title=\"Decades\")\n",
    "fig.show()\n",
    "\n",
    "del decade_counts"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "cols = [\n",
    "    \"valence\",\n",
    "    \"acousticness\",\n",
    "    \"danceability\",\n",
    "    \"duration_min\",\n",
    "    \"energy\",\n",
    "    \"instrumentalness\",\n",
    "    \"liveness\",\n",
    "    \"loudness\",\n",
    "    \"popularity\",\n",
    "    \"speechiness\",\n",
    "    \"tempo\",\n",
    "]\n",
    "for col in cols:\n",
    "    fig = px.histogram(\n",
    "        data_frame=df,\n",
    "        x=col,\n",
    "        color=\"decade\",\n",
    "        color_discrete_sequence=px.colors.qualitative.Light24,\n",
    "    )\n",
    "    fig.update_traces(opacity=0.7)\n",
    "    fig.update_layout(\n",
    "        bargap=0.1,\n",
    "        bargroupgap=0.05,\n",
    "        barmode=\"stack\",\n",
    "        title={\"text\": f\"Histogram of {col} per decade\", \"font\": {\"size\": 24}},\n",
    "        legend={\"title\": \"Decade\"},\n",
    "    )\n",
    "    fig.update_yaxes(title=\"Count\")\n",
    "    fig.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "decade_mean = df.groupby(\"decade\")[cols].mean()\n",
    "\n",
    "fig = make_subplots(\n",
    "    rows=4,\n",
    "    cols=3,\n",
    "    subplot_titles=(\n",
    "        decade_mean.columns[0],\n",
    "        decade_mean.columns[1],\n",
    "        decade_mean.columns[2],\n",
    "        decade_mean.columns[3],\n",
    "        decade_mean.columns[4],\n",
    "        decade_mean.columns[5],\n",
    "        decade_mean.columns[6],\n",
    "        decade_mean.columns[7],\n",
    "        decade_mean.columns[8],\n",
    "        decade_mean.columns[9],\n",
    "        decade_mean.columns[10],\n",
    "    ),\n",
    "    vertical_spacing=0.1,\n",
    ")\n",
    "\n",
    "fig.add_trace(\n",
    "    go.Bar(\n",
    "        y=decade_mean.index,\n",
    "        x=decade_mean.iloc[:, 0],\n",
    "        name=decade_mean.columns[0],\n",
    "        orientation=\"h\",\n",
    "    ),\n",
    "    row=1,\n",
    "    col=1,\n",
    ")\n",
    "\n",
    "fig.add_trace(\n",
    "    go.Bar(\n",
    "        y=decade_mean.index,\n",
    "        x=decade_mean.iloc[:, 1],\n",
    "        name=decade_mean.columns[1],\n",
    "        orientation=\"h\",\n",
    "    ),\n",
    "    row=1,\n",
    "    col=2,\n",
    ")\n",
    "\n",
    "fig.add_trace(\n",
    "    go.Bar(\n",
    "        y=decade_mean.index,\n",
    "        x=decade_mean.iloc[:, 2],\n",
    "        name=decade_mean.columns[2],\n",
    "        orientation=\"h\",\n",
    "    ),\n",
    "    row=1,\n",
    "    col=3,\n",
    ")\n",
    "\n",
    "fig.add_trace(\n",
    "    go.Bar(\n",
    "        y=decade_mean.index,\n",
    "        x=decade_mean.iloc[:, 3],\n",
    "        name=decade_mean.columns[3],\n",
    "        orientation=\"h\",\n",
    "    ),\n",
    "    row=2,\n",
    "    col=1,\n",
    ")\n",
    "\n",
    "fig.add_trace(\n",
    "    go.Bar(\n",
    "        y=decade_mean.index,\n",
    "        x=decade_mean.iloc[:, 4],\n",
    "        name=decade_mean.columns[4],\n",
    "        orientation=\"h\",\n",
    "    ),\n",
    "    row=2,\n",
    "    col=2,\n",
    ")\n",
    "\n",
    "fig.add_trace(\n",
    "    go.Bar(\n",
    "        y=decade_mean.index,\n",
    "        x=decade_mean.iloc[:, 5],\n",
    "        name=decade_mean.columns[5],\n",
    "        orientation=\"h\",\n",
    "    ),\n",
    "    row=2,\n",
    "    col=3,\n",
    ")\n",
    "\n",
    "fig.add_trace(\n",
    "    go.Bar(\n",
    "        y=decade_mean.index,\n",
    "        x=decade_mean.iloc[:, 6],\n",
    "        name=decade_mean.columns[6],\n",
    "        orientation=\"h\",\n",
    "    ),\n",
    "    row=3,\n",
    "    col=1,\n",
    ")\n",
    "\n",
    "fig.add_trace(\n",
    "    go.Bar(\n",
    "        y=decade_mean.index,\n",
    "        x=decade_mean.iloc[:, 7],\n",
    "        name=decade_mean.columns[7],\n",
    "        orientation=\"h\",\n",
    "    ),\n",
    "    row=3,\n",
    "    col=2,\n",
    ")\n",
    "\n",
    "fig.add_trace(\n",
    "    go.Bar(\n",
    "        y=decade_mean.index,\n",
    "        x=decade_mean.iloc[:, 8],\n",
    "        name=decade_mean.columns[8],\n",
    "        orientation=\"h\",\n",
    "    ),\n",
    "    row=3,\n",
    "    col=3,\n",
    ")\n",
    "\n",
    "fig.add_trace(\n",
    "    go.Bar(\n",
    "        y=decade_mean.index,\n",
    "        x=decade_mean.iloc[:, 9],\n",
    "        name=decade_mean.columns[9],\n",
    "        orientation=\"h\",\n",
    "    ),\n",
    "    row=4,\n",
    "    col=1,\n",
    ")\n",
    "\n",
    "fig.add_trace(\n",
    "    go.Bar(\n",
    "        y=decade_mean.index,\n",
    "        x=decade_mean.iloc[:, 10],\n",
    "        name=decade_mean.columns[10],\n",
    "        orientation=\"h\",\n",
    "    ),\n",
    "    row=4,\n",
    "    col=2,\n",
    ")\n",
    "\n",
    "fig.update_layout(\n",
    "    title={\"text\": \"Mean Musical Values per Decade\", \"font\": {\"size\": 22}},\n",
    "    legend={\n",
    "        \"orientation\": \"v\",\n",
    "        \"yanchor\": \"top\",\n",
    "        \"y\": 0.2,\n",
    "        \"xanchor\": \"right\",\n",
    "        \"x\": 0.9,\n",
    "    },\n",
    "    margin={\"b\": 10, \"r\": 10},\n",
    "    height=980,\n",
    ")\n",
    "\n",
    "fig.show()\n",
    "\n",
    "del decade_mean"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "decade_median = df.groupby(\"decade\")[cols].median()\n",
    "\n",
    "fig = make_subplots(\n",
    "    rows=4,\n",
    "    cols=3,\n",
    "    subplot_titles=(\n",
    "        decade_median.columns[0],\n",
    "        decade_median.columns[1],\n",
    "        decade_median.columns[2],\n",
    "        decade_median.columns[3],\n",
    "        decade_median.columns[4],\n",
    "        decade_median.columns[5],\n",
    "        decade_median.columns[6],\n",
    "        decade_median.columns[7],\n",
    "        decade_median.columns[8],\n",
    "        decade_median.columns[9],\n",
    "        decade_median.columns[10],\n",
    "    ),\n",
    "    vertical_spacing=0.1,\n",
    ")\n",
    "\n",
    "fig.add_trace(\n",
    "    go.Bar(\n",
    "        y=decade_median.index,\n",
    "        x=decade_median.iloc[:, 0],\n",
    "        name=decade_median.columns[0],\n",
    "        orientation=\"h\",\n",
    "    ),\n",
    "    row=1,\n",
    "    col=1,\n",
    ")\n",
    "\n",
    "fig.add_trace(\n",
    "    go.Bar(\n",
    "        y=decade_median.index,\n",
    "        x=decade_median.iloc[:, 1],\n",
    "        name=decade_median.columns[1],\n",
    "        orientation=\"h\",\n",
    "    ),\n",
    "    row=1,\n",
    "    col=2,\n",
    ")\n",
    "\n",
    "fig.add_trace(\n",
    "    go.Bar(\n",
    "        y=decade_median.index,\n",
    "        x=decade_median.iloc[:, 2],\n",
    "        name=decade_median.columns[2],\n",
    "        orientation=\"h\",\n",
    "    ),\n",
    "    row=1,\n",
    "    col=3,\n",
    ")\n",
    "\n",
    "fig.add_trace(\n",
    "    go.Bar(\n",
    "        y=decade_median.index,\n",
    "        x=decade_median.iloc[:, 3],\n",
    "        name=decade_median.columns[3],\n",
    "        orientation=\"h\",\n",
    "    ),\n",
    "    row=2,\n",
    "    col=1,\n",
    ")\n",
    "\n",
    "fig.add_trace(\n",
    "    go.Bar(\n",
    "        y=decade_median.index,\n",
    "        x=decade_median.iloc[:, 4],\n",
    "        name=decade_median.columns[4],\n",
    "        orientation=\"h\",\n",
    "    ),\n",
    "    row=2,\n",
    "    col=2,\n",
    ")\n",
    "\n",
    "fig.add_trace(\n",
    "    go.Bar(\n",
    "        y=decade_median.index,\n",
    "        x=decade_median.iloc[:, 5],\n",
    "        name=decade_median.columns[5],\n",
    "        orientation=\"h\",\n",
    "    ),\n",
    "    row=2,\n",
    "    col=3,\n",
    ")\n",
    "\n",
    "fig.add_trace(\n",
    "    go.Bar(\n",
    "        y=decade_median.index,\n",
    "        x=decade_median.iloc[:, 6],\n",
    "        name=decade_median.columns[6],\n",
    "        orientation=\"h\",\n",
    "    ),\n",
    "    row=3,\n",
    "    col=1,\n",
    ")\n",
    "\n",
    "fig.add_trace(\n",
    "    go.Bar(\n",
    "        y=decade_median.index,\n",
    "        x=decade_median.iloc[:, 7],\n",
    "        name=decade_median.columns[7],\n",
    "        orientation=\"h\",\n",
    "    ),\n",
    "    row=3,\n",
    "    col=2,\n",
    ")\n",
    "\n",
    "fig.add_trace(\n",
    "    go.Bar(\n",
    "        y=decade_median.index,\n",
    "        x=decade_median.iloc[:, 8],\n",
    "        name=decade_median.columns[8],\n",
    "        orientation=\"h\",\n",
    "    ),\n",
    "    row=3,\n",
    "    col=3,\n",
    ")\n",
    "\n",
    "fig.add_trace(\n",
    "    go.Bar(\n",
    "        y=decade_median.index,\n",
    "        x=decade_median.iloc[:, 9],\n",
    "        name=decade_median.columns[9],\n",
    "        orientation=\"h\",\n",
    "    ),\n",
    "    row=4,\n",
    "    col=1,\n",
    ")\n",
    "\n",
    "fig.add_trace(\n",
    "    go.Bar(\n",
    "        y=decade_median.index,\n",
    "        x=decade_median.iloc[:, 10],\n",
    "        name=decade_median.columns[10],\n",
    "        orientation=\"h\",\n",
    "    ),\n",
    "    row=4,\n",
    "    col=2,\n",
    ")\n",
    "\n",
    "fig.update_layout(\n",
    "    title={\"text\": \"Median Musical Values per Decade\", \"font\": {\"size\": 22}},\n",
    "    legend={\n",
    "        \"orientation\": \"v\",\n",
    "        \"yanchor\": \"top\",\n",
    "        \"y\": 0.2,\n",
    "        \"xanchor\": \"right\",\n",
    "        \"x\": 0.9,\n",
    "    },\n",
    "    margin={\"b\": 10, \"r\": 10},\n",
    "    height=980,\n",
    ")\n",
    "\n",
    "fig.show()\n",
    "\n",
    "del decade_median"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "explicit_count = (\n",
    "    df.groupby([\"decade\", \"explicit\"], as_index=False)[\"year\"]\n",
    "    .count()\n",
    "    .rename(columns={\"year\": \"count\"})\n",
    ")\n",
    "key_count = (\n",
    "    df.groupby([\"decade\", \"key\"], as_index=False)[\"year\"]\n",
    "    .count()\n",
    "    .rename(columns={\"year\": \"count\"})\n",
    ")\n",
    "mode_count = (\n",
    "    df.groupby([\"decade\", \"mode\"], as_index=False)[\"year\"]\n",
    "    .count()\n",
    "    .rename(columns={\"year\": \"count\"})\n",
    ")\n",
    "\n",
    "fig = px.histogram(\n",
    "    data_frame=explicit_count,\n",
    "    x=\"decade\",\n",
    "    y=\"count\",\n",
    "    color=\"explicit\",\n",
    "    histfunc=\"sum\",\n",
    "    color_discrete_sequence=px.colors.qualitative.Pastel,\n",
    "    text_auto=True,\n",
    ")\n",
    "fig.update_layout(\n",
    "    title={\"text\": \"Explicit Count per Decade\", \"font\": {\"size\": 24}},\n",
    "    bargap=0.2,\n",
    "    bargroupgap=0.1,\n",
    "    barmode=\"group\",\n",
    "    xaxis_title=\"Decade\",\n",
    "    yaxis_title=\"Count\",\n",
    ")\n",
    "fig.show()\n",
    "\n",
    "fig = px.histogram(\n",
    "    data_frame=mode_count,\n",
    "    x=\"decade\",\n",
    "    y=\"count\",\n",
    "    color=\"mode\",\n",
    "    histfunc=\"sum\",\n",
    "    color_discrete_sequence=px.colors.qualitative.Pastel,\n",
    "    text_auto=True,\n",
    ")\n",
    "fig.update_layout(\n",
    "    title={\"text\": \"Mode Count per Decade\", \"font\": {\"size\": 24}},\n",
    "    bargap=0.2,\n",
    "    bargroupgap=0.1,\n",
    "    barmode=\"group\",\n",
    "    xaxis_title=\"Decade\",\n",
    "    yaxis_title=\"Count\",\n",
    ")\n",
    "fig.show()\n",
    "\n",
    "fig = px.histogram(\n",
    "    data_frame=key_count,\n",
    "    x=\"decade\",\n",
    "    y=\"count\",\n",
    "    color=\"key\",\n",
    "    histfunc=\"sum\",\n",
    "    color_discrete_sequence=px.colors.qualitative.Pastel,\n",
    "    text_auto=True,\n",
    ")\n",
    "fig.update_layout(\n",
    "    title={\"text\": \"Key Count per Decade\", \"font\": {\"size\": 24}},\n",
    "    bargap=0.2,\n",
    "    bargroupgap=0.1,\n",
    "    barmode=\"stack\",\n",
    "    xaxis_title=\"Decade\",\n",
    "    yaxis_title=\"Count\",\n",
    ")\n",
    "fig.show()\n",
    "\n",
    "del (mode_count, key_count, explicit_count)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "cols = [\n",
    "    \"valence\",\n",
    "    \"acousticness\",\n",
    "    \"danceability\",\n",
    "    \"duration_min\",\n",
    "    \"energy\",\n",
    "    \"instrumentalness\",\n",
    "    \"liveness\",\n",
    "    \"loudness\",\n",
    "    \"year\",\n",
    "    \"speechiness\",\n",
    "    \"tempo\",\n",
    "]\n",
    "\n",
    "for col in cols:\n",
    "\n",
    "    fig = px.scatter(\n",
    "        data_frame=df,\n",
    "        x=col,\n",
    "        y=\"popularity\",\n",
    "        trendline=\"ols\",\n",
    "        trendline_color_override=\"#A6E3A1\",\n",
    "    )\n",
    "    fig.update_traces(marker={\"opacity\": 0.3, \"size\": 3, \"color\": \"#B4BEFE\"})\n",
    "    fig.update_layout(title={\"text\": f\"{col} vs popularity\", \"font\": {\"size\": 24}})\n",
    "    fig.show()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Header 1\n",
    "\n",
    "## Header 2\n",
    "\n",
    "### Header 3.1"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "cols = [\n",
    "    \"valence\",\n",
    "    \"acousticness\",\n",
    "    \"danceability\",\n",
    "    \"duration_min\",\n",
    "    \"energy\",\n",
    "    \"instrumentalness\",\n",
    "    \"liveness\",\n",
    "    \"loudness\",\n",
    "    \"year\",\n",
    "    \"speechiness\",\n",
    "    \"tempo\",\n",
    "]\n",
    "\n",
    "plt.figure(figsize=(15, 10))\n",
    "\n",
    "for i, col in enumerate(cols):\n",
    "    ax = plt.subplot(3, 4, i + 1)\n",
    "    sns.regplot(\n",
    "        data=df,\n",
    "        x=\"popularity\",\n",
    "        y=col,\n",
    "        ax=ax,\n",
    "        scatter_kws={\"alpha\": 0.5},\n",
    "        line_kws={\"color\": \"#F38BA8\"},\n",
    "    )\n",
    "\n",
    "plt.tight_layout()\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "cols = [\n",
    "    \"valence\",\n",
    "    \"acousticness\",\n",
    "    \"danceability\",\n",
    "    \"duration_min\",\n",
    "    \"energy\",\n",
    "    \"instrumentalness\",\n",
    "    \"liveness\",\n",
    "    \"loudness\",\n",
    "    \"year\",\n",
    "    \"speechiness\",\n",
    "    \"tempo\",\n",
    "    \"popularity\",\n",
    "]\n",
    "\n",
    "plt.figure(figsize=(10, 7))\n",
    "mask = np.triu(np.ones_like(df[cols].corr()))\n",
    "sns.heatmap(\n",
    "    df[cols].corr(),\n",
    "    annot=True,\n",
    "    fmt=\".2f\",\n",
    "    cmap=\"Blues\",\n",
    "    mask=mask,\n",
    ")\n",
    "plt.grid(visible=False)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "df[\"first_artist\"] = (\n",
    "    df[\"artists\"]\n",
    "    .apply(lambda x: str(x).split(\"x\")[0])\n",
    "    .apply(lambda x: str(x).replace(\"[\", \"\"))\n",
    "    .apply(lambda x: str(x).replace(\"]\", \"\"))\n",
    "    .apply(lambda x: str(x).replace(\"'\", \"\"))\n",
    ")\n",
    "df = df.drop(\"artists\", axis=1)\n",
    "df[\"first_artist\"] = df[\"first_artist\"].apply(lambda x: str(x).split(\",\")[0])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "popularity_check = (\n",
    "    df.groupby([\"first_artist\"], as_index=False)[\"popularity\"]\n",
    "    .agg({\"mean\", \"count\", \"median\"})\n",
    "    .sort_values(by=\"mean\", ascending=False)\n",
    "    .reset_index(drop=True)\n",
    ")\n",
    "\n",
    "popularity_check = popularity_check.drop(16091, axis=0)\n",
    "popularity_check = popularity_check.drop(16086, axis=0)\n",
    "popularity_check = popularity_check.drop(16429, axis=0)\n",
    "\n",
    "to_drop = popularity_check[popularity_check[\"count\"] <= 45].index\n",
    "popularity_check = popularity_check.drop(to_drop)\n",
    "popularity_check = popularity_check.sort_values(by=\"mean\", ascending=False).head(50)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Header 1\n",
    "\n",
    "## Header 2\n",
    "\n",
    "### Header 3.1"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "top_50_artists = pd.DataFrame()\n",
    "\n",
    "for i in popularity_check[\"first_artist\"].unique():\n",
    "    artist = df.query(\"first_artist == @i\")\n",
    "    top_50_artists = pd.concat([top_50_artists, artist], axis=0)\n",
    "\n",
    "top_50_artists = top_50_artists.reset_index(drop=True)\n",
    "top_50_artists.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "plt.figure(figsize=(12, 8))\n",
    "(\n",
    "    top_50_artists[\"first_artist\"]\n",
    "    .value_counts()\n",
    "    .sort_values(ascending=True)\n",
    "    .plot(kind=\"barh\")\n",
    ")\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "top_50_artists[\"decade\"].value_counts().sort_values(ascending=True).plot(kind=\"barh\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "cols = [\n",
    "    \"valence\",\n",
    "    \"acousticness\",\n",
    "    \"danceability\",\n",
    "    \"duration_min\",\n",
    "    \"energy\",\n",
    "    \"instrumentalness\",\n",
    "    \"liveness\",\n",
    "    \"loudness\",\n",
    "    \"year\",\n",
    "    \"speechiness\",\n",
    "    \"tempo\",\n",
    "]\n",
    "\n",
    "plt.figure(figsize=(15, 10))\n",
    "\n",
    "for i, col in enumerate(cols):\n",
    "    ax = plt.subplot(3, 4, i + 1)\n",
    "    sns.kdeplot(data=top_50_artists, x=col, hue=\"first_artist\", legend=False)\n",
    "\n",
    "plt.tight_layout()\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Header 1\n",
    "\n",
    "## Header 2\n",
    "\n",
    "### Header 3.1"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "import pandas as pd\n",
    "import numpy as np\n",
    "import seaborn as sns\n",
    "import matplotlib.pyplot as plt\n",
    "import matplotlib as mpl\n",
    "import mplcatppuccin\n",
    "import plotly.express as px\n",
    "import plotly.graph_objects as go\n",
    "from plotly.subplots import make_subplots\n",
    "import plotly.figure_factory as ff\n",
    "import warnings\n",
    "import plotly.io as pio\n",
    "\n",
    "warnings.filterwarnings('ignore')\n",
    "\n",
    "pio.renderers.default = 'notebook_connected'\n",
    "pio.templates.default = 'plotly_dark'\n",
    "\n",
    "\n",
    "%matplotlib inline\n",
    "%config InlineBackend.figure_format = 'retina'\n",
    "pd.set_option('display.max_columns', None)\n",
    "pd.set_option('display.precision', 2)\n",
    "pd.set_option('display.colheader_justify', 'left')\n",
    "\n",
    "mpl.rc(\n",
    "    'figure',\n",
    "    autolayout=True,\n",
    "    titlesize=18\n",
    ")\n",
    "\n",
    "mpl.style.use(['ggplot', 'mocha'])\n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Header 3.2\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "df = pd.read_csv(\n",
    "    \"data.csv\",\n",
    "    parse_dates=[\"release_date\"],\n",
    ")\n",
    "df.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "map_key = {\n",
    "    0: \"C\",\n",
    "    1: \"C#\",\n",
    "    2: \"D\",\n",
    "    3: \"D#\",\n",
    "    4: \"E\",\n",
    "    5: \"F\",\n",
    "    6: \"F#\",\n",
    "    7: \"G\",\n",
    "    8: \"G#\",\n",
    "    9: \"A\",\n",
    "    10: \"A#\",\n",
    "    11: \"B\",\n",
    "}\n",
    "\n",
    "map_mode = {1: \"Major\", 0: \"Minor\"}\n",
    "\n",
    "df[\"mode\"] = df[\"mode\"].map(map_mode)\n",
    "df[\"key\"] = df[\"key\"].map(map_key)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "check_dups = df[[\"artists\", \"name\"]]\n",
    "dups = check_dups[check_dups.duplicated()].index"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "print(\"Before dropping duplicated:\", df.shape)\n",
    "df = df.drop(dups)\n",
    "print(\"After dropping duplicated:\", df.shape)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Header 1.3\n",
    "\n",
    "## Header 2.3\n",
    "\n",
    "### Header 3.5"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "df[\"duration_ms\"] = df[\"duration_ms\"] / 60_000\n",
    "df = df.rename(columns={\"duration_ms\": \"duration_min\"})\n",
    "df.head()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Header 1.4\n",
    "\n",
    "## Header 2.4\n",
    "\n",
    "### Header 3.5"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "df = df.drop([\"release_date\", \"id\"], axis=1)\n",
    "df.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "def fun_subplots_plotly(df, col):\n",
    "\n",
    "    mean_val = df[col].mean()\n",
    "    median_val = df[col].median()\n",
    "    fig = make_subplots(rows=1, cols=2, column_widths=[0.75, 0.25])\n",
    "\n",
    "    fig.add_trace(\n",
    "        go.Histogram(\n",
    "            x=df[col], name=f\"Histogram {col}\", marker={\"color\": \"#EBA0AC\"}, nbinsx=50\n",
    "        ),\n",
    "        row=1,\n",
    "        col=1,\n",
    "    )\n",
    "\n",
    "    fig.add_shape(\n",
    "        type=\"line\",\n",
    "        xref=\"paper\",\n",
    "        yref=\"y\",\n",
    "        x0=-1,\n",
    "        x1=1,\n",
    "        y0=mean_val,\n",
    "        y1=mean_val,\n",
    "        row=1,\n",
    "        col=2,\n",
    "        line={\"color\": \"#A6E3A1\", \"width\": 3, \"dash\": \"dot\"},\n",
    "    )\n",
    "\n",
    "    fig.add_shape(\n",
    "        type=\"line\",\n",
    "        xref=\"paper\",\n",
    "        yref=\"y\",\n",
    "        x0=-1,\n",
    "        x1=1,\n",
    "        y0=median_val,\n",
    "        y1=median_val,\n",
    "        row=1,\n",
    "        col=2,\n",
    "        line={\"color\": \"#CBA6F7\", \"width\": 3, \"dash\": \"dot\"},\n",
    "    )\n",
    "\n",
    "    fig.add_annotation(\n",
    "        xref=\"paper\",\n",
    "        x=-0.7,\n",
    "        y=mean_val,\n",
    "        showarrow=True,\n",
    "        arrowhead=2,\n",
    "        text=f\"Mean = {mean_val:.2f}\",\n",
    "        row=1,\n",
    "        col=2,\n",
    "    )\n",
    "\n",
    "    fig.add_annotation(\n",
    "        xref=\"paper\",\n",
    "        x=0.7,\n",
    "        y=median_val,\n",
    "        showarrow=True,\n",
    "        arrowhead=2,\n",
    "        text=f\"Median = {median_val:.2f}\",\n",
    "        row=1,\n",
    "        col=2,\n",
    "    )\n",
    "\n",
    "    fig.add_trace(\n",
    "        go.Box(y=df[col], name=f\"Boxplot {col}\", marker={\"color\": \"#F9E2AF\"}),\n",
    "        row=1,\n",
    "        col=2,\n",
    "    )\n",
    "\n",
    "    fig.update_layout(\n",
    "        title={\"text\": f\"Distribution Plot {col}\", \"font\": {\"size\": 24}},\n",
    "        legend={\n",
    "            \"orientation\": \"h\",\n",
    "            \"yanchor\": \"bottom\",\n",
    "            \"y\": 1.02,\n",
    "            \"xanchor\": \"right\",\n",
    "            \"x\": 1,\n",
    "        },\n",
    "    )\n",
    "    fig.update_yaxes(title_text=\"Count\", row=1, col=1)\n",
    "    fig.update_yaxes(title_text=f\"{col}\", row=1, col=2)\n",
    "    fig.update_xaxes(title_text=f\"{col}\", row=1, col=1)\n",
    "    fig.update_xaxes(title_text=\"\", row=1, col=2)\n",
    "    fig.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "music_vals = [\n",
    "    \"valence\",\n",
    "    \"acousticness\",\n",
    "    \"danceability\",\n",
    "    \"duration_min\",\n",
    "    \"energy\",\n",
    "    \"instrumentalness\",\n",
    "    \"liveness\",\n",
    "    \"loudness\",\n",
    "    \"popularity\",\n",
    "    \"speechiness\",\n",
    "    \"tempo\",\n",
    "]\n",
    "\n",
    "for col in music_vals:\n",
    "    fun_subplots_plotly(df, col)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Header 1.2\n",
    "\n",
    "## Header 2.2\n",
    "\n",
    "### Header 3.4"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "bins = pd.IntervalIndex.from_breaks(\n",
    "    [1920, 1930, 1940, 1950, 1960, 1970, 1980, 1990, 2000, 2010, 2020]\n",
    ")\n",
    "\n",
    "df[\"decade\"] = pd.cut(df[\"year\"], bins).astype(\"str\")\n",
    "\n",
    "map_decade = {\n",
    "    \"(1920, 1930]\": \"1920s\",\n",
    "    \"(1930, 1940]\": \"1930s\",\n",
    "    \"(1940, 1950]\": \"1940s\",\n",
    "    \"(1950, 1960]\": \"1950s\",\n",
    "    \"(1960, 1970]\": \"1960s\",\n",
    "    \"(1970, 1980]\": \"1970s\",\n",
    "    \"(1980, 1990]\": \"1980s\",\n",
    "    \"(1990, 2000]\": \"1990s\",\n",
    "    \"(2000, 2010]\": \"2000s\",\n",
    "    \"(2010, 2020]\": \"2010s\",\n",
    "}\n",
    "\n",
    "df[\"decade\"] = df[\"decade\"].map(map_decade)\n",
    "\n",
    "df.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "decade_counts = (\n",
    "    df[\"decade\"].value_counts().reset_index().sort_values(by=\"decade\", ascending=True)\n",
    ")\n",
    "\n",
    "fig = px.bar(\n",
    "    data_frame=decade_counts,\n",
    "    y=\"decade\",\n",
    "    x=\"count\",\n",
    "    color=\"count\",\n",
    "    color_continuous_scale=px.colors.sequential.Sunset,\n",
    "    text_auto=True,\n",
    ")\n",
    "\n",
    "fig.update_layout(\n",
    "    title={\"text\": \"Count of songs per decade\", \"font\": {\"size\": 24}},\n",
    "    coloraxis_colorbar={\n",
    "        \"title\": \"Count\",\n",
    "        \"thicknessmode\": \"pixels\",\n",
    "        \"thickness\": 20,\n",
    "        \"lenmode\": \"pixels\",\n",
    "        \"len\": 500,\n",
    "        \"yanchor\": \"top\",\n",
    "        \"xanchor\": \"right\",\n",
    "        \"y\": 1.15,\n",
    "        \"x\": 0.95,\n",
    "        \"orientation\": \"h\",\n",
    "    },\n",
    "    margin={\"r\": 10},\n",
    ")\n",
    "\n",
    "fig.update_xaxes(title=\"Count\")\n",
    "fig.update_yaxes(title=\"Decades\")\n",
    "fig.show()\n",
    "\n",
    "del decade_counts"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "df = df.query(\"duration_min <= 5\")"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Header 1.2\n",
    "\n",
    "## Header 2.2\n",
    "\n",
    "### Header 3.4"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "decade_counts = (\n",
    "    df[\"decade\"].value_counts().reset_index().sort_values(by=\"decade\", ascending=True)\n",
    ")\n",
    "\n",
    "fig = px.bar(\n",
    "    data_frame=decade_counts,\n",
    "    y=\"decade\",\n",
    "    x=\"count\",\n",
    "    color=\"count\",\n",
    "    color_continuous_scale=px.colors.sequential.Sunset,\n",
    "    text_auto=True,\n",
    ")\n",
    "\n",
    "fig.update_layout(\n",
    "    title={\"text\": \"Count of songs per decade (< 5min)\", \"font\": {\"size\": 24}},\n",
    "    coloraxis_colorbar={\n",
    "        \"title\": \"Count\",\n",
    "        \"thicknessmode\": \"pixels\",\n",
    "        \"thickness\": 20,\n",
    "        \"lenmode\": \"pixels\",\n",
    "        \"len\": 500,\n",
    "        \"yanchor\": \"top\",\n",
    "        \"xanchor\": \"right\",\n",
    "        \"y\": 1.15,\n",
    "        \"x\": 0.95,\n",
    "        \"orientation\": \"h\",\n",
    "    },\n",
    "    margin={\"r\": 10},\n",
    ")\n",
    "\n",
    "fig.update_xaxes(title=\"Count\")\n",
    "fig.update_yaxes(title=\"Decades\")\n",
    "fig.show()\n",
    "\n",
    "del decade_counts"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "cols = [\n",
    "    \"valence\",\n",
    "    \"acousticness\",\n",
    "    \"danceability\",\n",
    "    \"duration_min\",\n",
    "    \"energy\",\n",
    "    \"instrumentalness\",\n",
    "    \"liveness\",\n",
    "    \"loudness\",\n",
    "    \"popularity\",\n",
    "    \"speechiness\",\n",
    "    \"tempo\",\n",
    "]\n",
    "for col in cols:\n",
    "    fig = px.histogram(\n",
    "        data_frame=df,\n",
    "        x=col,\n",
    "        color=\"decade\",\n",
    "        color_discrete_sequence=px.colors.qualitative.Light24,\n",
    "    )\n",
    "    fig.update_traces(opacity=0.7)\n",
    "    fig.update_layout(\n",
    "        bargap=0.1,\n",
    "        bargroupgap=0.05,\n",
    "        barmode=\"stack\",\n",
    "        title={\"text\": f\"Histogram of {col} per decade\", \"font\": {\"size\": 24}},\n",
    "        legend={\"title\": \"Decade\"},\n",
    "    )\n",
    "    fig.update_yaxes(title=\"Count\")\n",
    "    fig.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "decade_mean = df.groupby(\"decade\")[cols].mean()\n",
    "\n",
    "fig = make_subplots(\n",
    "    rows=4,\n",
    "    cols=3,\n",
    "    subplot_titles=(\n",
    "        decade_mean.columns[0],\n",
    "        decade_mean.columns[1],\n",
    "        decade_mean.columns[2],\n",
    "        decade_mean.columns[3],\n",
    "        decade_mean.columns[4],\n",
    "        decade_mean.columns[5],\n",
    "        decade_mean.columns[6],\n",
    "        decade_mean.columns[7],\n",
    "        decade_mean.columns[8],\n",
    "        decade_mean.columns[9],\n",
    "        decade_mean.columns[10],\n",
    "    ),\n",
    "    vertical_spacing=0.1,\n",
    ")\n",
    "\n",
    "fig.add_trace(\n",
    "    go.Bar(\n",
    "        y=decade_mean.index,\n",
    "        x=decade_mean.iloc[:, 0],\n",
    "        name=decade_mean.columns[0],\n",
    "        orientation=\"h\",\n",
    "    ),\n",
    "    row=1,\n",
    "    col=1,\n",
    ")\n",
    "\n",
    "fig.add_trace(\n",
    "    go.Bar(\n",
    "        y=decade_mean.index,\n",
    "        x=decade_mean.iloc[:, 1],\n",
    "        name=decade_mean.columns[1],\n",
    "        orientation=\"h\",\n",
    "    ),\n",
    "    row=1,\n",
    "    col=2,\n",
    ")\n",
    "\n",
    "fig.add_trace(\n",
    "    go.Bar(\n",
    "        y=decade_mean.index,\n",
    "        x=decade_mean.iloc[:, 2],\n",
    "        name=decade_mean.columns[2],\n",
    "        orientation=\"h\",\n",
    "    ),\n",
    "    row=1,\n",
    "    col=3,\n",
    ")\n",
    "\n",
    "fig.add_trace(\n",
    "    go.Bar(\n",
    "        y=decade_mean.index,\n",
    "        x=decade_mean.iloc[:, 3],\n",
    "        name=decade_mean.columns[3],\n",
    "        orientation=\"h\",\n",
    "    ),\n",
    "    row=2,\n",
    "    col=1,\n",
    ")\n",
    "\n",
    "fig.add_trace(\n",
    "    go.Bar(\n",
    "        y=decade_mean.index,\n",
    "        x=decade_mean.iloc[:, 4],\n",
    "        name=decade_mean.columns[4],\n",
    "        orientation=\"h\",\n",
    "    ),\n",
    "    row=2,\n",
    "    col=2,\n",
    ")\n",
    "\n",
    "fig.add_trace(\n",
    "    go.Bar(\n",
    "        y=decade_mean.index,\n",
    "        x=decade_mean.iloc[:, 5],\n",
    "        name=decade_mean.columns[5],\n",
    "        orientation=\"h\",\n",
    "    ),\n",
    "    row=2,\n",
    "    col=3,\n",
    ")\n",
    "\n",
    "fig.add_trace(\n",
    "    go.Bar(\n",
    "        y=decade_mean.index,\n",
    "        x=decade_mean.iloc[:, 6],\n",
    "        name=decade_mean.columns[6],\n",
    "        orientation=\"h\",\n",
    "    ),\n",
    "    row=3,\n",
    "    col=1,\n",
    ")\n",
    "\n",
    "fig.add_trace(\n",
    "    go.Bar(\n",
    "        y=decade_mean.index,\n",
    "        x=decade_mean.iloc[:, 7],\n",
    "        name=decade_mean.columns[7],\n",
    "        orientation=\"h\",\n",
    "    ),\n",
    "    row=3,\n",
    "    col=2,\n",
    ")\n",
    "\n",
    "fig.add_trace(\n",
    "    go.Bar(\n",
    "        y=decade_mean.index,\n",
    "        x=decade_mean.iloc[:, 8],\n",
    "        name=decade_mean.columns[8],\n",
    "        orientation=\"h\",\n",
    "    ),\n",
    "    row=3,\n",
    "    col=3,\n",
    ")\n",
    "\n",
    "fig.add_trace(\n",
    "    go.Bar(\n",
    "        y=decade_mean.index,\n",
    "        x=decade_mean.iloc[:, 9],\n",
    "        name=decade_mean.columns[9],\n",
    "        orientation=\"h\",\n",
    "    ),\n",
    "    row=4,\n",
    "    col=1,\n",
    ")\n",
    "\n",
    "fig.add_trace(\n",
    "    go.Bar(\n",
    "        y=decade_mean.index,\n",
    "        x=decade_mean.iloc[:, 10],\n",
    "        name=decade_mean.columns[10],\n",
    "        orientation=\"h\",\n",
    "    ),\n",
    "    row=4,\n",
    "    col=2,\n",
    ")\n",
    "\n",
    "fig.update_layout(\n",
    "    title={\"text\": \"Mean Musical Values per Decade\", \"font\": {\"size\": 22}},\n",
    "    legend={\n",
    "        \"orientation\": \"v\",\n",
    "        \"yanchor\": \"top\",\n",
    "        \"y\": 0.2,\n",
    "        \"xanchor\": \"right\",\n",
    "        \"x\": 0.9,\n",
    "    },\n",
    "    margin={\"b\": 10, \"r\": 10},\n",
    "    height=980,\n",
    ")\n",
    "\n",
    "fig.show()\n",
    "\n",
    "del decade_mean"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "decade_median = df.groupby(\"decade\")[cols].median()\n",
    "\n",
    "fig = make_subplots(\n",
    "    rows=4,\n",
    "    cols=3,\n",
    "    subplot_titles=(\n",
    "        decade_median.columns[0],\n",
    "        decade_median.columns[1],\n",
    "        decade_median.columns[2],\n",
    "        decade_median.columns[3],\n",
    "        decade_median.columns[4],\n",
    "        decade_median.columns[5],\n",
    "        decade_median.columns[6],\n",
    "        decade_median.columns[7],\n",
    "        decade_median.columns[8],\n",
    "        decade_median.columns[9],\n",
    "        decade_median.columns[10],\n",
    "    ),\n",
    "    vertical_spacing=0.1,\n",
    ")\n",
    "\n",
    "fig.add_trace(\n",
    "    go.Bar(\n",
    "        y=decade_median.index,\n",
    "        x=decade_median.iloc[:, 0],\n",
    "        name=decade_median.columns[0],\n",
    "        orientation=\"h\",\n",
    "    ),\n",
    "    row=1,\n",
    "    col=1,\n",
    ")\n",
    "\n",
    "fig.add_trace(\n",
    "    go.Bar(\n",
    "        y=decade_median.index,\n",
    "        x=decade_median.iloc[:, 1],\n",
    "        name=decade_median.columns[1],\n",
    "        orientation=\"h\",\n",
    "    ),\n",
    "    row=1,\n",
    "    col=2,\n",
    ")\n",
    "\n",
    "fig.add_trace(\n",
    "    go.Bar(\n",
    "        y=decade_median.index,\n",
    "        x=decade_median.iloc[:, 2],\n",
    "        name=decade_median.columns[2],\n",
    "        orientation=\"h\",\n",
    "    ),\n",
    "    row=1,\n",
    "    col=3,\n",
    ")\n",
    "\n",
    "fig.add_trace(\n",
    "    go.Bar(\n",
    "        y=decade_median.index,\n",
    "        x=decade_median.iloc[:, 3],\n",
    "        name=decade_median.columns[3],\n",
    "        orientation=\"h\",\n",
    "    ),\n",
    "    row=2,\n",
    "    col=1,\n",
    ")\n",
    "\n",
    "fig.add_trace(\n",
    "    go.Bar(\n",
    "        y=decade_median.index,\n",
    "        x=decade_median.iloc[:, 4],\n",
    "        name=decade_median.columns[4],\n",
    "        orientation=\"h\",\n",
    "    ),\n",
    "    row=2,\n",
    "    col=2,\n",
    ")\n",
    "\n",
    "fig.add_trace(\n",
    "    go.Bar(\n",
    "        y=decade_median.index,\n",
    "        x=decade_median.iloc[:, 5],\n",
    "        name=decade_median.columns[5],\n",
    "        orientation=\"h\",\n",
    "    ),\n",
    "    row=2,\n",
    "    col=3,\n",
    ")\n",
    "\n",
    "fig.add_trace(\n",
    "    go.Bar(\n",
    "        y=decade_median.index,\n",
    "        x=decade_median.iloc[:, 6],\n",
    "        name=decade_median.columns[6],\n",
    "        orientation=\"h\",\n",
    "    ),\n",
    "    row=3,\n",
    "    col=1,\n",
    ")\n",
    "\n",
    "fig.add_trace(\n",
    "    go.Bar(\n",
    "        y=decade_median.index,\n",
    "        x=decade_median.iloc[:, 7],\n",
    "        name=decade_median.columns[7],\n",
    "        orientation=\"h\",\n",
    "    ),\n",
    "    row=3,\n",
    "    col=2,\n",
    ")\n",
    "\n",
    "fig.add_trace(\n",
    "    go.Bar(\n",
    "        y=decade_median.index,\n",
    "        x=decade_median.iloc[:, 8],\n",
    "        name=decade_median.columns[8],\n",
    "        orientation=\"h\",\n",
    "    ),\n",
    "    row=3,\n",
    "    col=3,\n",
    ")\n",
    "\n",
    "fig.add_trace(\n",
    "    go.Bar(\n",
    "        y=decade_median.index,\n",
    "        x=decade_median.iloc[:, 9],\n",
    "        name=decade_median.columns[9],\n",
    "        orientation=\"h\",\n",
    "    ),\n",
    "    row=4,\n",
    "    col=1,\n",
    ")\n",
    "\n",
    "fig.add_trace(\n",
    "    go.Bar(\n",
    "        y=decade_median.index,\n",
    "        x=decade_median.iloc[:, 10],\n",
    "        name=decade_median.columns[10],\n",
    "        orientation=\"h\",\n",
    "    ),\n",
    "    row=4,\n",
    "    col=2,\n",
    ")\n",
    "\n",
    "fig.update_layout(\n",
    "    title={\"text\": \"Median Musical Values per Decade\", \"font\": {\"size\": 22}},\n",
    "    legend={\n",
    "        \"orientation\": \"v\",\n",
    "        \"yanchor\": \"top\",\n",
    "        \"y\": 0.2,\n",
    "        \"xanchor\": \"right\",\n",
    "        \"x\": 0.9,\n",
    "    },\n",
    "    margin={\"b\": 10, \"r\": 10},\n",
    "    height=980,\n",
    ")\n",
    "\n",
    "fig.show()\n",
    "\n",
    "del decade_median"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "explicit_count = (\n",
    "    df.groupby([\"decade\", \"explicit\"], as_index=False)[\"year\"]\n",
    "    .count()\n",
    "    .rename(columns={\"year\": \"count\"})\n",
    ")\n",
    "key_count = (\n",
    "    df.groupby([\"decade\", \"key\"], as_index=False)[\"year\"]\n",
    "    .count()\n",
    "    .rename(columns={\"year\": \"count\"})\n",
    ")\n",
    "mode_count = (\n",
    "    df.groupby([\"decade\", \"mode\"], as_index=False)[\"year\"]\n",
    "    .count()\n",
    "    .rename(columns={\"year\": \"count\"})\n",
    ")\n",
    "\n",
    "fig = px.histogram(\n",
    "    data_frame=explicit_count,\n",
    "    x=\"decade\",\n",
    "    y=\"count\",\n",
    "    color=\"explicit\",\n",
    "    histfunc=\"sum\",\n",
    "    color_discrete_sequence=px.colors.qualitative.Pastel,\n",
    "    text_auto=True,\n",
    ")\n",
    "fig.update_layout(\n",
    "    title={\"text\": \"Explicit Count per Decade\", \"font\": {\"size\": 24}},\n",
    "    bargap=0.2,\n",
    "    bargroupgap=0.1,\n",
    "    barmode=\"group\",\n",
    "    xaxis_title=\"Decade\",\n",
    "    yaxis_title=\"Count\",\n",
    ")\n",
    "fig.show()\n",
    "\n",
    "fig = px.histogram(\n",
    "    data_frame=mode_count,\n",
    "    x=\"decade\",\n",
    "    y=\"count\",\n",
    "    color=\"mode\",\n",
    "    histfunc=\"sum\",\n",
    "    color_discrete_sequence=px.colors.qualitative.Pastel,\n",
    "    text_auto=True,\n",
    ")\n",
    "fig.update_layout(\n",
    "    title={\"text\": \"Mode Count per Decade\", \"font\": {\"size\": 24}},\n",
    "    bargap=0.2,\n",
    "    bargroupgap=0.1,\n",
    "    barmode=\"group\",\n",
    "    xaxis_title=\"Decade\",\n",
    "    yaxis_title=\"Count\",\n",
    ")\n",
    "fig.show()\n",
    "\n",
    "fig = px.histogram(\n",
    "    data_frame=key_count,\n",
    "    x=\"decade\",\n",
    "    y=\"count\",\n",
    "    color=\"key\",\n",
    "    histfunc=\"sum\",\n",
    "    color_discrete_sequence=px.colors.qualitative.Pastel,\n",
    "    text_auto=True,\n",
    ")\n",
    "fig.update_layout(\n",
    "    title={\"text\": \"Key Count per Decade\", \"font\": {\"size\": 24}},\n",
    "    bargap=0.2,\n",
    "    bargroupgap=0.1,\n",
    "    barmode=\"stack\",\n",
    "    xaxis_title=\"Decade\",\n",
    "    yaxis_title=\"Count\",\n",
    ")\n",
    "fig.show()\n",
    "\n",
    "del (mode_count, key_count, explicit_count)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "cols = [\n",
    "    \"valence\",\n",
    "    \"acousticness\",\n",
    "    \"danceability\",\n",
    "    \"duration_min\",\n",
    "    \"energy\",\n",
    "    \"instrumentalness\",\n",
    "    \"liveness\",\n",
    "    \"loudness\",\n",
    "    \"year\",\n",
    "    \"speechiness\",\n",
    "    \"tempo\",\n",
    "]\n",
    "\n",
    "for col in cols:\n",
    "\n",
    "    fig = px.scatter(\n",
    "        data_frame=df,\n",
    "        x=col,\n",
    "        y=\"popularity\",\n",
    "        trendline=\"ols\",\n",
    "        trendline_color_override=\"#A6E3A1\",\n",
    "    )\n",
    "    fig.update_traces(marker={\"opacity\": 0.3, \"size\": 3, \"color\": \"#B4BEFE\"})\n",
    "    fig.update_layout(title={\"text\": f\"{col} vs popularity\", \"font\": {\"size\": 24}})\n",
    "    fig.show()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Header 1\n",
    "\n",
    "## Header 2\n",
    "\n",
    "### Header 3.1"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "cols = [\n",
    "    \"valence\",\n",
    "    \"acousticness\",\n",
    "    \"danceability\",\n",
    "    \"duration_min\",\n",
    "    \"energy\",\n",
    "    \"instrumentalness\",\n",
    "    \"liveness\",\n",
    "    \"loudness\",\n",
    "    \"year\",\n",
    "    \"speechiness\",\n",
    "    \"tempo\",\n",
    "]\n",
    "\n",
    "plt.figure(figsize=(15, 10))\n",
    "\n",
    "for i, col in enumerate(cols):\n",
    "    ax = plt.subplot(3, 4, i + 1)\n",
    "    sns.regplot(\n",
    "        data=df,\n",
    "        x=\"popularity\",\n",
    "        y=col,\n",
    "        ax=ax,\n",
    "        scatter_kws={\"alpha\": 0.5},\n",
    "        line_kws={\"color\": \"#F38BA8\"},\n",
    "    )\n",
    "\n",
    "plt.tight_layout()\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "cols = [\n",
    "    \"valence\",\n",
    "    \"acousticness\",\n",
    "    \"danceability\",\n",
    "    \"duration_min\",\n",
    "    \"energy\",\n",
    "    \"instrumentalness\",\n",
    "    \"liveness\",\n",
    "    \"loudness\",\n",
    "    \"year\",\n",
    "    \"speechiness\",\n",
    "    \"tempo\",\n",
    "    \"popularity\",\n",
    "]\n",
    "\n",
    "plt.figure(figsize=(10, 7))\n",
    "mask = np.triu(np.ones_like(df[cols].corr()))\n",
    "sns.heatmap(\n",
    "    df[cols].corr(),\n",
    "    annot=True,\n",
    "    fmt=\".2f\",\n",
    "    cmap=\"Blues\",\n",
    "    mask=mask,\n",
    ")\n",
    "plt.grid(visible=False)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "df[\"first_artist\"] = (\n",
    "    df[\"artists\"]\n",
    "    .apply(lambda x: str(x).split(\"x\")[0])\n",
    "    .apply(lambda x: str(x).replace(\"[\", \"\"))\n",
    "    .apply(lambda x: str(x).replace(\"]\", \"\"))\n",
    "    .apply(lambda x: str(x).replace(\"'\", \"\"))\n",
    ")\n",
    "df = df.drop(\"artists\", axis=1)\n",
    "df[\"first_artist\"] = df[\"first_artist\"].apply(lambda x: str(x).split(\",\")[0])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "popularity_check = (\n",
    "    df.groupby([\"first_artist\"], as_index=False)[\"popularity\"]\n",
    "    .agg({\"mean\", \"count\", \"median\"})\n",
    "    .sort_values(by=\"mean\", ascending=False)\n",
    "    .reset_index(drop=True)\n",
    ")\n",
    "\n",
    "popularity_check = popularity_check.drop(16091, axis=0)\n",
    "popularity_check = popularity_check.drop(16086, axis=0)\n",
    "popularity_check = popularity_check.drop(16429, axis=0)\n",
    "\n",
    "to_drop = popularity_check[popularity_check[\"count\"] <= 45].index\n",
    "popularity_check = popularity_check.drop(to_drop)\n",
    "popularity_check = popularity_check.sort_values(by=\"mean\", ascending=False).head(50)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Header 1\n",
    "\n",
    "## Header 2\n",
    "\n",
    "### Header 3.1"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "top_50_artists = pd.DataFrame()\n",
    "\n",
    "for i in popularity_check[\"first_artist\"].unique():\n",
    "    artist = df.query(\"first_artist == @i\")\n",
    "    top_50_artists = pd.concat([top_50_artists, artist], axis=0)\n",
    "\n",
    "top_50_artists = top_50_artists.reset_index(drop=True)\n",
    "top_50_artists.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "plt.figure(figsize=(12, 8))\n",
    "(\n",
    "    top_50_artists[\"first_artist\"]\n",
    "    .value_counts()\n",
    "    .sort_values(ascending=True)\n",
    "    .plot(kind=\"barh\")\n",
    ")\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "top_50_artists[\"decade\"].value_counts().sort_values(ascending=True).plot(kind=\"barh\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "cols = [\n",
    "    \"valence\",\n",
    "    \"acousticness\",\n",
    "    \"danceability\",\n",
    "    \"duration_min\",\n",
    "    \"energy\",\n",
    "    \"instrumentalness\",\n",
    "    \"liveness\",\n",
    "    \"loudness\",\n",
    "    \"year\",\n",
    "    \"speechiness\",\n",
    "    \"tempo\",\n",
    "]\n",
    "\n",
    "plt.figure(figsize=(15, 10))\n",
    "\n",
    "for i, col in enumerate(cols):\n",
    "    ax = plt.subplot(3, 4, i + 1)\n",
    "    sns.kdeplot(data=top_50_artists, x=col, hue=\"first_artist\", legend=False)\n",
    "\n",
    "plt.tight_layout()\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Header 1\n",
    "\n",
    "## Header 2\n",
    "\n",
    "### Header 3.1"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "bins = pd.IntervalIndex.from_breaks(\n",
    "    [1920, 1930, 1940, 1950, 1960, 1970, 1980, 1990, 2000, 2010, 2020]\n",
    ")\n",
    "\n",
    "df[\"decade\"] = pd.cut(df[\"year\"], bins).astype(\"str\")\n",
    "\n",
    "map_decade = {\n",
    "    \"(1920, 1930]\": \"1920s\",\n",
    "    \"(1930, 1940]\": \"1930s\",\n",
    "    \"(1940, 1950]\": \"1940s\",\n",
    "    \"(1950, 1960]\": \"1950s\",\n",
    "    \"(1960, 1970]\": \"1960s\",\n",
    "    \"(1970, 1980]\": \"1970s\",\n",
    "    \"(1980, 1990]\": \"1980s\",\n",
    "    \"(1990, 2000]\": \"1990s\",\n",
    "    \"(2000, 2010]\": \"2000s\",\n",
    "    \"(2010, 2020]\": \"2010s\",\n",
    "}\n",
    "\n",
    "df[\"decade\"] = df[\"decade\"].map(map_decade)\n",
    "\n",
    "df.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "decade_counts = (\n",
    "    df[\"decade\"].value_counts().reset_index().sort_values(by=\"decade\", ascending=True)\n",
    ")\n",
    "\n",
    "fig = px.bar(\n",
    "    data_frame=decade_counts,\n",
    "    y=\"decade\",\n",
    "    x=\"count\",\n",
    "    color=\"count\",\n",
    "    color_continuous_scale=px.colors.sequential.Sunset,\n",
    "    text_auto=True,\n",
    ")\n",
    "\n",
    "fig.update_layout(\n",
    "    title={\"text\": \"Count of songs per decade\", \"font\": {\"size\": 24}},\n",
    "    coloraxis_colorbar={\n",
    "        \"title\": \"Count\",\n",
    "        \"thicknessmode\": \"pixels\",\n",
    "        \"thickness\": 20,\n",
    "        \"lenmode\": \"pixels\",\n",
    "        \"len\": 500,\n",
    "        \"yanchor\": \"top\",\n",
    "        \"xanchor\": \"right\",\n",
    "        \"y\": 1.15,\n",
    "        \"x\": 0.95,\n",
    "        \"orientation\": \"h\",\n",
    "    },\n",
    "    margin={\"r\": 10},\n",
    ")\n",
    "\n",
    "fig.update_xaxes(title=\"Count\")\n",
    "fig.update_yaxes(title=\"Decades\")\n",
    "fig.show()\n",
    "\n",
    "del decade_counts"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "df = df.query(\"duration_min <= 5\")"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Header 1.2\n",
    "\n",
    "## Header 2.2\n",
    "\n",
    "### Header 3.4"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "decade_counts = (\n",
    "    df[\"decade\"].value_counts().reset_index().sort_values(by=\"decade\", ascending=True)\n",
    ")\n",
    "\n",
    "fig = px.bar(\n",
    "    data_frame=decade_counts,\n",
    "    y=\"decade\",\n",
    "    x=\"count\",\n",
    "    color=\"count\",\n",
    "    color_continuous_scale=px.colors.sequential.Sunset,\n",
    "    text_auto=True,\n",
    ")\n",
    "\n",
    "fig.update_layout(\n",
    "    title={\"text\": \"Count of songs per decade (< 5min)\", \"font\": {\"size\": 24}},\n",
    "    coloraxis_colorbar={\n",
    "        \"title\": \"Count\",\n",
    "        \"thicknessmode\": \"pixels\",\n",
    "        \"thickness\": 20,\n",
    "        \"lenmode\": \"pixels\",\n",
    "        \"len\": 500,\n",
    "        \"yanchor\": \"top\",\n",
    "        \"xanchor\": \"right\",\n",
    "        \"y\": 1.15,\n",
    "        \"x\": 0.95,\n",
    "        \"orientation\": \"h\",\n",
    "    },\n",
    "    margin={\"r\": 10},\n",
    ")\n",
    "\n",
    "fig.update_xaxes(title=\"Count\")\n",
    "fig.update_yaxes(title=\"Decades\")\n",
    "fig.show()\n",
    "\n",
    "del decade_counts"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "cols = [\n",
    "    \"valence\",\n",
    "    \"acousticness\",\n",
    "    \"danceability\",\n",
    "    \"duration_min\",\n",
    "    \"energy\",\n",
    "    \"instrumentalness\",\n",
    "    \"liveness\",\n",
    "    \"loudness\",\n",
    "    \"popularity\",\n",
    "    \"speechiness\",\n",
    "    \"tempo\",\n",
    "]\n",
    "for col in cols:\n",
    "    fig = px.histogram(\n",
    "        data_frame=df,\n",
    "        x=col,\n",
    "        color=\"decade\",\n",
    "        color_discrete_sequence=px.colors.qualitative.Light24,\n",
    "    )\n",
    "    fig.update_traces(opacity=0.7)\n",
    "    fig.update_layout(\n",
    "        bargap=0.1,\n",
    "        bargroupgap=0.05,\n",
    "        barmode=\"stack\",\n",
    "        title={\"text\": f\"Histogram of {col} per decade\", \"font\": {\"size\": 24}},\n",
    "        legend={\"title\": \"Decade\"},\n",
    "    )\n",
    "    fig.update_yaxes(title=\"Count\")\n",
    "    fig.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "decade_mean = df.groupby(\"decade\")[cols].mean()\n",
    "\n",
    "fig = make_subplots(\n",
    "    rows=4,\n",
    "    cols=3,\n",
    "    subplot_titles=(\n",
    "        decade_mean.columns[0],\n",
    "        decade_mean.columns[1],\n",
    "        decade_mean.columns[2],\n",
    "        decade_mean.columns[3],\n",
    "        decade_mean.columns[4],\n",
    "        decade_mean.columns[5],\n",
    "        decade_mean.columns[6],\n",
    "        decade_mean.columns[7],\n",
    "        decade_mean.columns[8],\n",
    "        decade_mean.columns[9],\n",
    "        decade_mean.columns[10],\n",
    "    ),\n",
    "    vertical_spacing=0.1,\n",
    ")\n",
    "\n",
    "fig.add_trace(\n",
    "    go.Bar(\n",
    "        y=decade_mean.index,\n",
    "        x=decade_mean.iloc[:, 0],\n",
    "        name=decade_mean.columns[0],\n",
    "        orientation=\"h\",\n",
    "    ),\n",
    "    row=1,\n",
    "    col=1,\n",
    ")\n",
    "\n",
    "fig.add_trace(\n",
    "    go.Bar(\n",
    "        y=decade_mean.index,\n",
    "        x=decade_mean.iloc[:, 1],\n",
    "        name=decade_mean.columns[1],\n",
    "        orientation=\"h\",\n",
    "    ),\n",
    "    row=1,\n",
    "    col=2,\n",
    ")\n",
    "\n",
    "fig.add_trace(\n",
    "    go.Bar(\n",
    "        y=decade_mean.index,\n",
    "        x=decade_mean.iloc[:, 2],\n",
    "        name=decade_mean.columns[2],\n",
    "        orientation=\"h\",\n",
    "    ),\n",
    "    row=1,\n",
    "    col=3,\n",
    ")\n",
    "\n",
    "fig.add_trace(\n",
    "    go.Bar(\n",
    "        y=decade_mean.index,\n",
    "        x=decade_mean.iloc[:, 3],\n",
    "        name=decade_mean.columns[3],\n",
    "        orientation=\"h\",\n",
    "    ),\n",
    "    row=2,\n",
    "    col=1,\n",
    ")\n",
    "\n",
    "fig.add_trace(\n",
    "    go.Bar(\n",
    "        y=decade_mean.index,\n",
    "        x=decade_mean.iloc[:, 4],\n",
    "        name=decade_mean.columns[4],\n",
    "        orientation=\"h\",\n",
    "    ),\n",
    "    row=2,\n",
    "    col=2,\n",
    ")\n",
    "\n",
    "fig.add_trace(\n",
    "    go.Bar(\n",
    "        y=decade_mean.index,\n",
    "        x=decade_mean.iloc[:, 5],\n",
    "        name=decade_mean.columns[5],\n",
    "        orientation=\"h\",\n",
    "    ),\n",
    "    row=2,\n",
    "    col=3,\n",
    ")\n",
    "\n",
    "fig.add_trace(\n",
    "    go.Bar(\n",
    "        y=decade_mean.index,\n",
    "        x=decade_mean.iloc[:, 6],\n",
    "        name=decade_mean.columns[6],\n",
    "        orientation=\"h\",\n",
    "    ),\n",
    "    row=3,\n",
    "    col=1,\n",
    ")\n",
    "\n",
    "fig.add_trace(\n",
    "    go.Bar(\n",
    "        y=decade_mean.index,\n",
    "        x=decade_mean.iloc[:, 7],\n",
    "        name=decade_mean.columns[7],\n",
    "        orientation=\"h\",\n",
    "    ),\n",
    "    row=3,\n",
    "    col=2,\n",
    ")\n",
    "\n",
    "fig.add_trace(\n",
    "    go.Bar(\n",
    "        y=decade_mean.index,\n",
    "        x=decade_mean.iloc[:, 8],\n",
    "        name=decade_mean.columns[8],\n",
    "        orientation=\"h\",\n",
    "    ),\n",
    "    row=3,\n",
    "    col=3,\n",
    ")\n",
    "\n",
    "fig.add_trace(\n",
    "    go.Bar(\n",
    "        y=decade_mean.index,\n",
    "        x=decade_mean.iloc[:, 9],\n",
    "        name=decade_mean.columns[9],\n",
    "        orientation=\"h\",\n",
    "    ),\n",
    "    row=4,\n",
    "    col=1,\n",
    ")\n",
    "\n",
    "fig.add_trace(\n",
    "    go.Bar(\n",
    "        y=decade_mean.index,\n",
    "        x=decade_mean.iloc[:, 10],\n",
    "        name=decade_mean.columns[10],\n",
    "        orientation=\"h\",\n",
    "    ),\n",
    "    row=4,\n",
    "    col=2,\n",
    ")\n",
    "\n",
    "fig.update_layout(\n",
    "    title={\"text\": \"Mean Musical Values per Decade\", \"font\": {\"size\": 22}},\n",
    "    legend={\n",
    "        \"orientation\": \"v\",\n",
    "        \"yanchor\": \"top\",\n",
    "        \"y\": 0.2,\n",
    "        \"xanchor\": \"right\",\n",
    "        \"x\": 0.9,\n",
    "    },\n",
    "    margin={\"b\": 10, \"r\": 10},\n",
    "    height=980,\n",
    ")\n",
    "\n",
    "fig.show()\n",
    "\n",
    "del decade_mean"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "decade_median = df.groupby(\"decade\")[cols].median()\n",
    "\n",
    "fig = make_subplots(\n",
    "    rows=4,\n",
    "    cols=3,\n",
    "    subplot_titles=(\n",
    "        decade_median.columns[0],\n",
    "        decade_median.columns[1],\n",
    "        decade_median.columns[2],\n",
    "        decade_median.columns[3],\n",
    "        decade_median.columns[4],\n",
    "        decade_median.columns[5],\n",
    "        decade_median.columns[6],\n",
    "        decade_median.columns[7],\n",
    "        decade_median.columns[8],\n",
    "        decade_median.columns[9],\n",
    "        decade_median.columns[10],\n",
    "    ),\n",
    "    vertical_spacing=0.1,\n",
    ")\n",
    "\n",
    "fig.add_trace(\n",
    "    go.Bar(\n",
    "        y=decade_median.index,\n",
    "        x=decade_median.iloc[:, 0],\n",
    "        name=decade_median.columns[0],\n",
    "        orientation=\"h\",\n",
    "    ),\n",
    "    row=1,\n",
    "    col=1,\n",
    ")\n",
    "\n",
    "fig.add_trace(\n",
    "    go.Bar(\n",
    "        y=decade_median.index,\n",
    "        x=decade_median.iloc[:, 1],\n",
    "        name=decade_median.columns[1],\n",
    "        orientation=\"h\",\n",
    "    ),\n",
    "    row=1,\n",
    "    col=2,\n",
    ")\n",
    "\n",
    "fig.add_trace(\n",
    "    go.Bar(\n",
    "        y=decade_median.index,\n",
    "        x=decade_median.iloc[:, 2],\n",
    "        name=decade_median.columns[2],\n",
    "        orientation=\"h\",\n",
    "    ),\n",
    "    row=1,\n",
    "    col=3,\n",
    ")\n",
    "\n",
    "fig.add_trace(\n",
    "    go.Bar(\n",
    "        y=decade_median.index,\n",
    "        x=decade_median.iloc[:, 3],\n",
    "        name=decade_median.columns[3],\n",
    "        orientation=\"h\",\n",
    "    ),\n",
    "    row=2,\n",
    "    col=1,\n",
    ")\n",
    "\n",
    "fig.add_trace(\n",
    "    go.Bar(\n",
    "        y=decade_median.index,\n",
    "        x=decade_median.iloc[:, 4],\n",
    "        name=decade_median.columns[4],\n",
    "        orientation=\"h\",\n",
    "    ),\n",
    "    row=2,\n",
    "    col=2,\n",
    ")\n",
    "\n",
    "fig.add_trace(\n",
    "    go.Bar(\n",
    "        y=decade_median.index,\n",
    "        x=decade_median.iloc[:, 5],\n",
    "        name=decade_median.columns[5],\n",
    "        orientation=\"h\",\n",
    "    ),\n",
    "    row=2,\n",
    "    col=3,\n",
    ")\n",
    "\n",
    "fig.add_trace(\n",
    "    go.Bar(\n",
    "        y=decade_median.index,\n",
    "        x=decade_median.iloc[:, 6],\n",
    "        name=decade_median.columns[6],\n",
    "        orientation=\"h\",\n",
    "    ),\n",
    "    row=3,\n",
    "    col=1,\n",
    ")\n",
    "\n",
    "fig.add_trace(\n",
    "    go.Bar(\n",
    "        y=decade_median.index,\n",
    "        x=decade_median.iloc[:, 7],\n",
    "        name=decade_median.columns[7],\n",
    "        orientation=\"h\",\n",
    "    ),\n",
    "    row=3,\n",
    "    col=2,\n",
    ")\n",
    "\n",
    "fig.add_trace(\n",
    "    go.Bar(\n",
    "        y=decade_median.index,\n",
    "        x=decade_median.iloc[:, 8],\n",
    "        name=decade_median.columns[8],\n",
    "        orientation=\"h\",\n",
    "    ),\n",
    "    row=3,\n",
    "    col=3,\n",
    ")\n",
    "\n",
    "fig.add_trace(\n",
    "    go.Bar(\n",
    "        y=decade_median.index,\n",
    "        x=decade_median.iloc[:, 9],\n",
    "        name=decade_median.columns[9],\n",
    "        orientation=\"h\",\n",
    "    ),\n",
    "    row=4,\n",
    "    col=1,\n",
    ")\n",
    "\n",
    "fig.add_trace(\n",
    "    go.Bar(\n",
    "        y=decade_median.index,\n",
    "        x=decade_median.iloc[:, 10],\n",
    "        name=decade_median.columns[10],\n",
    "        orientation=\"h\",\n",
    "    ),\n",
    "    row=4,\n",
    "    col=2,\n",
    ")\n",
    "\n",
    "fig.update_layout(\n",
    "    title={\"text\": \"Median Musical Values per Decade\", \"font\": {\"size\": 22}},\n",
    "    legend={\n",
    "        \"orientation\": \"v\",\n",
    "        \"yanchor\": \"top\",\n",
    "        \"y\": 0.2,\n",
    "        \"xanchor\": \"right\",\n",
    "        \"x\": 0.9,\n",
    "    },\n",
    "    margin={\"b\": 10, \"r\": 10},\n",
    "    height=980,\n",
    ")\n",
    "\n",
    "fig.show()\n",
    "\n",
    "del decade_median"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "explicit_count = (\n",
    "    df.groupby([\"decade\", \"explicit\"], as_index=False)[\"year\"]\n",
    "    .count()\n",
    "    .rename(columns={\"year\": \"count\"})\n",
    ")\n",
    "key_count = (\n",
    "    df.groupby([\"decade\", \"key\"], as_index=False)[\"year\"]\n",
    "    .count()\n",
    "    .rename(columns={\"year\": \"count\"})\n",
    ")\n",
    "mode_count = (\n",
    "    df.groupby([\"decade\", \"mode\"], as_index=False)[\"year\"]\n",
    "    .count()\n",
    "    .rename(columns={\"year\": \"count\"})\n",
    ")\n",
    "\n",
    "fig = px.histogram(\n",
    "    data_frame=explicit_count,\n",
    "    x=\"decade\",\n",
    "    y=\"count\",\n",
    "    color=\"explicit\",\n",
    "    histfunc=\"sum\",\n",
    "    color_discrete_sequence=px.colors.qualitative.Pastel,\n",
    "    text_auto=True,\n",
    ")\n",
    "fig.update_layout(\n",
    "    title={\"text\": \"Explicit Count per Decade\", \"font\": {\"size\": 24}},\n",
    "    bargap=0.2,\n",
    "    bargroupgap=0.1,\n",
    "    barmode=\"group\",\n",
    "    xaxis_title=\"Decade\",\n",
    "    yaxis_title=\"Count\",\n",
    ")\n",
    "fig.show()\n",
    "\n",
    "fig = px.histogram(\n",
    "    data_frame=mode_count,\n",
    "    x=\"decade\",\n",
    "    y=\"count\",\n",
    "    color=\"mode\",\n",
    "    histfunc=\"sum\",\n",
    "    color_discrete_sequence=px.colors.qualitative.Pastel,\n",
    "    text_auto=True,\n",
    ")\n",
    "fig.update_layout(\n",
    "    title={\"text\": \"Mode Count per Decade\", \"font\": {\"size\": 24}},\n",
    "    bargap=0.2,\n",
    "    bargroupgap=0.1,\n",
    "    barmode=\"group\",\n",
    "    xaxis_title=\"Decade\",\n",
    "    yaxis_title=\"Count\",\n",
    ")\n",
    "fig.show()\n",
    "\n",
    "fig = px.histogram(\n",
    "    data_frame=key_count,\n",
    "    x=\"decade\",\n",
    "    y=\"count\",\n",
    "    color=\"key\",\n",
    "    histfunc=\"sum\",\n",
    "    color_discrete_sequence=px.colors.qualitative.Pastel,\n",
    "    text_auto=True,\n",
    ")\n",
    "fig.update_layout(\n",
    "    title={\"text\": \"Key Count per Decade\", \"font\": {\"size\": 24}},\n",
    "    bargap=0.2,\n",
    "    bargroupgap=0.1,\n",
    "    barmode=\"stack\",\n",
    "    xaxis_title=\"Decade\",\n",
    "    yaxis_title=\"Count\",\n",
    ")\n",
    "fig.show()\n",
    "\n",
    "del (mode_count, key_count, explicit_count)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "cols = [\n",
    "    \"valence\",\n",
    "    \"acousticness\",\n",
    "    \"danceability\",\n",
    "    \"duration_min\",\n",
    "    \"energy\",\n",
    "    \"instrumentalness\",\n",
    "    \"liveness\",\n",
    "    \"loudness\",\n",
    "    \"year\",\n",
    "    \"speechiness\",\n",
    "    \"tempo\",\n",
    "]\n",
    "\n",
    "for col in cols:\n",
    "\n",
    "    fig = px.scatter(\n",
    "        data_frame=df,\n",
    "        x=col,\n",
    "        y=\"popularity\",\n",
    "        trendline=\"ols\",\n",
    "        trendline_color_override=\"#A6E3A1\",\n",
    "    )\n",
    "    fig.update_traces(marker={\"opacity\": 0.3, \"size\": 3, \"color\": \"#B4BEFE\"})\n",
    "    fig.update_layout(title={\"text\": f\"{col} vs popularity\", \"font\": {\"size\": 24}})\n",
    "    fig.show()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Header 1\n",
    "\n",
    "## Header 2\n",
    "\n",
    "### Header 3.1"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "cols = [\n",
    "    \"valence\",\n",
    "    \"acousticness\",\n",
    "    \"danceability\",\n",
    "    \"duration_min\",\n",
    "    \"energy\",\n",
    "    \"instrumentalness\",\n",
    "    \"liveness\",\n",
    "    \"loudness\",\n",
    "    \"year\",\n",
    "    \"speechiness\",\n",
    "    \"tempo\",\n",
    "]\n",
    "\n",
    "plt.figure(figsize=(15, 10))\n",
    "\n",
    "for i, col in enumerate(cols):\n",
    "    ax = plt.subplot(3, 4, i + 1)\n",
    "    sns.regplot(\n",
    "        data=df,\n",
    "        x=\"popularity\",\n",
    "        y=col,\n",
    "        ax=ax,\n",
    "        scatter_kws={\"alpha\": 0.5},\n",
    "        line_kws={\"color\": \"#F38BA8\"},\n",
    "    )\n",
    "\n",
    "plt.tight_layout()\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "cols = [\n",
    "    \"valence\",\n",
    "    \"acousticness\",\n",
    "    \"danceability\",\n",
    "    \"duration_min\",\n",
    "    \"energy\",\n",
    "    \"instrumentalness\",\n",
    "    \"liveness\",\n",
    "    \"loudness\",\n",
    "    \"year\",\n",
    "    \"speechiness\",\n",
    "    \"tempo\",\n",
    "    \"popularity\",\n",
    "]\n",
    "\n",
    "plt.figure(figsize=(10, 7))\n",
    "mask = np.triu(np.ones_like(df[cols].corr()))\n",
    "sns.heatmap(\n",
    "    df[cols].corr(),\n",
    "    annot=True,\n",
    "    fmt=\".2f\",\n",
    "    cmap=\"Blues\",\n",
    "    mask=mask,\n",
    ")\n",
    "plt.grid(visible=False)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "df[\"first_artist\"] = (\n",
    "    df[\"artists\"]\n",
    "    .apply(lambda x: str(x).split(\"x\")[0])\n",
    "    .apply(lambda x: str(x).replace(\"[\", \"\"))\n",
    "    .apply(lambda x: str(x).replace(\"]\", \"\"))\n",
    "    .apply(lambda x: str(x).replace(\"'\", \"\"))\n",
    ")\n",
    "df = df.drop(\"artists\", axis=1)\n",
    "df[\"first_artist\"] = df[\"first_artist\"].apply(lambda x: str(x).split(\",\")[0])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "popularity_check = (\n",
    "    df.groupby([\"first_artist\"], as_index=False)[\"popularity\"]\n",
    "    .agg({\"mean\", \"count\", \"median\"})\n",
    "    .sort_values(by=\"mean\", ascending=False)\n",
    "    .reset_index(drop=True)\n",
    ")\n",
    "\n",
    "popularity_check = popularity_check.drop(16091, axis=0)\n",
    "popularity_check = popularity_check.drop(16086, axis=0)\n",
    "popularity_check = popularity_check.drop(16429, axis=0)\n",
    "\n",
    "to_drop = popularity_check[popularity_check[\"count\"] <= 45].index\n",
    "popularity_check = popularity_check.drop(to_drop)\n",
    "popularity_check = popularity_check.sort_values(by=\"mean\", ascending=False).head(50)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Header 1\n",
    "\n",
    "## Header 2\n",
    "\n",
    "### Header 3.1"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "top_50_artists = pd.DataFrame()\n",
    "\n",
    "for i in popularity_check[\"first_artist\"].unique():\n",
    "    artist = df.query(\"first_artist == @i\")\n",
    "    top_50_artists = pd.concat([top_50_artists, artist], axis=0)\n",
    "\n",
    "top_50_artists = top_50_artists.reset_index(drop=True)\n",
    "top_50_artists.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "plt.figure(figsize=(12, 8))\n",
    "(\n",
    "    top_50_artists[\"first_artist\"]\n",
    "    .value_counts()\n",
    "    .sort_values(ascending=True)\n",
    "    .plot(kind=\"barh\")\n",
    ")\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "top_50_artists[\"decade\"].value_counts().sort_values(ascending=True).plot(kind=\"barh\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "cols = [\n",
    "    \"valence\",\n",
    "    \"acousticness\",\n",
    "    \"danceability\",\n",
    "    \"duration_min\",\n",
    "    \"energy\",\n",
    "    \"instrumentalness\",\n",
    "    \"liveness\",\n",
    "    \"loudness\",\n",
    "    \"year\",\n",
    "    \"speechiness\",\n",
    "    \"tempo\",\n",
    "]\n",
    "\n",
    "plt.figure(figsize=(15, 10))\n",
    "\n",
    "for i, col in enumerate(cols):\n",
    "    ax = plt.subplot(3, 4, i + 1)\n",
    "    sns.kdeplot(data=top_50_artists, x=col, hue=\"first_artist\", legend=False)\n",
    "\n",
    "plt.tight_layout()\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Header 1\n",
    "\n",
    "## Header 2\n",
    "\n",
    "### Header 3.1"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Header 1\n",
    "\n",
    "## Header 2\n",
    "\n",
    "### Header 3.1"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Header 1\n",
    "\n",
    "## Header 2\n",
    "\n",
    "### Header 3.1"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Header 1\n",
    "\n",
    "## Header 2\n",
    "\n",
    "### Header 3.1"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Header 1\n",
    "\n",
    "## Header 2\n",
    "\n",
    "### Header 3.1"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "import pandas as pd\n",
    "import numpy as np\n",
    "import seaborn as sns\n",
    "import matplotlib.pyplot as plt\n",
    "import matplotlib as mpl\n",
    "import mplcatppuccin\n",
    "import plotly.express as px\n",
    "import plotly.graph_objects as go\n",
    "from plotly.subplots import make_subplots\n",
    "import plotly.figure_factory as ff\n",
    "import warnings\n",
    "import plotly.io as pio\n",
    "\n",
    "warnings.filterwarnings('ignore')\n",
    "\n",
    "pio.renderers.default = 'notebook_connected'\n",
    "pio.templates.default = 'plotly_dark'\n",
    "\n",
    "\n",
    "%matplotlib inline\n",
    "%config InlineBackend.figure_format = 'retina'\n",
    "pd.set_option('display.max_columns', None)\n",
    "pd.set_option('display.precision', 2)\n",
    "pd.set_option('display.colheader_justify', 'left')\n",
    "\n",
    "mpl.rc(\n",
    "    'figure',\n",
    "    autolayout=True,\n",
    "    titlesize=18\n",
    ")\n",
    "\n",
    "mpl.style.use(['ggplot', 'mocha'])\n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Header 3.2\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "df = pd.read_csv(\n",
    "    \"data.csv\",\n",
    "    parse_dates=[\"release_date\"],\n",
    ")\n",
    "df.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "map_key = {\n",
    "    0: \"C\",\n",
    "    1: \"C#\",\n",
    "    2: \"D\",\n",
    "    3: \"D#\",\n",
    "    4: \"E\",\n",
    "    5: \"F\",\n",
    "    6: \"F#\",\n",
    "    7: \"G\",\n",
    "    8: \"G#\",\n",
    "    9: \"A\",\n",
    "    10: \"A#\",\n",
    "    11: \"B\",\n",
    "}\n",
    "\n",
    "map_mode = {1: \"Major\", 0: \"Minor\"}\n",
    "\n",
    "df[\"mode\"] = df[\"mode\"].map(map_mode)\n",
    "df[\"key\"] = df[\"key\"].map(map_key)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "check_dups = df[[\"artists\", \"name\"]]\n",
    "dups = check_dups[check_dups.duplicated()].index"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "print(\"Before dropping duplicated:\", df.shape)\n",
    "df = df.drop(dups)\n",
    "print(\"After dropping duplicated:\", df.shape)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Header 1.3\n",
    "\n",
    "## Header 2.3\n",
    "\n",
    "### Header 3.5"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "df[\"duration_ms\"] = df[\"duration_ms\"] / 60_000\n",
    "df = df.rename(columns={\"duration_ms\": \"duration_min\"})\n",
    "df.head()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Header 1.4\n",
    "\n",
    "## Header 2.4\n",
    "\n",
    "### Header 3.5"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "df = df.drop([\"release_date\", \"id\"], axis=1)\n",
    "df.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "def fun_subplots_plotly(df, col):\n",
    "\n",
    "    mean_val = df[col].mean()\n",
    "    median_val = df[col].median()\n",
    "    fig = make_subplots(rows=1, cols=2, column_widths=[0.75, 0.25])\n",
    "\n",
    "    fig.add_trace(\n",
    "        go.Histogram(\n",
    "            x=df[col], name=f\"Histogram {col}\", marker={\"color\": \"#EBA0AC\"}, nbinsx=50\n",
    "        ),\n",
    "        row=1,\n",
    "        col=1,\n",
    "    )\n",
    "\n",
    "    fig.add_shape(\n",
    "        type=\"line\",\n",
    "        xref=\"paper\",\n",
    "        yref=\"y\",\n",
    "        x0=-1,\n",
    "        x1=1,\n",
    "        y0=mean_val,\n",
    "        y1=mean_val,\n",
    "        row=1,\n",
    "        col=2,\n",
    "        line={\"color\": \"#A6E3A1\", \"width\": 3, \"dash\": \"dot\"},\n",
    "    )\n",
    "\n",
    "    fig.add_shape(\n",
    "        type=\"line\",\n",
    "        xref=\"paper\",\n",
    "        yref=\"y\",\n",
    "        x0=-1,\n",
    "        x1=1,\n",
    "        y0=median_val,\n",
    "        y1=median_val,\n",
    "        row=1,\n",
    "        col=2,\n",
    "        line={\"color\": \"#CBA6F7\", \"width\": 3, \"dash\": \"dot\"},\n",
    "    )\n",
    "\n",
    "    fig.add_annotation(\n",
    "        xref=\"paper\",\n",
    "        x=-0.7,\n",
    "        y=mean_val,\n",
    "        showarrow=True,\n",
    "        arrowhead=2,\n",
    "        text=f\"Mean = {mean_val:.2f}\",\n",
    "        row=1,\n",
    "        col=2,\n",
    "    )\n",
    "\n",
    "    fig.add_annotation(\n",
    "        xref=\"paper\",\n",
    "        x=0.7,\n",
    "        y=median_val,\n",
    "        showarrow=True,\n",
    "        arrowhead=2,\n",
    "        text=f\"Median = {median_val:.2f}\",\n",
    "        row=1,\n",
    "        col=2,\n",
    "    )\n",
    "\n",
    "    fig.add_trace(\n",
    "        go.Box(y=df[col], name=f\"Boxplot {col}\", marker={\"color\": \"#F9E2AF\"}),\n",
    "        row=1,\n",
    "        col=2,\n",
    "    )\n",
    "\n",
    "    fig.update_layout(\n",
    "        title={\"text\": f\"Distribution Plot {col}\", \"font\": {\"size\": 24}},\n",
    "        legend={\n",
    "            \"orientation\": \"h\",\n",
    "            \"yanchor\": \"bottom\",\n",
    "            \"y\": 1.02,\n",
    "            \"xanchor\": \"right\",\n",
    "            \"x\": 1,\n",
    "        },\n",
    "    )\n",
    "    fig.update_yaxes(title_text=\"Count\", row=1, col=1)\n",
    "    fig.update_yaxes(title_text=f\"{col}\", row=1, col=2)\n",
    "    fig.update_xaxes(title_text=f\"{col}\", row=1, col=1)\n",
    "    fig.update_xaxes(title_text=\"\", row=1, col=2)\n",
    "    fig.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "music_vals = [\n",
    "    \"valence\",\n",
    "    \"acousticness\",\n",
    "    \"danceability\",\n",
    "    \"duration_min\",\n",
    "    \"energy\",\n",
    "    \"instrumentalness\",\n",
    "    \"liveness\",\n",
    "    \"loudness\",\n",
    "    \"popularity\",\n",
    "    \"speechiness\",\n",
    "    \"tempo\",\n",
    "]\n",
    "\n",
    "for col in music_vals:\n",
    "    fun_subplots_plotly(df, col)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Header 1.2\n",
    "\n",
    "## Header 2.2\n",
    "\n",
    "### Header 3.4"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "bins = pd.IntervalIndex.from_breaks(\n",
    "    [1920, 1930, 1940, 1950, 1960, 1970, 1980, 1990, 2000, 2010, 2020]\n",
    ")\n",
    "\n",
    "df[\"decade\"] = pd.cut(df[\"year\"], bins).astype(\"str\")\n",
    "\n",
    "map_decade = {\n",
    "    \"(1920, 1930]\": \"1920s\",\n",
    "    \"(1930, 1940]\": \"1930s\",\n",
    "    \"(1940, 1950]\": \"1940s\",\n",
    "    \"(1950, 1960]\": \"1950s\",\n",
    "    \"(1960, 1970]\": \"1960s\",\n",
    "    \"(1970, 1980]\": \"1970s\",\n",
    "    \"(1980, 1990]\": \"1980s\",\n",
    "    \"(1990, 2000]\": \"1990s\",\n",
    "    \"(2000, 2010]\": \"2000s\",\n",
    "    \"(2010, 2020]\": \"2010s\",\n",
    "}\n",
    "\n",
    "df[\"decade\"] = df[\"decade\"].map(map_decade)\n",
    "\n",
    "df.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "decade_counts = (\n",
    "    df[\"decade\"].value_counts().reset_index().sort_values(by=\"decade\", ascending=True)\n",
    ")\n",
    "\n",
    "fig = px.bar(\n",
    "    data_frame=decade_counts,\n",
    "    y=\"decade\",\n",
    "    x=\"count\",\n",
    "    color=\"count\",\n",
    "    color_continuous_scale=px.colors.sequential.Sunset,\n",
    "    text_auto=True,\n",
    ")\n",
    "\n",
    "fig.update_layout(\n",
    "    title={\"text\": \"Count of songs per decade\", \"font\": {\"size\": 24}},\n",
    "    coloraxis_colorbar={\n",
    "        \"title\": \"Count\",\n",
    "        \"thicknessmode\": \"pixels\",\n",
    "        \"thickness\": 20,\n",
    "        \"lenmode\": \"pixels\",\n",
    "        \"len\": 500,\n",
    "        \"yanchor\": \"top\",\n",
    "        \"xanchor\": \"right\",\n",
    "        \"y\": 1.15,\n",
    "        \"x\": 0.95,\n",
    "        \"orientation\": \"h\",\n",
    "    },\n",
    "    margin={\"r\": 10},\n",
    ")\n",
    "\n",
    "fig.update_xaxes(title=\"Count\")\n",
    "fig.update_yaxes(title=\"Decades\")\n",
    "fig.show()\n",
    "\n",
    "del decade_counts"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "df = df.query(\"duration_min <= 5\")"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Header 1.2\n",
    "\n",
    "## Header 2.2\n",
    "\n",
    "### Header 3.4"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "decade_counts = (\n",
    "    df[\"decade\"].value_counts().reset_index().sort_values(by=\"decade\", ascending=True)\n",
    ")\n",
    "\n",
    "fig = px.bar(\n",
    "    data_frame=decade_counts,\n",
    "    y=\"decade\",\n",
    "    x=\"count\",\n",
    "    color=\"count\",\n",
    "    color_continuous_scale=px.colors.sequential.Sunset,\n",
    "    text_auto=True,\n",
    ")\n",
    "\n",
    "fig.update_layout(\n",
    "    title={\"text\": \"Count of songs per decade (< 5min)\", \"font\": {\"size\": 24}},\n",
    "    coloraxis_colorbar={\n",
    "        \"title\": \"Count\",\n",
    "        \"thicknessmode\": \"pixels\",\n",
    "        \"thickness\": 20,\n",
    "        \"lenmode\": \"pixels\",\n",
    "        \"len\": 500,\n",
    "        \"yanchor\": \"top\",\n",
    "        \"xanchor\": \"right\",\n",
    "        \"y\": 1.15,\n",
    "        \"x\": 0.95,\n",
    "        \"orientation\": \"h\",\n",
    "    },\n",
    "    margin={\"r\": 10},\n",
    ")\n",
    "\n",
    "fig.update_xaxes(title=\"Count\")\n",
    "fig.update_yaxes(title=\"Decades\")\n",
    "fig.show()\n",
    "\n",
    "del decade_counts"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "cols = [\n",
    "    \"valence\",\n",
    "    \"acousticness\",\n",
    "    \"danceability\",\n",
    "    \"duration_min\",\n",
    "    \"energy\",\n",
    "    \"instrumentalness\",\n",
    "    \"liveness\",\n",
    "    \"loudness\",\n",
    "    \"popularity\",\n",
    "    \"speechiness\",\n",
    "    \"tempo\",\n",
    "]\n",
    "for col in cols:\n",
    "    fig = px.histogram(\n",
    "        data_frame=df,\n",
    "        x=col,\n",
    "        color=\"decade\",\n",
    "        color_discrete_sequence=px.colors.qualitative.Light24,\n",
    "    )\n",
    "    fig.update_traces(opacity=0.7)\n",
    "    fig.update_layout(\n",
    "        bargap=0.1,\n",
    "        bargroupgap=0.05,\n",
    "        barmode=\"stack\",\n",
    "        title={\"text\": f\"Histogram of {col} per decade\", \"font\": {\"size\": 24}},\n",
    "        legend={\"title\": \"Decade\"},\n",
    "    )\n",
    "    fig.update_yaxes(title=\"Count\")\n",
    "    fig.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "decade_mean = df.groupby(\"decade\")[cols].mean()\n",
    "\n",
    "fig = make_subplots(\n",
    "    rows=4,\n",
    "    cols=3,\n",
    "    subplot_titles=(\n",
    "        decade_mean.columns[0],\n",
    "        decade_mean.columns[1],\n",
    "        decade_mean.columns[2],\n",
    "        decade_mean.columns[3],\n",
    "        decade_mean.columns[4],\n",
    "        decade_mean.columns[5],\n",
    "        decade_mean.columns[6],\n",
    "        decade_mean.columns[7],\n",
    "        decade_mean.columns[8],\n",
    "        decade_mean.columns[9],\n",
    "        decade_mean.columns[10],\n",
    "    ),\n",
    "    vertical_spacing=0.1,\n",
    ")\n",
    "\n",
    "fig.add_trace(\n",
    "    go.Bar(\n",
    "        y=decade_mean.index,\n",
    "        x=decade_mean.iloc[:, 0],\n",
    "        name=decade_mean.columns[0],\n",
    "        orientation=\"h\",\n",
    "    ),\n",
    "    row=1,\n",
    "    col=1,\n",
    ")\n",
    "\n",
    "fig.add_trace(\n",
    "    go.Bar(\n",
    "        y=decade_mean.index,\n",
    "        x=decade_mean.iloc[:, 1],\n",
    "        name=decade_mean.columns[1],\n",
    "        orientation=\"h\",\n",
    "    ),\n",
    "    row=1,\n",
    "    col=2,\n",
    ")\n",
    "\n",
    "fig.add_trace(\n",
    "    go.Bar(\n",
    "        y=decade_mean.index,\n",
    "        x=decade_mean.iloc[:, 2],\n",
    "        name=decade_mean.columns[2],\n",
    "        orientation=\"h\",\n",
    "    ),\n",
    "    row=1,\n",
    "    col=3,\n",
    ")\n",
    "\n",
    "fig.add_trace(\n",
    "    go.Bar(\n",
    "        y=decade_mean.index,\n",
    "        x=decade_mean.iloc[:, 3],\n",
    "        name=decade_mean.columns[3],\n",
    "        orientation=\"h\",\n",
    "    ),\n",
    "    row=2,\n",
    "    col=1,\n",
    ")\n",
    "\n",
    "fig.add_trace(\n",
    "    go.Bar(\n",
    "        y=decade_mean.index,\n",
    "        x=decade_mean.iloc[:, 4],\n",
    "        name=decade_mean.columns[4],\n",
    "        orientation=\"h\",\n",
    "    ),\n",
    "    row=2,\n",
    "    col=2,\n",
    ")\n",
    "\n",
    "fig.add_trace(\n",
    "    go.Bar(\n",
    "        y=decade_mean.index,\n",
    "        x=decade_mean.iloc[:, 5],\n",
    "        name=decade_mean.columns[5],\n",
    "        orientation=\"h\",\n",
    "    ),\n",
    "    row=2,\n",
    "    col=3,\n",
    ")\n",
    "\n",
    "fig.add_trace(\n",
    "    go.Bar(\n",
    "        y=decade_mean.index,\n",
    "        x=decade_mean.iloc[:, 6],\n",
    "        name=decade_mean.columns[6],\n",
    "        orientation=\"h\",\n",
    "    ),\n",
    "    row=3,\n",
    "    col=1,\n",
    ")\n",
    "\n",
    "fig.add_trace(\n",
    "    go.Bar(\n",
    "        y=decade_mean.index,\n",
    "        x=decade_mean.iloc[:, 7],\n",
    "        name=decade_mean.columns[7],\n",
    "        orientation=\"h\",\n",
    "    ),\n",
    "    row=3,\n",
    "    col=2,\n",
    ")\n",
    "\n",
    "fig.add_trace(\n",
    "    go.Bar(\n",
    "        y=decade_mean.index,\n",
    "        x=decade_mean.iloc[:, 8],\n",
    "        name=decade_mean.columns[8],\n",
    "        orientation=\"h\",\n",
    "    ),\n",
    "    row=3,\n",
    "    col=3,\n",
    ")\n",
    "\n",
    "fig.add_trace(\n",
    "    go.Bar(\n",
    "        y=decade_mean.index,\n",
    "        x=decade_mean.iloc[:, 9],\n",
    "        name=decade_mean.columns[9],\n",
    "        orientation=\"h\",\n",
    "    ),\n",
    "    row=4,\n",
    "    col=1,\n",
    ")\n",
    "\n",
    "fig.add_trace(\n",
    "    go.Bar(\n",
    "        y=decade_mean.index,\n",
    "        x=decade_mean.iloc[:, 10],\n",
    "        name=decade_mean.columns[10],\n",
    "        orientation=\"h\",\n",
    "    ),\n",
    "    row=4,\n",
    "    col=2,\n",
    ")\n",
    "\n",
    "fig.update_layout(\n",
    "    title={\"text\": \"Mean Musical Values per Decade\", \"font\": {\"size\": 22}},\n",
    "    legend={\n",
    "        \"orientation\": \"v\",\n",
    "        \"yanchor\": \"top\",\n",
    "        \"y\": 0.2,\n",
    "        \"xanchor\": \"right\",\n",
    "        \"x\": 0.9,\n",
    "    },\n",
    "    margin={\"b\": 10, \"r\": 10},\n",
    "    height=980,\n",
    ")\n",
    "\n",
    "fig.show()\n",
    "\n",
    "del decade_mean"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "decade_median = df.groupby(\"decade\")[cols].median()\n",
    "\n",
    "fig = make_subplots(\n",
    "    rows=4,\n",
    "    cols=3,\n",
    "    subplot_titles=(\n",
    "        decade_median.columns[0],\n",
    "        decade_median.columns[1],\n",
    "        decade_median.columns[2],\n",
    "        decade_median.columns[3],\n",
    "        decade_median.columns[4],\n",
    "        decade_median.columns[5],\n",
    "        decade_median.columns[6],\n",
    "        decade_median.columns[7],\n",
    "        decade_median.columns[8],\n",
    "        decade_median.columns[9],\n",
    "        decade_median.columns[10],\n",
    "    ),\n",
    "    vertical_spacing=0.1,\n",
    ")\n",
    "\n",
    "fig.add_trace(\n",
    "    go.Bar(\n",
    "        y=decade_median.index,\n",
    "        x=decade_median.iloc[:, 0],\n",
    "        name=decade_median.columns[0],\n",
    "        orientation=\"h\",\n",
    "    ),\n",
    "    row=1,\n",
    "    col=1,\n",
    ")\n",
    "\n",
    "fig.add_trace(\n",
    "    go.Bar(\n",
    "        y=decade_median.index,\n",
    "        x=decade_median.iloc[:, 1],\n",
    "        name=decade_median.columns[1],\n",
    "        orientation=\"h\",\n",
    "    ),\n",
    "    row=1,\n",
    "    col=2,\n",
    ")\n",
    "\n",
    "fig.add_trace(\n",
    "    go.Bar(\n",
    "        y=decade_median.index,\n",
    "        x=decade_median.iloc[:, 2],\n",
    "        name=decade_median.columns[2],\n",
    "        orientation=\"h\",\n",
    "    ),\n",
    "    row=1,\n",
    "    col=3,\n",
    ")\n",
    "\n",
    "fig.add_trace(\n",
    "    go.Bar(\n",
    "        y=decade_median.index,\n",
    "        x=decade_median.iloc[:, 3],\n",
    "        name=decade_median.columns[3],\n",
    "        orientation=\"h\",\n",
    "    ),\n",
    "    row=2,\n",
    "    col=1,\n",
    ")\n",
    "\n",
    "fig.add_trace(\n",
    "    go.Bar(\n",
    "        y=decade_median.index,\n",
    "        x=decade_median.iloc[:, 4],\n",
    "        name=decade_median.columns[4],\n",
    "        orientation=\"h\",\n",
    "    ),\n",
    "    row=2,\n",
    "    col=2,\n",
    ")\n",
    "\n",
    "fig.add_trace(\n",
    "    go.Bar(\n",
    "        y=decade_median.index,\n",
    "        x=decade_median.iloc[:, 5],\n",
    "        name=decade_median.columns[5],\n",
    "        orientation=\"h\",\n",
    "    ),\n",
    "    row=2,\n",
    "    col=3,\n",
    ")\n",
    "\n",
    "fig.add_trace(\n",
    "    go.Bar(\n",
    "        y=decade_median.index,\n",
    "        x=decade_median.iloc[:, 6],\n",
    "        name=decade_median.columns[6],\n",
    "        orientation=\"h\",\n",
    "    ),\n",
    "    row=3,\n",
    "    col=1,\n",
    ")\n",
    "\n",
    "fig.add_trace(\n",
    "    go.Bar(\n",
    "        y=decade_median.index,\n",
    "        x=decade_median.iloc[:, 7],\n",
    "        name=decade_median.columns[7],\n",
    "        orientation=\"h\",\n",
    "    ),\n",
    "    row=3,\n",
    "    col=2,\n",
    ")\n",
    "\n",
    "fig.add_trace(\n",
    "    go.Bar(\n",
    "        y=decade_median.index,\n",
    "        x=decade_median.iloc[:, 8],\n",
    "        name=decade_median.columns[8],\n",
    "        orientation=\"h\",\n",
    "    ),\n",
    "    row=3,\n",
    "    col=3,\n",
    ")\n",
    "\n",
    "fig.add_trace(\n",
    "    go.Bar(\n",
    "        y=decade_median.index,\n",
    "        x=decade_median.iloc[:, 9],\n",
    "        name=decade_median.columns[9],\n",
    "        orientation=\"h\",\n",
    "    ),\n",
    "    row=4,\n",
    "    col=1,\n",
    ")\n",
    "\n",
    "fig.add_trace(\n",
    "    go.Bar(\n",
    "        y=decade_median.index,\n",
    "        x=decade_median.iloc[:, 10],\n",
    "        name=decade_median.columns[10],\n",
    "        orientation=\"h\",\n",
    "    ),\n",
    "    row=4,\n",
    "    col=2,\n",
    ")\n",
    "\n",
    "fig.update_layout(\n",
    "    title={\"text\": \"Median Musical Values per Decade\", \"font\": {\"size\": 22}},\n",
    "    legend={\n",
    "        \"orientation\": \"v\",\n",
    "        \"yanchor\": \"top\",\n",
    "        \"y\": 0.2,\n",
    "        \"xanchor\": \"right\",\n",
    "        \"x\": 0.9,\n",
    "    },\n",
    "    margin={\"b\": 10, \"r\": 10},\n",
    "    height=980,\n",
    ")\n",
    "\n",
    "fig.show()\n",
    "\n",
    "del decade_median"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "explicit_count = (\n",
    "    df.groupby([\"decade\", \"explicit\"], as_index=False)[\"year\"]\n",
    "    .count()\n",
    "    .rename(columns={\"year\": \"count\"})\n",
    ")\n",
    "key_count = (\n",
    "    df.groupby([\"decade\", \"key\"], as_index=False)[\"year\"]\n",
    "    .count()\n",
    "    .rename(columns={\"year\": \"count\"})\n",
    ")\n",
    "mode_count = (\n",
    "    df.groupby([\"decade\", \"mode\"], as_index=False)[\"year\"]\n",
    "    .count()\n",
    "    .rename(columns={\"year\": \"count\"})\n",
    ")\n",
    "\n",
    "fig = px.histogram(\n",
    "    data_frame=explicit_count,\n",
    "    x=\"decade\",\n",
    "    y=\"count\",\n",
    "    color=\"explicit\",\n",
    "    histfunc=\"sum\",\n",
    "    color_discrete_sequence=px.colors.qualitative.Pastel,\n",
    "    text_auto=True,\n",
    ")\n",
    "fig.update_layout(\n",
    "    title={\"text\": \"Explicit Count per Decade\", \"font\": {\"size\": 24}},\n",
    "    bargap=0.2,\n",
    "    bargroupgap=0.1,\n",
    "    barmode=\"group\",\n",
    "    xaxis_title=\"Decade\",\n",
    "    yaxis_title=\"Count\",\n",
    ")\n",
    "fig.show()\n",
    "\n",
    "fig = px.histogram(\n",
    "    data_frame=mode_count,\n",
    "    x=\"decade\",\n",
    "    y=\"count\",\n",
    "    color=\"mode\",\n",
    "    histfunc=\"sum\",\n",
    "    color_discrete_sequence=px.colors.qualitative.Pastel,\n",
    "    text_auto=True,\n",
    ")\n",
    "fig.update_layout(\n",
    "    title={\"text\": \"Mode Count per Decade\", \"font\": {\"size\": 24}},\n",
    "    bargap=0.2,\n",
    "    bargroupgap=0.1,\n",
    "    barmode=\"group\",\n",
    "    xaxis_title=\"Decade\",\n",
    "    yaxis_title=\"Count\",\n",
    ")\n",
    "fig.show()\n",
    "\n",
    "fig = px.histogram(\n",
    "    data_frame=key_count,\n",
    "    x=\"decade\",\n",
    "    y=\"count\",\n",
    "    color=\"key\",\n",
    "    histfunc=\"sum\",\n",
    "    color_discrete_sequence=px.colors.qualitative.Pastel,\n",
    "    text_auto=True,\n",
    ")\n",
    "fig.update_layout(\n",
    "    title={\"text\": \"Key Count per Decade\", \"font\": {\"size\": 24}},\n",
    "    bargap=0.2,\n",
    "    bargroupgap=0.1,\n",
    "    barmode=\"stack\",\n",
    "    xaxis_title=\"Decade\",\n",
    "    yaxis_title=\"Count\",\n",
    ")\n",
    "fig.show()\n",
    "\n",
    "del (mode_count, key_count, explicit_count)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "cols = [\n",
    "    \"valence\",\n",
    "    \"acousticness\",\n",
    "    \"danceability\",\n",
    "    \"duration_min\",\n",
    "    \"energy\",\n",
    "    \"instrumentalness\",\n",
    "    \"liveness\",\n",
    "    \"loudness\",\n",
    "    \"year\",\n",
    "    \"speechiness\",\n",
    "    \"tempo\",\n",
    "]\n",
    "\n",
    "for col in cols:\n",
    "\n",
    "    fig = px.scatter(\n",
    "        data_frame=df,\n",
    "        x=col,\n",
    "        y=\"popularity\",\n",
    "        trendline=\"ols\",\n",
    "        trendline_color_override=\"#A6E3A1\",\n",
    "    )\n",
    "    fig.update_traces(marker={\"opacity\": 0.3, \"size\": 3, \"color\": \"#B4BEFE\"})\n",
    "    fig.update_layout(title={\"text\": f\"{col} vs popularity\", \"font\": {\"size\": 24}})\n",
    "    fig.show()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Header 1\n",
    "\n",
    "## Header 2\n",
    "\n",
    "### Header 3.1"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "cols = [\n",
    "    \"valence\",\n",
    "    \"acousticness\",\n",
    "    \"danceability\",\n",
    "    \"duration_min\",\n",
    "    \"energy\",\n",
    "    \"instrumentalness\",\n",
    "    \"liveness\",\n",
    "    \"loudness\",\n",
    "    \"year\",\n",
    "    \"speechiness\",\n",
    "    \"tempo\",\n",
    "]\n",
    "\n",
    "plt.figure(figsize=(15, 10))\n",
    "\n",
    "for i, col in enumerate(cols):\n",
    "    ax = plt.subplot(3, 4, i + 1)\n",
    "    sns.regplot(\n",
    "        data=df,\n",
    "        x=\"popularity\",\n",
    "        y=col,\n",
    "        ax=ax,\n",
    "        scatter_kws={\"alpha\": 0.5},\n",
    "        line_kws={\"color\": \"#F38BA8\"},\n",
    "    )\n",
    "\n",
    "plt.tight_layout()\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "cols = [\n",
    "    \"valence\",\n",
    "    \"acousticness\",\n",
    "    \"danceability\",\n",
    "    \"duration_min\",\n",
    "    \"energy\",\n",
    "    \"instrumentalness\",\n",
    "    \"liveness\",\n",
    "    \"loudness\",\n",
    "    \"year\",\n",
    "    \"speechiness\",\n",
    "    \"tempo\",\n",
    "    \"popularity\",\n",
    "]\n",
    "\n",
    "plt.figure(figsize=(10, 7))\n",
    "mask = np.triu(np.ones_like(df[cols].corr()))\n",
    "sns.heatmap(\n",
    "    df[cols].corr(),\n",
    "    annot=True,\n",
    "    fmt=\".2f\",\n",
    "    cmap=\"Blues\",\n",
    "    mask=mask,\n",
    ")\n",
    "plt.grid(visible=False)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "df[\"first_artist\"] = (\n",
    "    df[\"artists\"]\n",
    "    .apply(lambda x: str(x).split(\"x\")[0])\n",
    "    .apply(lambda x: str(x).replace(\"[\", \"\"))\n",
    "    .apply(lambda x: str(x).replace(\"]\", \"\"))\n",
    "    .apply(lambda x: str(x).replace(\"'\", \"\"))\n",
    ")\n",
    "df = df.drop(\"artists\", axis=1)\n",
    "df[\"first_artist\"] = df[\"first_artist\"].apply(lambda x: str(x).split(\",\")[0])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "popularity_check = (\n",
    "    df.groupby([\"first_artist\"], as_index=False)[\"popularity\"]\n",
    "    .agg({\"mean\", \"count\", \"median\"})\n",
    "    .sort_values(by=\"mean\", ascending=False)\n",
    "    .reset_index(drop=True)\n",
    ")\n",
    "\n",
    "popularity_check = popularity_check.drop(16091, axis=0)\n",
    "popularity_check = popularity_check.drop(16086, axis=0)\n",
    "popularity_check = popularity_check.drop(16429, axis=0)\n",
    "\n",
    "to_drop = popularity_check[popularity_check[\"count\"] <= 45].index\n",
    "popularity_check = popularity_check.drop(to_drop)\n",
    "popularity_check = popularity_check.sort_values(by=\"mean\", ascending=False).head(50)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Header 1\n",
    "\n",
    "## Header 2\n",
    "\n",
    "### Header 3.1"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "top_50_artists = pd.DataFrame()\n",
    "\n",
    "for i in popularity_check[\"first_artist\"].unique():\n",
    "    artist = df.query(\"first_artist == @i\")\n",
    "    top_50_artists = pd.concat([top_50_artists, artist], axis=0)\n",
    "\n",
    "top_50_artists = top_50_artists.reset_index(drop=True)\n",
    "top_50_artists.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "plt.figure(figsize=(12, 8))\n",
    "(\n",
    "    top_50_artists[\"first_artist\"]\n",
    "    .value_counts()\n",
    "    .sort_values(ascending=True)\n",
    "    .plot(kind=\"barh\")\n",
    ")\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "top_50_artists[\"decade\"].value_counts().sort_values(ascending=True).plot(kind=\"barh\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "cols = [\n",
    "    \"valence\",\n",
    "    \"acousticness\",\n",
    "    \"danceability\",\n",
    "    \"duration_min\",\n",
    "    \"energy\",\n",
    "    \"instrumentalness\",\n",
    "    \"liveness\",\n",
    "    \"loudness\",\n",
    "    \"year\",\n",
    "    \"speechiness\",\n",
    "    \"tempo\",\n",
    "]\n",
    "\n",
    "plt.figure(figsize=(15, 10))\n",
    "\n",
    "for i, col in enumerate(cols):\n",
    "    ax = plt.subplot(3, 4, i + 1)\n",
    "    sns.kdeplot(data=top_50_artists, x=col, hue=\"first_artist\", legend=False)\n",
    "\n",
    "plt.tight_layout()\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Header 1\n",
    "\n",
    "## Header 2\n",
    "\n",
    "### Header 3.1"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "import pandas as pd\n",
    "import numpy as np\n",
    "import seaborn as sns\n",
    "import matplotlib.pyplot as plt\n",
    "import matplotlib as mpl\n",
    "import mplcatppuccin\n",
    "import plotly.express as px\n",
    "import plotly.graph_objects as go\n",
    "from plotly.subplots import make_subplots\n",
    "import plotly.figure_factory as ff\n",
    "import warnings\n",
    "import plotly.io as pio\n",
    "\n",
    "warnings.filterwarnings('ignore')\n",
    "\n",
    "pio.renderers.default = 'notebook_connected'\n",
    "pio.templates.default = 'plotly_dark'\n",
    "\n",
    "\n",
    "%matplotlib inline\n",
    "%config InlineBackend.figure_format = 'retina'\n",
    "pd.set_option('display.max_columns', None)\n",
    "pd.set_option('display.precision', 2)\n",
    "pd.set_option('display.colheader_justify', 'left')\n",
    "\n",
    "mpl.rc(\n",
    "    'figure',\n",
    "    autolayout=True,\n",
    "    titlesize=18\n",
    ")\n",
    "\n",
    "mpl.style.use(['ggplot', 'mocha'])\n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Header 3.2\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "df = pd.read_csv(\n",
    "    \"data.csv\",\n",
    "    parse_dates=[\"release_date\"],\n",
    ")\n",
    "df.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "map_key = {\n",
    "    0: \"C\",\n",
    "    1: \"C#\",\n",
    "    2: \"D\",\n",
    "    3: \"D#\",\n",
    "    4: \"E\",\n",
    "    5: \"F\",\n",
    "    6: \"F#\",\n",
    "    7: \"G\",\n",
    "    8: \"G#\",\n",
    "    9: \"A\",\n",
    "    10: \"A#\",\n",
    "    11: \"B\",\n",
    "}\n",
    "\n",
    "map_mode = {1: \"Major\", 0: \"Minor\"}\n",
    "\n",
    "df[\"mode\"] = df[\"mode\"].map(map_mode)\n",
    "df[\"key\"] = df[\"key\"].map(map_key)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "check_dups = df[[\"artists\", \"name\"]]\n",
    "dups = check_dups[check_dups.duplicated()].index"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "print(\"Before dropping duplicated:\", df.shape)\n",
    "df = df.drop(dups)\n",
    "print(\"After dropping duplicated:\", df.shape)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Header 1.3\n",
    "\n",
    "## Header 2.3\n",
    "\n",
    "### Header 3.5"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "df[\"duration_ms\"] = df[\"duration_ms\"] / 60_000\n",
    "df = df.rename(columns={\"duration_ms\": \"duration_min\"})\n",
    "df.head()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Header 1.4\n",
    "\n",
    "## Header 2.4\n",
    "\n",
    "### Header 3.5"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "df = df.drop([\"release_date\", \"id\"], axis=1)\n",
    "df.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "def fun_subplots_plotly(df, col):\n",
    "\n",
    "    mean_val = df[col].mean()\n",
    "    median_val = df[col].median()\n",
    "    fig = make_subplots(rows=1, cols=2, column_widths=[0.75, 0.25])\n",
    "\n",
    "    fig.add_trace(\n",
    "        go.Histogram(\n",
    "            x=df[col], name=f\"Histogram {col}\", marker={\"color\": \"#EBA0AC\"}, nbinsx=50\n",
    "        ),\n",
    "        row=1,\n",
    "        col=1,\n",
    "    )\n",
    "\n",
    "    fig.add_shape(\n",
    "        type=\"line\",\n",
    "        xref=\"paper\",\n",
    "        yref=\"y\",\n",
    "        x0=-1,\n",
    "        x1=1,\n",
    "        y0=mean_val,\n",
    "        y1=mean_val,\n",
    "        row=1,\n",
    "        col=2,\n",
    "        line={\"color\": \"#A6E3A1\", \"width\": 3, \"dash\": \"dot\"},\n",
    "    )\n",
    "\n",
    "    fig.add_shape(\n",
    "        type=\"line\",\n",
    "        xref=\"paper\",\n",
    "        yref=\"y\",\n",
    "        x0=-1,\n",
    "        x1=1,\n",
    "        y0=median_val,\n",
    "        y1=median_val,\n",
    "        row=1,\n",
    "        col=2,\n",
    "        line={\"color\": \"#CBA6F7\", \"width\": 3, \"dash\": \"dot\"},\n",
    "    )\n",
    "\n",
    "    fig.add_annotation(\n",
    "        xref=\"paper\",\n",
    "        x=-0.7,\n",
    "        y=mean_val,\n",
    "        showarrow=True,\n",
    "        arrowhead=2,\n",
    "        text=f\"Mean = {mean_val:.2f}\",\n",
    "        row=1,\n",
    "        col=2,\n",
    "    )\n",
    "\n",
    "    fig.add_annotation(\n",
    "        xref=\"paper\",\n",
    "        x=0.7,\n",
    "        y=median_val,\n",
    "        showarrow=True,\n",
    "        arrowhead=2,\n",
    "        text=f\"Median = {median_val:.2f}\",\n",
    "        row=1,\n",
    "        col=2,\n",
    "    )\n",
    "\n",
    "    fig.add_trace(\n",
    "        go.Box(y=df[col], name=f\"Boxplot {col}\", marker={\"color\": \"#F9E2AF\"}),\n",
    "        row=1,\n",
    "        col=2,\n",
    "    )\n",
    "\n",
    "    fig.update_layout(\n",
    "        title={\"text\": f\"Distribution Plot {col}\", \"font\": {\"size\": 24}},\n",
    "        legend={\n",
    "            \"orientation\": \"h\",\n",
    "            \"yanchor\": \"bottom\",\n",
    "            \"y\": 1.02,\n",
    "            \"xanchor\": \"right\",\n",
    "            \"x\": 1,\n",
    "        },\n",
    "    )\n",
    "    fig.update_yaxes(title_text=\"Count\", row=1, col=1)\n",
    "    fig.update_yaxes(title_text=f\"{col}\", row=1, col=2)\n",
    "    fig.update_xaxes(title_text=f\"{col}\", row=1, col=1)\n",
    "    fig.update_xaxes(title_text=\"\", row=1, col=2)\n",
    "    fig.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "music_vals = [\n",
    "    \"valence\",\n",
    "    \"acousticness\",\n",
    "    \"danceability\",\n",
    "    \"duration_min\",\n",
    "    \"energy\",\n",
    "    \"instrumentalness\",\n",
    "    \"liveness\",\n",
    "    \"loudness\",\n",
    "    \"popularity\",\n",
    "    \"speechiness\",\n",
    "    \"tempo\",\n",
    "]\n",
    "\n",
    "for col in music_vals:\n",
    "    fun_subplots_plotly(df, col)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Header 1.2\n",
    "\n",
    "## Header 2.2\n",
    "\n",
    "### Header 3.4"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "bins = pd.IntervalIndex.from_breaks(\n",
    "    [1920, 1930, 1940, 1950, 1960, 1970, 1980, 1990, 2000, 2010, 2020]\n",
    ")\n",
    "\n",
    "df[\"decade\"] = pd.cut(df[\"year\"], bins).astype(\"str\")\n",
    "\n",
    "map_decade = {\n",
    "    \"(1920, 1930]\": \"1920s\",\n",
    "    \"(1930, 1940]\": \"1930s\",\n",
    "    \"(1940, 1950]\": \"1940s\",\n",
    "    \"(1950, 1960]\": \"1950s\",\n",
    "    \"(1960, 1970]\": \"1960s\",\n",
    "    \"(1970, 1980]\": \"1970s\",\n",
    "    \"(1980, 1990]\": \"1980s\",\n",
    "    \"(1990, 2000]\": \"1990s\",\n",
    "    \"(2000, 2010]\": \"2000s\",\n",
    "    \"(2010, 2020]\": \"2010s\",\n",
    "}\n",
    "\n",
    "df[\"decade\"] = df[\"decade\"].map(map_decade)\n",
    "\n",
    "df.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "decade_counts = (\n",
    "    df[\"decade\"].value_counts().reset_index().sort_values(by=\"decade\", ascending=True)\n",
    ")\n",
    "\n",
    "fig = px.bar(\n",
    "    data_frame=decade_counts,\n",
    "    y=\"decade\",\n",
    "    x=\"count\",\n",
    "    color=\"count\",\n",
    "    color_continuous_scale=px.colors.sequential.Sunset,\n",
    "    text_auto=True,\n",
    ")\n",
    "\n",
    "fig.update_layout(\n",
    "    title={\"text\": \"Count of songs per decade\", \"font\": {\"size\": 24}},\n",
    "    coloraxis_colorbar={\n",
    "        \"title\": \"Count\",\n",
    "        \"thicknessmode\": \"pixels\",\n",
    "        \"thickness\": 20,\n",
    "        \"lenmode\": \"pixels\",\n",
    "        \"len\": 500,\n",
    "        \"yanchor\": \"top\",\n",
    "        \"xanchor\": \"right\",\n",
    "        \"y\": 1.15,\n",
    "        \"x\": 0.95,\n",
    "        \"orientation\": \"h\",\n",
    "    },\n",
    "    margin={\"r\": 10},\n",
    ")\n",
    "\n",
    "fig.update_xaxes(title=\"Count\")\n",
    "fig.update_yaxes(title=\"Decades\")\n",
    "fig.show()\n",
    "\n",
    "del decade_counts"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "df = df.query(\"duration_min <= 5\")"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Header 1.2\n",
    "\n",
    "## Header 2.2\n",
    "\n",
    "### Header 3.4"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "decade_counts = (\n",
    "    df[\"decade\"].value_counts().reset_index().sort_values(by=\"decade\", ascending=True)\n",
    ")\n",
    "\n",
    "fig = px.bar(\n",
    "    data_frame=decade_counts,\n",
    "    y=\"decade\",\n",
    "    x=\"count\",\n",
    "    color=\"count\",\n",
    "    color_continuous_scale=px.colors.sequential.Sunset,\n",
    "    text_auto=True,\n",
    ")\n",
    "\n",
    "fig.update_layout(\n",
    "    title={\"text\": \"Count of songs per decade (< 5min)\", \"font\": {\"size\": 24}},\n",
    "    coloraxis_colorbar={\n",
    "        \"title\": \"Count\",\n",
    "        \"thicknessmode\": \"pixels\",\n",
    "        \"thickness\": 20,\n",
    "        \"lenmode\": \"pixels\",\n",
    "        \"len\": 500,\n",
    "        \"yanchor\": \"top\",\n",
    "        \"xanchor\": \"right\",\n",
    "        \"y\": 1.15,\n",
    "        \"x\": 0.95,\n",
    "        \"orientation\": \"h\",\n",
    "    },\n",
    "    margin={\"r\": 10},\n",
    ")\n",
    "\n",
    "fig.update_xaxes(title=\"Count\")\n",
    "fig.update_yaxes(title=\"Decades\")\n",
    "fig.show()\n",
    "\n",
    "del decade_counts"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "cols = [\n",
    "    \"valence\",\n",
    "    \"acousticness\",\n",
    "    \"danceability\",\n",
    "    \"duration_min\",\n",
    "    \"energy\",\n",
    "    \"instrumentalness\",\n",
    "    \"liveness\",\n",
    "    \"loudness\",\n",
    "    \"popularity\",\n",
    "    \"speechiness\",\n",
    "    \"tempo\",\n",
    "]\n",
    "for col in cols:\n",
    "    fig = px.histogram(\n",
    "        data_frame=df,\n",
    "        x=col,\n",
    "        color=\"decade\",\n",
    "        color_discrete_sequence=px.colors.qualitative.Light24,\n",
    "    )\n",
    "    fig.update_traces(opacity=0.7)\n",
    "    fig.update_layout(\n",
    "        bargap=0.1,\n",
    "        bargroupgap=0.05,\n",
    "        barmode=\"stack\",\n",
    "        title={\"text\": f\"Histogram of {col} per decade\", \"font\": {\"size\": 24}},\n",
    "        legend={\"title\": \"Decade\"},\n",
    "    )\n",
    "    fig.update_yaxes(title=\"Count\")\n",
    "    fig.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "decade_mean = df.groupby(\"decade\")[cols].mean()\n",
    "\n",
    "fig = make_subplots(\n",
    "    rows=4,\n",
    "    cols=3,\n",
    "    subplot_titles=(\n",
    "        decade_mean.columns[0],\n",
    "        decade_mean.columns[1],\n",
    "        decade_mean.columns[2],\n",
    "        decade_mean.columns[3],\n",
    "        decade_mean.columns[4],\n",
    "        decade_mean.columns[5],\n",
    "        decade_mean.columns[6],\n",
    "        decade_mean.columns[7],\n",
    "        decade_mean.columns[8],\n",
    "        decade_mean.columns[9],\n",
    "        decade_mean.columns[10],\n",
    "    ),\n",
    "    vertical_spacing=0.1,\n",
    ")\n",
    "\n",
    "fig.add_trace(\n",
    "    go.Bar(\n",
    "        y=decade_mean.index,\n",
    "        x=decade_mean.iloc[:, 0],\n",
    "        name=decade_mean.columns[0],\n",
    "        orientation=\"h\",\n",
    "    ),\n",
    "    row=1,\n",
    "    col=1,\n",
    ")\n",
    "\n",
    "fig.add_trace(\n",
    "    go.Bar(\n",
    "        y=decade_mean.index,\n",
    "        x=decade_mean.iloc[:, 1],\n",
    "        name=decade_mean.columns[1],\n",
    "        orientation=\"h\",\n",
    "    ),\n",
    "    row=1,\n",
    "    col=2,\n",
    ")\n",
    "\n",
    "fig.add_trace(\n",
    "    go.Bar(\n",
    "        y=decade_mean.index,\n",
    "        x=decade_mean.iloc[:, 2],\n",
    "        name=decade_mean.columns[2],\n",
    "        orientation=\"h\",\n",
    "    ),\n",
    "    row=1,\n",
    "    col=3,\n",
    ")\n",
    "\n",
    "fig.add_trace(\n",
    "    go.Bar(\n",
    "        y=decade_mean.index,\n",
    "        x=decade_mean.iloc[:, 3],\n",
    "        name=decade_mean.columns[3],\n",
    "        orientation=\"h\",\n",
    "    ),\n",
    "    row=2,\n",
    "    col=1,\n",
    ")\n",
    "\n",
    "fig.add_trace(\n",
    "    go.Bar(\n",
    "        y=decade_mean.index,\n",
    "        x=decade_mean.iloc[:, 4],\n",
    "        name=decade_mean.columns[4],\n",
    "        orientation=\"h\",\n",
    "    ),\n",
    "    row=2,\n",
    "    col=2,\n",
    ")\n",
    "\n",
    "fig.add_trace(\n",
    "    go.Bar(\n",
    "        y=decade_mean.index,\n",
    "        x=decade_mean.iloc[:, 5],\n",
    "        name=decade_mean.columns[5],\n",
    "        orientation=\"h\",\n",
    "    ),\n",
    "    row=2,\n",
    "    col=3,\n",
    ")\n",
    "\n",
    "fig.add_trace(\n",
    "    go.Bar(\n",
    "        y=decade_mean.index,\n",
    "        x=decade_mean.iloc[:, 6],\n",
    "        name=decade_mean.columns[6],\n",
    "        orientation=\"h\",\n",
    "    ),\n",
    "    row=3,\n",
    "    col=1,\n",
    ")\n",
    "\n",
    "fig.add_trace(\n",
    "    go.Bar(\n",
    "        y=decade_mean.index,\n",
    "        x=decade_mean.iloc[:, 7],\n",
    "        name=decade_mean.columns[7],\n",
    "        orientation=\"h\",\n",
    "    ),\n",
    "    row=3,\n",
    "    col=2,\n",
    ")\n",
    "\n",
    "fig.add_trace(\n",
    "    go.Bar(\n",
    "        y=decade_mean.index,\n",
    "        x=decade_mean.iloc[:, 8],\n",
    "        name=decade_mean.columns[8],\n",
    "        orientation=\"h\",\n",
    "    ),\n",
    "    row=3,\n",
    "    col=3,\n",
    ")\n",
    "\n",
    "fig.add_trace(\n",
    "    go.Bar(\n",
    "        y=decade_mean.index,\n",
    "        x=decade_mean.iloc[:, 9],\n",
    "        name=decade_mean.columns[9],\n",
    "        orientation=\"h\",\n",
    "    ),\n",
    "    row=4,\n",
    "    col=1,\n",
    ")\n",
    "\n",
    "fig.add_trace(\n",
    "    go.Bar(\n",
    "        y=decade_mean.index,\n",
    "        x=decade_mean.iloc[:, 10],\n",
    "        name=decade_mean.columns[10],\n",
    "        orientation=\"h\",\n",
    "    ),\n",
    "    row=4,\n",
    "    col=2,\n",
    ")\n",
    "\n",
    "fig.update_layout(\n",
    "    title={\"text\": \"Mean Musical Values per Decade\", \"font\": {\"size\": 22}},\n",
    "    legend={\n",
    "        \"orientation\": \"v\",\n",
    "        \"yanchor\": \"top\",\n",
    "        \"y\": 0.2,\n",
    "        \"xanchor\": \"right\",\n",
    "        \"x\": 0.9,\n",
    "    },\n",
    "    margin={\"b\": 10, \"r\": 10},\n",
    "    height=980,\n",
    ")\n",
    "\n",
    "fig.show()\n",
    "\n",
    "del decade_mean"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "decade_median = df.groupby(\"decade\")[cols].median()\n",
    "\n",
    "fig = make_subplots(\n",
    "    rows=4,\n",
    "    cols=3,\n",
    "    subplot_titles=(\n",
    "        decade_median.columns[0],\n",
    "        decade_median.columns[1],\n",
    "        decade_median.columns[2],\n",
    "        decade_median.columns[3],\n",
    "        decade_median.columns[4],\n",
    "        decade_median.columns[5],\n",
    "        decade_median.columns[6],\n",
    "        decade_median.columns[7],\n",
    "        decade_median.columns[8],\n",
    "        decade_median.columns[9],\n",
    "        decade_median.columns[10],\n",
    "    ),\n",
    "    vertical_spacing=0.1,\n",
    ")\n",
    "\n",
    "fig.add_trace(\n",
    "    go.Bar(\n",
    "        y=decade_median.index,\n",
    "        x=decade_median.iloc[:, 0],\n",
    "        name=decade_median.columns[0],\n",
    "        orientation=\"h\",\n",
    "    ),\n",
    "    row=1,\n",
    "    col=1,\n",
    ")\n",
    "\n",
    "fig.add_trace(\n",
    "    go.Bar(\n",
    "        y=decade_median.index,\n",
    "        x=decade_median.iloc[:, 1],\n",
    "        name=decade_median.columns[1],\n",
    "        orientation=\"h\",\n",
    "    ),\n",
    "    row=1,\n",
    "    col=2,\n",
    ")\n",
    "\n",
    "fig.add_trace(\n",
    "    go.Bar(\n",
    "        y=decade_median.index,\n",
    "        x=decade_median.iloc[:, 2],\n",
    "        name=decade_median.columns[2],\n",
    "        orientation=\"h\",\n",
    "    ),\n",
    "    row=1,\n",
    "    col=3,\n",
    ")\n",
    "\n",
    "fig.add_trace(\n",
    "    go.Bar(\n",
    "        y=decade_median.index,\n",
    "        x=decade_median.iloc[:, 3],\n",
    "        name=decade_median.columns[3],\n",
    "        orientation=\"h\",\n",
    "    ),\n",
    "    row=2,\n",
    "    col=1,\n",
    ")\n",
    "\n",
    "fig.add_trace(\n",
    "    go.Bar(\n",
    "        y=decade_median.index,\n",
    "        x=decade_median.iloc[:, 4],\n",
    "        name=decade_median.columns[4],\n",
    "        orientation=\"h\",\n",
    "    ),\n",
    "    row=2,\n",
    "    col=2,\n",
    ")\n",
    "\n",
    "fig.add_trace(\n",
    "    go.Bar(\n",
    "        y=decade_median.index,\n",
    "        x=decade_median.iloc[:, 5],\n",
    "        name=decade_median.columns[5],\n",
    "        orientation=\"h\",\n",
    "    ),\n",
    "    row=2,\n",
    "    col=3,\n",
    ")\n",
    "\n",
    "fig.add_trace(\n",
    "    go.Bar(\n",
    "        y=decade_median.index,\n",
    "        x=decade_median.iloc[:, 6],\n",
    "        name=decade_median.columns[6],\n",
    "        orientation=\"h\",\n",
    "    ),\n",
    "    row=3,\n",
    "    col=1,\n",
    ")\n",
    "\n",
    "fig.add_trace(\n",
    "    go.Bar(\n",
    "        y=decade_median.index,\n",
    "        x=decade_median.iloc[:, 7],\n",
    "        name=decade_median.columns[7],\n",
    "        orientation=\"h\",\n",
    "    ),\n",
    "    row=3,\n",
    "    col=2,\n",
    ")\n",
    "\n",
    "fig.add_trace(\n",
    "    go.Bar(\n",
    "        y=decade_median.index,\n",
    "        x=decade_median.iloc[:, 8],\n",
    "        name=decade_median.columns[8],\n",
    "        orientation=\"h\",\n",
    "    ),\n",
    "    row=3,\n",
    "    col=3,\n",
    ")\n",
    "\n",
    "fig.add_trace(\n",
    "    go.Bar(\n",
    "        y=decade_median.index,\n",
    "        x=decade_median.iloc[:, 9],\n",
    "        name=decade_median.columns[9],\n",
    "        orientation=\"h\",\n",
    "    ),\n",
    "    row=4,\n",
    "    col=1,\n",
    ")\n",
    "\n",
    "fig.add_trace(\n",
    "    go.Bar(\n",
    "        y=decade_median.index,\n",
    "        x=decade_median.iloc[:, 10],\n",
    "        name=decade_median.columns[10],\n",
    "        orientation=\"h\",\n",
    "    ),\n",
    "    row=4,\n",
    "    col=2,\n",
    ")\n",
    "\n",
    "fig.update_layout(\n",
    "    title={\"text\": \"Median Musical Values per Decade\", \"font\": {\"size\": 22}},\n",
    "    legend={\n",
    "        \"orientation\": \"v\",\n",
    "        \"yanchor\": \"top\",\n",
    "        \"y\": 0.2,\n",
    "        \"xanchor\": \"right\",\n",
    "        \"x\": 0.9,\n",
    "    },\n",
    "    margin={\"b\": 10, \"r\": 10},\n",
    "    height=980,\n",
    ")\n",
    "\n",
    "fig.show()\n",
    "\n",
    "del decade_median"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "explicit_count = (\n",
    "    df.groupby([\"decade\", \"explicit\"], as_index=False)[\"year\"]\n",
    "    .count()\n",
    "    .rename(columns={\"year\": \"count\"})\n",
    ")\n",
    "key_count = (\n",
    "    df.groupby([\"decade\", \"key\"], as_index=False)[\"year\"]\n",
    "    .count()\n",
    "    .rename(columns={\"year\": \"count\"})\n",
    ")\n",
    "mode_count = (\n",
    "    df.groupby([\"decade\", \"mode\"], as_index=False)[\"year\"]\n",
    "    .count()\n",
    "    .rename(columns={\"year\": \"count\"})\n",
    ")\n",
    "\n",
    "fig = px.histogram(\n",
    "    data_frame=explicit_count,\n",
    "    x=\"decade\",\n",
    "    y=\"count\",\n",
    "    color=\"explicit\",\n",
    "    histfunc=\"sum\",\n",
    "    color_discrete_sequence=px.colors.qualitative.Pastel,\n",
    "    text_auto=True,\n",
    ")\n",
    "fig.update_layout(\n",
    "    title={\"text\": \"Explicit Count per Decade\", \"font\": {\"size\": 24}},\n",
    "    bargap=0.2,\n",
    "    bargroupgap=0.1,\n",
    "    barmode=\"group\",\n",
    "    xaxis_title=\"Decade\",\n",
    "    yaxis_title=\"Count\",\n",
    ")\n",
    "fig.show()\n",
    "\n",
    "fig = px.histogram(\n",
    "    data_frame=mode_count,\n",
    "    x=\"decade\",\n",
    "    y=\"count\",\n",
    "    color=\"mode\",\n",
    "    histfunc=\"sum\",\n",
    "    color_discrete_sequence=px.colors.qualitative.Pastel,\n",
    "    text_auto=True,\n",
    ")\n",
    "fig.update_layout(\n",
    "    title={\"text\": \"Mode Count per Decade\", \"font\": {\"size\": 24}},\n",
    "    bargap=0.2,\n",
    "    bargroupgap=0.1,\n",
    "    barmode=\"group\",\n",
    "    xaxis_title=\"Decade\",\n",
    "    yaxis_title=\"Count\",\n",
    ")\n",
    "fig.show()\n",
    "\n",
    "fig = px.histogram(\n",
    "    data_frame=key_count,\n",
    "    x=\"decade\",\n",
    "    y=\"count\",\n",
    "    color=\"key\",\n",
    "    histfunc=\"sum\",\n",
    "    color_discrete_sequence=px.colors.qualitative.Pastel,\n",
    "    text_auto=True,\n",
    ")\n",
    "fig.update_layout(\n",
    "    title={\"text\": \"Key Count per Decade\", \"font\": {\"size\": 24}},\n",
    "    bargap=0.2,\n",
    "    bargroupgap=0.1,\n",
    "    barmode=\"stack\",\n",
    "    xaxis_title=\"Decade\",\n",
    "    yaxis_title=\"Count\",\n",
    ")\n",
    "fig.show()\n",
    "\n",
    "del (mode_count, key_count, explicit_count)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "cols = [\n",
    "    \"valence\",\n",
    "    \"acousticness\",\n",
    "    \"danceability\",\n",
    "    \"duration_min\",\n",
    "    \"energy\",\n",
    "    \"instrumentalness\",\n",
    "    \"liveness\",\n",
    "    \"loudness\",\n",
    "    \"year\",\n",
    "    \"speechiness\",\n",
    "    \"tempo\",\n",
    "]\n",
    "\n",
    "for col in cols:\n",
    "\n",
    "    fig = px.scatter(\n",
    "        data_frame=df,\n",
    "        x=col,\n",
    "        y=\"popularity\",\n",
    "        trendline=\"ols\",\n",
    "        trendline_color_override=\"#A6E3A1\",\n",
    "    )\n",
    "    fig.update_traces(marker={\"opacity\": 0.3, \"size\": 3, \"color\": \"#B4BEFE\"})\n",
    "    fig.update_layout(title={\"text\": f\"{col} vs popularity\", \"font\": {\"size\": 24}})\n",
    "    fig.show()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Header 1\n",
    "\n",
    "## Header 2\n",
    "\n",
    "### Header 3.1"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "cols = [\n",
    "    \"valence\",\n",
    "    \"acousticness\",\n",
    "    \"danceability\",\n",
    "    \"duration_min\",\n",
    "    \"energy\",\n",
    "    \"instrumentalness\",\n",
    "    \"liveness\",\n",
    "    \"loudness\",\n",
    "    \"year\",\n",
    "    \"speechiness\",\n",
    "    \"tempo\",\n",
    "]\n",
    "\n",
    "plt.figure(figsize=(15, 10))\n",
    "\n",
    "for i, col in enumerate(cols):\n",
    "    ax = plt.subplot(3, 4, i + 1)\n",
    "    sns.regplot(\n",
    "        data=df,\n",
    "        x=\"popularity\",\n",
    "        y=col,\n",
    "        ax=ax,\n",
    "        scatter_kws={\"alpha\": 0.5},\n",
    "        line_kws={\"color\": \"#F38BA8\"},\n",
    "    )\n",
    "\n",
    "plt.tight_layout()\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "cols = [\n",
    "    \"valence\",\n",
    "    \"acousticness\",\n",
    "    \"danceability\",\n",
    "    \"duration_min\",\n",
    "    \"energy\",\n",
    "    \"instrumentalness\",\n",
    "    \"liveness\",\n",
    "    \"loudness\",\n",
    "    \"year\",\n",
    "    \"speechiness\",\n",
    "    \"tempo\",\n",
    "    \"popularity\",\n",
    "]\n",
    "\n",
    "plt.figure(figsize=(10, 7))\n",
    "mask = np.triu(np.ones_like(df[cols].corr()))\n",
    "sns.heatmap(\n",
    "    df[cols].corr(),\n",
    "    annot=True,\n",
    "    fmt=\".2f\",\n",
    "    cmap=\"Blues\",\n",
    "    mask=mask,\n",
    ")\n",
    "plt.grid(visible=False)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "df[\"first_artist\"] = (\n",
    "    df[\"artists\"]\n",
    "    .apply(lambda x: str(x).split(\"x\")[0])\n",
    "    .apply(lambda x: str(x).replace(\"[\", \"\"))\n",
    "    .apply(lambda x: str(x).replace(\"]\", \"\"))\n",
    "    .apply(lambda x: str(x).replace(\"'\", \"\"))\n",
    ")\n",
    "df = df.drop(\"artists\", axis=1)\n",
    "df[\"first_artist\"] = df[\"first_artist\"].apply(lambda x: str(x).split(\",\")[0])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "popularity_check = (\n",
    "    df.groupby([\"first_artist\"], as_index=False)[\"popularity\"]\n",
    "    .agg({\"mean\", \"count\", \"median\"})\n",
    "    .sort_values(by=\"mean\", ascending=False)\n",
    "    .reset_index(drop=True)\n",
    ")\n",
    "\n",
    "popularity_check = popularity_check.drop(16091, axis=0)\n",
    "popularity_check = popularity_check.drop(16086, axis=0)\n",
    "popularity_check = popularity_check.drop(16429, axis=0)\n",
    "\n",
    "to_drop = popularity_check[popularity_check[\"count\"] <= 45].index\n",
    "popularity_check = popularity_check.drop(to_drop)\n",
    "popularity_check = popularity_check.sort_values(by=\"mean\", ascending=False).head(50)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Header 1\n",
    "\n",
    "## Header 2\n",
    "\n",
    "### Header 3.1"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "top_50_artists = pd.DataFrame()\n",
    "\n",
    "for i in popularity_check[\"first_artist\"].unique():\n",
    "    artist = df.query(\"first_artist == @i\")\n",
    "    top_50_artists = pd.concat([top_50_artists, artist], axis=0)\n",
    "\n",
    "top_50_artists = top_50_artists.reset_index(drop=True)\n",
    "top_50_artists.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "plt.figure(figsize=(12, 8))\n",
    "(\n",
    "    top_50_artists[\"first_artist\"]\n",
    "    .value_counts()\n",
    "    .sort_values(ascending=True)\n",
    "    .plot(kind=\"barh\")\n",
    ")\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "top_50_artists[\"decade\"].value_counts().sort_values(ascending=True).plot(kind=\"barh\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "cols = [\n",
    "    \"valence\",\n",
    "    \"acousticness\",\n",
    "    \"danceability\",\n",
    "    \"duration_min\",\n",
    "    \"energy\",\n",
    "    \"instrumentalness\",\n",
    "    \"liveness\",\n",
    "    \"loudness\",\n",
    "    \"year\",\n",
    "    \"speechiness\",\n",
    "    \"tempo\",\n",
    "]\n",
    "\n",
    "plt.figure(figsize=(15, 10))\n",
    "\n",
    "for i, col in enumerate(cols):\n",
    "    ax = plt.subplot(3, 4, i + 1)\n",
    "    sns.kdeplot(data=top_50_artists, x=col, hue=\"first_artist\", legend=False)\n",
    "\n",
    "plt.tight_layout()\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Header 1\n",
    "\n",
    "## Header 2\n",
    "\n",
    "### Header 3.1"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "import pandas as pd\n",
    "import numpy as np\n",
    "import seaborn as sns\n",
    "import matplotlib.pyplot as plt\n",
    "import matplotlib as mpl\n",
    "import mplcatppuccin\n",
    "import plotly.express as px\n",
    "import plotly.graph_objects as go\n",
    "from plotly.subplots import make_subplots\n",
    "import plotly.figure_factory as ff\n",
    "import warnings\n",
    "import plotly.io as pio\n",
    "\n",
    "warnings.filterwarnings('ignore')\n",
    "\n",
    "pio.renderers.default = 'notebook_connected'\n",
    "pio.templates.default = 'plotly_dark'\n",
    "\n",
    "\n",
    "%matplotlib inline\n",
    "%config InlineBackend.figure_format = 'retina'\n",
    "pd.set_option('display.max_columns', None)\n",
    "pd.set_option('display.precision', 2)\n",
    "pd.set_option('display.colheader_justify', 'left')\n",
    "\n",
    "mpl.rc(\n",
    "    'figure',\n",
    "    autolayout=True,\n",
    "    titlesize=18\n",
    ")\n",
    "\n",
    "mpl.style.use(['ggplot', 'mocha'])\n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Header 3.2\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "df = pd.read_csv(\n",
    "    \"data.csv\",\n",
    "    parse_dates=[\"release_date\"],\n",
    ")\n",
    "df.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "map_key = {\n",
    "    0: \"C\",\n",
    "    1: \"C#\",\n",
    "    2: \"D\",\n",
    "    3: \"D#\",\n",
    "    4: \"E\",\n",
    "    5: \"F\",\n",
    "    6: \"F#\",\n",
    "    7: \"G\",\n",
    "    8: \"G#\",\n",
    "    9: \"A\",\n",
    "    10: \"A#\",\n",
    "    11: \"B\",\n",
    "}\n",
    "\n",
    "map_mode = {1: \"Major\", 0: \"Minor\"}\n",
    "\n",
    "df[\"mode\"] = df[\"mode\"].map(map_mode)\n",
    "df[\"key\"] = df[\"key\"].map(map_key)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "check_dups = df[[\"artists\", \"name\"]]\n",
    "dups = check_dups[check_dups.duplicated()].index"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "print(\"Before dropping duplicated:\", df.shape)\n",
    "df = df.drop(dups)\n",
    "print(\"After dropping duplicated:\", df.shape)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Header 1.3\n",
    "\n",
    "## Header 2.3\n",
    "\n",
    "### Header 3.5"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "df[\"duration_ms\"] = df[\"duration_ms\"] / 60_000\n",
    "df = df.rename(columns={\"duration_ms\": \"duration_min\"})\n",
    "df.head()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Header 1.4\n",
    "\n",
    "## Header 2.4\n",
    "\n",
    "### Header 3.5"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "df = df.drop([\"release_date\", \"id\"], axis=1)\n",
    "df.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "def fun_subplots_plotly(df, col):\n",
    "\n",
    "    mean_val = df[col].mean()\n",
    "    median_val = df[col].median()\n",
    "    fig = make_subplots(rows=1, cols=2, column_widths=[0.75, 0.25])\n",
    "\n",
    "    fig.add_trace(\n",
    "        go.Histogram(\n",
    "            x=df[col], name=f\"Histogram {col}\", marker={\"color\": \"#EBA0AC\"}, nbinsx=50\n",
    "        ),\n",
    "        row=1,\n",
    "        col=1,\n",
    "    )\n",
    "\n",
    "    fig.add_shape(\n",
    "        type=\"line\",\n",
    "        xref=\"paper\",\n",
    "        yref=\"y\",\n",
    "        x0=-1,\n",
    "        x1=1,\n",
    "        y0=mean_val,\n",
    "        y1=mean_val,\n",
    "        row=1,\n",
    "        col=2,\n",
    "        line={\"color\": \"#A6E3A1\", \"width\": 3, \"dash\": \"dot\"},\n",
    "    )\n",
    "\n",
    "    fig.add_shape(\n",
    "        type=\"line\",\n",
    "        xref=\"paper\",\n",
    "        yref=\"y\",\n",
    "        x0=-1,\n",
    "        x1=1,\n",
    "        y0=median_val,\n",
    "        y1=median_val,\n",
    "        row=1,\n",
    "        col=2,\n",
    "        line={\"color\": \"#CBA6F7\", \"width\": 3, \"dash\": \"dot\"},\n",
    "    )\n",
    "\n",
    "    fig.add_annotation(\n",
    "        xref=\"paper\",\n",
    "        x=-0.7,\n",
    "        y=mean_val,\n",
    "        showarrow=True,\n",
    "        arrowhead=2,\n",
    "        text=f\"Mean = {mean_val:.2f}\",\n",
    "        row=1,\n",
    "        col=2,\n",
    "    )\n",
    "\n",
    "    fig.add_annotation(\n",
    "        xref=\"paper\",\n",
    "        x=0.7,\n",
    "        y=median_val,\n",
    "        showarrow=True,\n",
    "        arrowhead=2,\n",
    "        text=f\"Median = {median_val:.2f}\",\n",
    "        row=1,\n",
    "        col=2,\n",
    "    )\n",
    "\n",
    "    fig.add_trace(\n",
    "        go.Box(y=df[col], name=f\"Boxplot {col}\", marker={\"color\": \"#F9E2AF\"}),\n",
    "        row=1,\n",
    "        col=2,\n",
    "    )\n",
    "\n",
    "    fig.update_layout(\n",
    "        title={\"text\": f\"Distribution Plot {col}\", \"font\": {\"size\": 24}},\n",
    "        legend={\n",
    "            \"orientation\": \"h\",\n",
    "            \"yanchor\": \"bottom\",\n",
    "            \"y\": 1.02,\n",
    "            \"xanchor\": \"right\",\n",
    "            \"x\": 1,\n",
    "        },\n",
    "    )\n",
    "    fig.update_yaxes(title_text=\"Count\", row=1, col=1)\n",
    "    fig.update_yaxes(title_text=f\"{col}\", row=1, col=2)\n",
    "    fig.update_xaxes(title_text=f\"{col}\", row=1, col=1)\n",
    "    fig.update_xaxes(title_text=\"\", row=1, col=2)\n",
    "    fig.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "music_vals = [\n",
    "    \"valence\",\n",
    "    \"acousticness\",\n",
    "    \"danceability\",\n",
    "    \"duration_min\",\n",
    "    \"energy\",\n",
    "    \"instrumentalness\",\n",
    "    \"liveness\",\n",
    "    \"loudness\",\n",
    "    \"popularity\",\n",
    "    \"speechiness\",\n",
    "    \"tempo\",\n",
    "]\n",
    "\n",
    "for col in music_vals:\n",
    "    fun_subplots_plotly(df, col)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Header 1.2\n",
    "\n",
    "## Header 2.2\n",
    "\n",
    "### Header 3.4"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "bins = pd.IntervalIndex.from_breaks(\n",
    "    [1920, 1930, 1940, 1950, 1960, 1970, 1980, 1990, 2000, 2010, 2020]\n",
    ")\n",
    "\n",
    "df[\"decade\"] = pd.cut(df[\"year\"], bins).astype(\"str\")\n",
    "\n",
    "map_decade = {\n",
    "    \"(1920, 1930]\": \"1920s\",\n",
    "    \"(1930, 1940]\": \"1930s\",\n",
    "    \"(1940, 1950]\": \"1940s\",\n",
    "    \"(1950, 1960]\": \"1950s\",\n",
    "    \"(1960, 1970]\": \"1960s\",\n",
    "    \"(1970, 1980]\": \"1970s\",\n",
    "    \"(1980, 1990]\": \"1980s\",\n",
    "    \"(1990, 2000]\": \"1990s\",\n",
    "    \"(2000, 2010]\": \"2000s\",\n",
    "    \"(2010, 2020]\": \"2010s\",\n",
    "}\n",
    "\n",
    "df[\"decade\"] = df[\"decade\"].map(map_decade)\n",
    "\n",
    "df.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "decade_counts = (\n",
    "    df[\"decade\"].value_counts().reset_index().sort_values(by=\"decade\", ascending=True)\n",
    ")\n",
    "\n",
    "fig = px.bar(\n",
    "    data_frame=decade_counts,\n",
    "    y=\"decade\",\n",
    "    x=\"count\",\n",
    "    color=\"count\",\n",
    "    color_continuous_scale=px.colors.sequential.Sunset,\n",
    "    text_auto=True,\n",
    ")\n",
    "\n",
    "fig.update_layout(\n",
    "    title={\"text\": \"Count of songs per decade\", \"font\": {\"size\": 24}},\n",
    "    coloraxis_colorbar={\n",
    "        \"title\": \"Count\",\n",
    "        \"thicknessmode\": \"pixels\",\n",
    "        \"thickness\": 20,\n",
    "        \"lenmode\": \"pixels\",\n",
    "        \"len\": 500,\n",
    "        \"yanchor\": \"top\",\n",
    "        \"xanchor\": \"right\",\n",
    "        \"y\": 1.15,\n",
    "        \"x\": 0.95,\n",
    "        \"orientation\": \"h\",\n",
    "    },\n",
    "    margin={\"r\": 10},\n",
    ")\n",
    "\n",
    "fig.update_xaxes(title=\"Count\")\n",
    "fig.update_yaxes(title=\"Decades\")\n",
    "fig.show()\n",
    "\n",
    "del decade_counts"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "df = df.query(\"duration_min <= 5\")"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Header 1.2\n",
    "\n",
    "## Header 2.2\n",
    "\n",
    "### Header 3.4"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "decade_counts = (\n",
    "    df[\"decade\"].value_counts().reset_index().sort_values(by=\"decade\", ascending=True)\n",
    ")\n",
    "\n",
    "fig = px.bar(\n",
    "    data_frame=decade_counts,\n",
    "    y=\"decade\",\n",
    "    x=\"count\",\n",
    "    color=\"count\",\n",
    "    color_continuous_scale=px.colors.sequential.Sunset,\n",
    "    text_auto=True,\n",
    ")\n",
    "\n",
    "fig.update_layout(\n",
    "    title={\"text\": \"Count of songs per decade (< 5min)\", \"font\": {\"size\": 24}},\n",
    "    coloraxis_colorbar={\n",
    "        \"title\": \"Count\",\n",
    "        \"thicknessmode\": \"pixels\",\n",
    "        \"thickness\": 20,\n",
    "        \"lenmode\": \"pixels\",\n",
    "        \"len\": 500,\n",
    "        \"yanchor\": \"top\",\n",
    "        \"xanchor\": \"right\",\n",
    "        \"y\": 1.15,\n",
    "        \"x\": 0.95,\n",
    "        \"orientation\": \"h\",\n",
    "    },\n",
    "    margin={\"r\": 10},\n",
    ")\n",
    "\n",
    "fig.update_xaxes(title=\"Count\")\n",
    "fig.update_yaxes(title=\"Decades\")\n",
    "fig.show()\n",
    "\n",
    "del decade_counts"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "cols = [\n",
    "    \"valence\",\n",
    "    \"acousticness\",\n",
    "    \"danceability\",\n",
    "    \"duration_min\",\n",
    "    \"energy\",\n",
    "    \"instrumentalness\",\n",
    "    \"liveness\",\n",
    "    \"loudness\",\n",
    "    \"popularity\",\n",
    "    \"speechiness\",\n",
    "    \"tempo\",\n",
    "]\n",
    "for col in cols:\n",
    "    fig = px.histogram(\n",
    "        data_frame=df,\n",
    "        x=col,\n",
    "        color=\"decade\",\n",
    "        color_discrete_sequence=px.colors.qualitative.Light24,\n",
    "    )\n",
    "    fig.update_traces(opacity=0.7)\n",
    "    fig.update_layout(\n",
    "        bargap=0.1,\n",
    "        bargroupgap=0.05,\n",
    "        barmode=\"stack\",\n",
    "        title={\"text\": f\"Histogram of {col} per decade\", \"font\": {\"size\": 24}},\n",
    "        legend={\"title\": \"Decade\"},\n",
    "    )\n",
    "    fig.update_yaxes(title=\"Count\")\n",
    "    fig.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "decade_mean = df.groupby(\"decade\")[cols].mean()\n",
    "\n",
    "fig = make_subplots(\n",
    "    rows=4,\n",
    "    cols=3,\n",
    "    subplot_titles=(\n",
    "        decade_mean.columns[0],\n",
    "        decade_mean.columns[1],\n",
    "        decade_mean.columns[2],\n",
    "        decade_mean.columns[3],\n",
    "        decade_mean.columns[4],\n",
    "        decade_mean.columns[5],\n",
    "        decade_mean.columns[6],\n",
    "        decade_mean.columns[7],\n",
    "        decade_mean.columns[8],\n",
    "        decade_mean.columns[9],\n",
    "        decade_mean.columns[10],\n",
    "    ),\n",
    "    vertical_spacing=0.1,\n",
    ")\n",
    "\n",
    "fig.add_trace(\n",
    "    go.Bar(\n",
    "        y=decade_mean.index,\n",
    "        x=decade_mean.iloc[:, 0],\n",
    "        name=decade_mean.columns[0],\n",
    "        orientation=\"h\",\n",
    "    ),\n",
    "    row=1,\n",
    "    col=1,\n",
    ")\n",
    "\n",
    "fig.add_trace(\n",
    "    go.Bar(\n",
    "        y=decade_mean.index,\n",
    "        x=decade_mean.iloc[:, 1],\n",
    "        name=decade_mean.columns[1],\n",
    "        orientation=\"h\",\n",
    "    ),\n",
    "    row=1,\n",
    "    col=2,\n",
    ")\n",
    "\n",
    "fig.add_trace(\n",
    "    go.Bar(\n",
    "        y=decade_mean.index,\n",
    "        x=decade_mean.iloc[:, 2],\n",
    "        name=decade_mean.columns[2],\n",
    "        orientation=\"h\",\n",
    "    ),\n",
    "    row=1,\n",
    "    col=3,\n",
    ")\n",
    "\n",
    "fig.add_trace(\n",
    "    go.Bar(\n",
    "        y=decade_mean.index,\n",
    "        x=decade_mean.iloc[:, 3],\n",
    "        name=decade_mean.columns[3],\n",
    "        orientation=\"h\",\n",
    "    ),\n",
    "    row=2,\n",
    "    col=1,\n",
    ")\n",
    "\n",
    "fig.add_trace(\n",
    "    go.Bar(\n",
    "        y=decade_mean.index,\n",
    "        x=decade_mean.iloc[:, 4],\n",
    "        name=decade_mean.columns[4],\n",
    "        orientation=\"h\",\n",
    "    ),\n",
    "    row=2,\n",
    "    col=2,\n",
    ")\n",
    "\n",
    "fig.add_trace(\n",
    "    go.Bar(\n",
    "        y=decade_mean.index,\n",
    "        x=decade_mean.iloc[:, 5],\n",
    "        name=decade_mean.columns[5],\n",
    "        orientation=\"h\",\n",
    "    ),\n",
    "    row=2,\n",
    "    col=3,\n",
    ")\n",
    "\n",
    "fig.add_trace(\n",
    "    go.Bar(\n",
    "        y=decade_mean.index,\n",
    "        x=decade_mean.iloc[:, 6],\n",
    "        name=decade_mean.columns[6],\n",
    "        orientation=\"h\",\n",
    "    ),\n",
    "    row=3,\n",
    "    col=1,\n",
    ")\n",
    "\n",
    "fig.add_trace(\n",
    "    go.Bar(\n",
    "        y=decade_mean.index,\n",
    "        x=decade_mean.iloc[:, 7],\n",
    "        name=decade_mean.columns[7],\n",
    "        orientation=\"h\",\n",
    "    ),\n",
    "    row=3,\n",
    "    col=2,\n",
    ")\n",
    "\n",
    "fig.add_trace(\n",
    "    go.Bar(\n",
    "        y=decade_mean.index,\n",
    "        x=decade_mean.iloc[:, 8],\n",
    "        name=decade_mean.columns[8],\n",
    "        orientation=\"h\",\n",
    "    ),\n",
    "    row=3,\n",
    "    col=3,\n",
    ")\n",
    "\n",
    "fig.add_trace(\n",
    "    go.Bar(\n",
    "        y=decade_mean.index,\n",
    "        x=decade_mean.iloc[:, 9],\n",
    "        name=decade_mean.columns[9],\n",
    "        orientation=\"h\",\n",
    "    ),\n",
    "    row=4,\n",
    "    col=1,\n",
    ")\n",
    "\n",
    "fig.add_trace(\n",
    "    go.Bar(\n",
    "        y=decade_mean.index,\n",
    "        x=decade_mean.iloc[:, 10],\n",
    "        name=decade_mean.columns[10],\n",
    "        orientation=\"h\",\n",
    "    ),\n",
    "    row=4,\n",
    "    col=2,\n",
    ")\n",
    "\n",
    "fig.update_layout(\n",
    "    title={\"text\": \"Mean Musical Values per Decade\", \"font\": {\"size\": 22}},\n",
    "    legend={\n",
    "        \"orientation\": \"v\",\n",
    "        \"yanchor\": \"top\",\n",
    "        \"y\": 0.2,\n",
    "        \"xanchor\": \"right\",\n",
    "        \"x\": 0.9,\n",
    "    },\n",
    "    margin={\"b\": 10, \"r\": 10},\n",
    "    height=980,\n",
    ")\n",
    "\n",
    "fig.show()\n",
    "\n",
    "del decade_mean"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "decade_median = df.groupby(\"decade\")[cols].median()\n",
    "\n",
    "fig = make_subplots(\n",
    "    rows=4,\n",
    "    cols=3,\n",
    "    subplot_titles=(\n",
    "        decade_median.columns[0],\n",
    "        decade_median.columns[1],\n",
    "        decade_median.columns[2],\n",
    "        decade_median.columns[3],\n",
    "        decade_median.columns[4],\n",
    "        decade_median.columns[5],\n",
    "        decade_median.columns[6],\n",
    "        decade_median.columns[7],\n",
    "        decade_median.columns[8],\n",
    "        decade_median.columns[9],\n",
    "        decade_median.columns[10],\n",
    "    ),\n",
    "    vertical_spacing=0.1,\n",
    ")\n",
    "\n",
    "fig.add_trace(\n",
    "    go.Bar(\n",
    "        y=decade_median.index,\n",
    "        x=decade_median.iloc[:, 0],\n",
    "        name=decade_median.columns[0],\n",
    "        orientation=\"h\",\n",
    "    ),\n",
    "    row=1,\n",
    "    col=1,\n",
    ")\n",
    "\n",
    "fig.add_trace(\n",
    "    go.Bar(\n",
    "        y=decade_median.index,\n",
    "        x=decade_median.iloc[:, 1],\n",
    "        name=decade_median.columns[1],\n",
    "        orientation=\"h\",\n",
    "    ),\n",
    "    row=1,\n",
    "    col=2,\n",
    ")\n",
    "\n",
    "fig.add_trace(\n",
    "    go.Bar(\n",
    "        y=decade_median.index,\n",
    "        x=decade_median.iloc[:, 2],\n",
    "        name=decade_median.columns[2],\n",
    "        orientation=\"h\",\n",
    "    ),\n",
    "    row=1,\n",
    "    col=3,\n",
    ")\n",
    "\n",
    "fig.add_trace(\n",
    "    go.Bar(\n",
    "        y=decade_median.index,\n",
    "        x=decade_median.iloc[:, 3],\n",
    "        name=decade_median.columns[3],\n",
    "        orientation=\"h\",\n",
    "    ),\n",
    "    row=2,\n",
    "    col=1,\n",
    ")\n",
    "\n",
    "fig.add_trace(\n",
    "    go.Bar(\n",
    "        y=decade_median.index,\n",
    "        x=decade_median.iloc[:, 4],\n",
    "        name=decade_median.columns[4],\n",
    "        orientation=\"h\",\n",
    "    ),\n",
    "    row=2,\n",
    "    col=2,\n",
    ")\n",
    "\n",
    "fig.add_trace(\n",
    "    go.Bar(\n",
    "        y=decade_median.index,\n",
    "        x=decade_median.iloc[:, 5],\n",
    "        name=decade_median.columns[5],\n",
    "        orientation=\"h\",\n",
    "    ),\n",
    "    row=2,\n",
    "    col=3,\n",
    ")\n",
    "\n",
    "fig.add_trace(\n",
    "    go.Bar(\n",
    "        y=decade_median.index,\n",
    "        x=decade_median.iloc[:, 6],\n",
    "        name=decade_median.columns[6],\n",
    "        orientation=\"h\",\n",
    "    ),\n",
    "    row=3,\n",
    "    col=1,\n",
    ")\n",
    "\n",
    "fig.add_trace(\n",
    "    go.Bar(\n",
    "        y=decade_median.index,\n",
    "        x=decade_median.iloc[:, 7],\n",
    "        name=decade_median.columns[7],\n",
    "        orientation=\"h\",\n",
    "    ),\n",
    "    row=3,\n",
    "    col=2,\n",
    ")\n",
    "\n",
    "fig.add_trace(\n",
    "    go.Bar(\n",
    "        y=decade_median.index,\n",
    "        x=decade_median.iloc[:, 8],\n",
    "        name=decade_median.columns[8],\n",
    "        orientation=\"h\",\n",
    "    ),\n",
    "    row=3,\n",
    "    col=3,\n",
    ")\n",
    "\n",
    "fig.add_trace(\n",
    "    go.Bar(\n",
    "        y=decade_median.index,\n",
    "        x=decade_median.iloc[:, 9],\n",
    "        name=decade_median.columns[9],\n",
    "        orientation=\"h\",\n",
    "    ),\n",
    "    row=4,\n",
    "    col=1,\n",
    ")\n",
    "\n",
    "fig.add_trace(\n",
    "    go.Bar(\n",
    "        y=decade_median.index,\n",
    "        x=decade_median.iloc[:, 10],\n",
    "        name=decade_median.columns[10],\n",
    "        orientation=\"h\",\n",
    "    ),\n",
    "    row=4,\n",
    "    col=2,\n",
    ")\n",
    "\n",
    "fig.update_layout(\n",
    "    title={\"text\": \"Median Musical Values per Decade\", \"font\": {\"size\": 22}},\n",
    "    legend={\n",
    "        \"orientation\": \"v\",\n",
    "        \"yanchor\": \"top\",\n",
    "        \"y\": 0.2,\n",
    "        \"xanchor\": \"right\",\n",
    "        \"x\": 0.9,\n",
    "    },\n",
    "    margin={\"b\": 10, \"r\": 10},\n",
    "    height=980,\n",
    ")\n",
    "\n",
    "fig.show()\n",
    "\n",
    "del decade_median"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "explicit_count = (\n",
    "    df.groupby([\"decade\", \"explicit\"], as_index=False)[\"year\"]\n",
    "    .count()\n",
    "    .rename(columns={\"year\": \"count\"})\n",
    ")\n",
    "key_count = (\n",
    "    df.groupby([\"decade\", \"key\"], as_index=False)[\"year\"]\n",
    "    .count()\n",
    "    .rename(columns={\"year\": \"count\"})\n",
    ")\n",
    "mode_count = (\n",
    "    df.groupby([\"decade\", \"mode\"], as_index=False)[\"year\"]\n",
    "    .count()\n",
    "    .rename(columns={\"year\": \"count\"})\n",
    ")\n",
    "\n",
    "fig = px.histogram(\n",
    "    data_frame=explicit_count,\n",
    "    x=\"decade\",\n",
    "    y=\"count\",\n",
    "    color=\"explicit\",\n",
    "    histfunc=\"sum\",\n",
    "    color_discrete_sequence=px.colors.qualitative.Pastel,\n",
    "    text_auto=True,\n",
    ")\n",
    "fig.update_layout(\n",
    "    title={\"text\": \"Explicit Count per Decade\", \"font\": {\"size\": 24}},\n",
    "    bargap=0.2,\n",
    "    bargroupgap=0.1,\n",
    "    barmode=\"group\",\n",
    "    xaxis_title=\"Decade\",\n",
    "    yaxis_title=\"Count\",\n",
    ")\n",
    "fig.show()\n",
    "\n",
    "fig = px.histogram(\n",
    "    data_frame=mode_count,\n",
    "    x=\"decade\",\n",
    "    y=\"count\",\n",
    "    color=\"mode\",\n",
    "    histfunc=\"sum\",\n",
    "    color_discrete_sequence=px.colors.qualitative.Pastel,\n",
    "    text_auto=True,\n",
    ")\n",
    "fig.update_layout(\n",
    "    title={\"text\": \"Mode Count per Decade\", \"font\": {\"size\": 24}},\n",
    "    bargap=0.2,\n",
    "    bargroupgap=0.1,\n",
    "    barmode=\"group\",\n",
    "    xaxis_title=\"Decade\",\n",
    "    yaxis_title=\"Count\",\n",
    ")\n",
    "fig.show()\n",
    "\n",
    "fig = px.histogram(\n",
    "    data_frame=key_count,\n",
    "    x=\"decade\",\n",
    "    y=\"count\",\n",
    "    color=\"key\",\n",
    "    histfunc=\"sum\",\n",
    "    color_discrete_sequence=px.colors.qualitative.Pastel,\n",
    "    text_auto=True,\n",
    ")\n",
    "fig.update_layout(\n",
    "    title={\"text\": \"Key Count per Decade\", \"font\": {\"size\": 24}},\n",
    "    bargap=0.2,\n",
    "    bargroupgap=0.1,\n",
    "    barmode=\"stack\",\n",
    "    xaxis_title=\"Decade\",\n",
    "    yaxis_title=\"Count\",\n",
    ")\n",
    "fig.show()\n",
    "\n",
    "del (mode_count, key_count, explicit_count)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "cols = [\n",
    "    \"valence\",\n",
    "    \"acousticness\",\n",
    "    \"danceability\",\n",
    "    \"duration_min\",\n",
    "    \"energy\",\n",
    "    \"instrumentalness\",\n",
    "    \"liveness\",\n",
    "    \"loudness\",\n",
    "    \"year\",\n",
    "    \"speechiness\",\n",
    "    \"tempo\",\n",
    "]\n",
    "\n",
    "for col in cols:\n",
    "\n",
    "    fig = px.scatter(\n",
    "        data_frame=df,\n",
    "        x=col,\n",
    "        y=\"popularity\",\n",
    "        trendline=\"ols\",\n",
    "        trendline_color_override=\"#A6E3A1\",\n",
    "    )\n",
    "    fig.update_traces(marker={\"opacity\": 0.3, \"size\": 3, \"color\": \"#B4BEFE\"})\n",
    "    fig.update_layout(title={\"text\": f\"{col} vs popularity\", \"font\": {\"size\": 24}})\n",
    "    fig.show()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Header 1\n",
    "\n",
    "## Header 2\n",
    "\n",
    "### Header 3.1"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "cols = [\n",
    "    \"valence\",\n",
    "    \"acousticness\",\n",
    "    \"danceability\",\n",
    "    \"duration_min\",\n",
    "    \"energy\",\n",
    "    \"instrumentalness\",\n",
    "    \"liveness\",\n",
    "    \"loudness\",\n",
    "    \"year\",\n",
    "    \"speechiness\",\n",
    "    \"tempo\",\n",
    "]\n",
    "\n",
    "plt.figure(figsize=(15, 10))\n",
    "\n",
    "for i, col in enumerate(cols):\n",
    "    ax = plt.subplot(3, 4, i + 1)\n",
    "    sns.regplot(\n",
    "        data=df,\n",
    "        x=\"popularity\",\n",
    "        y=col,\n",
    "        ax=ax,\n",
    "        scatter_kws={\"alpha\": 0.5},\n",
    "        line_kws={\"color\": \"#F38BA8\"},\n",
    "    )\n",
    "\n",
    "plt.tight_layout()\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "cols = [\n",
    "    \"valence\",\n",
    "    \"acousticness\",\n",
    "    \"danceability\",\n",
    "    \"duration_min\",\n",
    "    \"energy\",\n",
    "    \"instrumentalness\",\n",
    "    \"liveness\",\n",
    "    \"loudness\",\n",
    "    \"year\",\n",
    "    \"speechiness\",\n",
    "    \"tempo\",\n",
    "    \"popularity\",\n",
    "]\n",
    "\n",
    "plt.figure(figsize=(10, 7))\n",
    "mask = np.triu(np.ones_like(df[cols].corr()))\n",
    "sns.heatmap(\n",
    "    df[cols].corr(),\n",
    "    annot=True,\n",
    "    fmt=\".2f\",\n",
    "    cmap=\"Blues\",\n",
    "    mask=mask,\n",
    ")\n",
    "plt.grid(visible=False)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "df[\"first_artist\"] = (\n",
    "    df[\"artists\"]\n",
    "    .apply(lambda x: str(x).split(\"x\")[0])\n",
    "    .apply(lambda x: str(x).replace(\"[\", \"\"))\n",
    "    .apply(lambda x: str(x).replace(\"]\", \"\"))\n",
    "    .apply(lambda x: str(x).replace(\"'\", \"\"))\n",
    ")\n",
    "df = df.drop(\"artists\", axis=1)\n",
    "df[\"first_artist\"] = df[\"first_artist\"].apply(lambda x: str(x).split(\",\")[0])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "popularity_check = (\n",
    "    df.groupby([\"first_artist\"], as_index=False)[\"popularity\"]\n",
    "    .agg({\"mean\", \"count\", \"median\"})\n",
    "    .sort_values(by=\"mean\", ascending=False)\n",
    "    .reset_index(drop=True)\n",
    ")\n",
    "\n",
    "popularity_check = popularity_check.drop(16091, axis=0)\n",
    "popularity_check = popularity_check.drop(16086, axis=0)\n",
    "popularity_check = popularity_check.drop(16429, axis=0)\n",
    "\n",
    "to_drop = popularity_check[popularity_check[\"count\"] <= 45].index\n",
    "popularity_check = popularity_check.drop(to_drop)\n",
    "popularity_check = popularity_check.sort_values(by=\"mean\", ascending=False).head(50)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Header 1\n",
    "\n",
    "## Header 2\n",
    "\n",
    "### Header 3.1"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "top_50_artists = pd.DataFrame()\n",
    "\n",
    "for i in popularity_check[\"first_artist\"].unique():\n",
    "    artist = df.query(\"first_artist == @i\")\n",
    "    top_50_artists = pd.concat([top_50_artists, artist], axis=0)\n",
    "\n",
    "top_50_artists = top_50_artists.reset_index(drop=True)\n",
    "top_50_artists.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "plt.figure(figsize=(12, 8))\n",
    "(\n",
    "    top_50_artists[\"first_artist\"]\n",
    "    .value_counts()\n",
    "    .sort_values(ascending=True)\n",
    "    .plot(kind=\"barh\")\n",
    ")\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "top_50_artists[\"decade\"].value_counts().sort_values(ascending=True).plot(kind=\"barh\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "cols = [\n",
    "    \"valence\",\n",
    "    \"acousticness\",\n",
    "    \"danceability\",\n",
    "    \"duration_min\",\n",
    "    \"energy\",\n",
    "    \"instrumentalness\",\n",
    "    \"liveness\",\n",
    "    \"loudness\",\n",
    "    \"year\",\n",
    "    \"speechiness\",\n",
    "    \"tempo\",\n",
    "]\n",
    "\n",
    "plt.figure(figsize=(15, 10))\n",
    "\n",
    "for i, col in enumerate(cols):\n",
    "    ax = plt.subplot(3, 4, i + 1)\n",
    "    sns.kdeplot(data=top_50_artists, x=col, hue=\"first_artist\", legend=False)\n",
    "\n",
    "plt.tight_layout()\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Header 1\n",
    "\n",
    "## Header 2\n",
    "\n",
    "### Header 3.1"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "import pandas as pd\n",
    "import numpy as np\n",
    "import seaborn as sns\n",
    "import matplotlib.pyplot as plt\n",
    "import matplotlib as mpl\n",
    "import mplcatppuccin\n",
    "import plotly.express as px\n",
    "import plotly.graph_objects as go\n",
    "from plotly.subplots import make_subplots\n",
    "import plotly.figure_factory as ff\n",
    "import warnings\n",
    "import plotly.io as pio\n",
    "\n",
    "warnings.filterwarnings('ignore')\n",
    "\n",
    "pio.renderers.default = 'notebook_connected'\n",
    "pio.templates.default = 'plotly_dark'\n",
    "\n",
    "\n",
    "%matplotlib inline\n",
    "%config InlineBackend.figure_format = 'retina'\n",
    "pd.set_option('display.max_columns', None)\n",
    "pd.set_option('display.precision', 2)\n",
    "pd.set_option('display.colheader_justify', 'left')\n",
    "\n",
    "mpl.rc(\n",
    "    'figure',\n",
    "    autolayout=True,\n",
    "    titlesize=18\n",
    ")\n",
    "\n",
    "mpl.style.use(['ggplot', 'mocha'])\n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Header 3.2\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "df = pd.read_csv(\n",
    "    \"data.csv\",\n",
    "    parse_dates=[\"release_date\"],\n",
    ")\n",
    "df.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "map_key = {\n",
    "    0: \"C\",\n",
    "    1: \"C#\",\n",
    "    2: \"D\",\n",
    "    3: \"D#\",\n",
    "    4: \"E\",\n",
    "    5: \"F\",\n",
    "    6: \"F#\",\n",
    "    7: \"G\",\n",
    "    8: \"G#\",\n",
    "    9: \"A\",\n",
    "    10: \"A#\",\n",
    "    11: \"B\",\n",
    "}\n",
    "\n",
    "map_mode = {1: \"Major\", 0: \"Minor\"}\n",
    "\n",
    "df[\"mode\"] = df[\"mode\"].map(map_mode)\n",
    "df[\"key\"] = df[\"key\"].map(map_key)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "check_dups = df[[\"artists\", \"name\"]]\n",
    "dups = check_dups[check_dups.duplicated()].index"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "print(\"Before dropping duplicated:\", df.shape)\n",
    "df = df.drop(dups)\n",
    "print(\"After dropping duplicated:\", df.shape)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Header 1.3\n",
    "\n",
    "## Header 2.3\n",
    "\n",
    "### Header 3.5"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "df[\"duration_ms\"] = df[\"duration_ms\"] / 60_000\n",
    "df = df.rename(columns={\"duration_ms\": \"duration_min\"})\n",
    "df.head()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Header 1.4\n",
    "\n",
    "## Header 2.4\n",
    "\n",
    "### Header 3.5"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "df = df.drop([\"release_date\", \"id\"], axis=1)\n",
    "df.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "def fun_subplots_plotly(df, col):\n",
    "\n",
    "    mean_val = df[col].mean()\n",
    "    median_val = df[col].median()\n",
    "    fig = make_subplots(rows=1, cols=2, column_widths=[0.75, 0.25])\n",
    "\n",
    "    fig.add_trace(\n",
    "        go.Histogram(\n",
    "            x=df[col], name=f\"Histogram {col}\", marker={\"color\": \"#EBA0AC\"}, nbinsx=50\n",
    "        ),\n",
    "        row=1,\n",
    "        col=1,\n",
    "    )\n",
    "\n",
    "    fig.add_shape(\n",
    "        type=\"line\",\n",
    "        xref=\"paper\",\n",
    "        yref=\"y\",\n",
    "        x0=-1,\n",
    "        x1=1,\n",
    "        y0=mean_val,\n",
    "        y1=mean_val,\n",
    "        row=1,\n",
    "        col=2,\n",
    "        line={\"color\": \"#A6E3A1\", \"width\": 3, \"dash\": \"dot\"},\n",
    "    )\n",
    "\n",
    "    fig.add_shape(\n",
    "        type=\"line\",\n",
    "        xref=\"paper\",\n",
    "        yref=\"y\",\n",
    "        x0=-1,\n",
    "        x1=1,\n",
    "        y0=median_val,\n",
    "        y1=median_val,\n",
    "        row=1,\n",
    "        col=2,\n",
    "        line={\"color\": \"#CBA6F7\", \"width\": 3, \"dash\": \"dot\"},\n",
    "    )\n",
    "\n",
    "    fig.add_annotation(\n",
    "        xref=\"paper\",\n",
    "        x=-0.7,\n",
    "        y=mean_val,\n",
    "        showarrow=True,\n",
    "        arrowhead=2,\n",
    "        text=f\"Mean = {mean_val:.2f}\",\n",
    "        row=1,\n",
    "        col=2,\n",
    "    )\n",
    "\n",
    "    fig.add_annotation(\n",
    "        xref=\"paper\",\n",
    "        x=0.7,\n",
    "        y=median_val,\n",
    "        showarrow=True,\n",
    "        arrowhead=2,\n",
    "        text=f\"Median = {median_val:.2f}\",\n",
    "        row=1,\n",
    "        col=2,\n",
    "    )\n",
    "\n",
    "    fig.add_trace(\n",
    "        go.Box(y=df[col], name=f\"Boxplot {col}\", marker={\"color\": \"#F9E2AF\"}),\n",
    "        row=1,\n",
    "        col=2,\n",
    "    )\n",
    "\n",
    "    fig.update_layout(\n",
    "        title={\"text\": f\"Distribution Plot {col}\", \"font\": {\"size\": 24}},\n",
    "        legend={\n",
    "            \"orientation\": \"h\",\n",
    "            \"yanchor\": \"bottom\",\n",
    "            \"y\": 1.02,\n",
    "            \"xanchor\": \"right\",\n",
    "            \"x\": 1,\n",
    "        },\n",
    "    )\n",
    "    fig.update_yaxes(title_text=\"Count\", row=1, col=1)\n",
    "    fig.update_yaxes(title_text=f\"{col}\", row=1, col=2)\n",
    "    fig.update_xaxes(title_text=f\"{col}\", row=1, col=1)\n",
    "    fig.update_xaxes(title_text=\"\", row=1, col=2)\n",
    "    fig.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "music_vals = [\n",
    "    \"valence\",\n",
    "    \"acousticness\",\n",
    "    \"danceability\",\n",
    "    \"duration_min\",\n",
    "    \"energy\",\n",
    "    \"instrumentalness\",\n",
    "    \"liveness\",\n",
    "    \"loudness\",\n",
    "    \"popularity\",\n",
    "    \"speechiness\",\n",
    "    \"tempo\",\n",
    "]\n",
    "\n",
    "for col in music_vals:\n",
    "    fun_subplots_plotly(df, col)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Header 1.2\n",
    "\n",
    "## Header 2.2\n",
    "\n",
    "### Header 3.4"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "bins = pd.IntervalIndex.from_breaks(\n",
    "    [1920, 1930, 1940, 1950, 1960, 1970, 1980, 1990, 2000, 2010, 2020]\n",
    ")\n",
    "\n",
    "df[\"decade\"] = pd.cut(df[\"year\"], bins).astype(\"str\")\n",
    "\n",
    "map_decade = {\n",
    "    \"(1920, 1930]\": \"1920s\",\n",
    "    \"(1930, 1940]\": \"1930s\",\n",
    "    \"(1940, 1950]\": \"1940s\",\n",
    "    \"(1950, 1960]\": \"1950s\",\n",
    "    \"(1960, 1970]\": \"1960s\",\n",
    "    \"(1970, 1980]\": \"1970s\",\n",
    "    \"(1980, 1990]\": \"1980s\",\n",
    "    \"(1990, 2000]\": \"1990s\",\n",
    "    \"(2000, 2010]\": \"2000s\",\n",
    "    \"(2010, 2020]\": \"2010s\",\n",
    "}\n",
    "\n",
    "df[\"decade\"] = df[\"decade\"].map(map_decade)\n",
    "\n",
    "df.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "decade_counts = (\n",
    "    df[\"decade\"].value_counts().reset_index().sort_values(by=\"decade\", ascending=True)\n",
    ")\n",
    "\n",
    "fig = px.bar(\n",
    "    data_frame=decade_counts,\n",
    "    y=\"decade\",\n",
    "    x=\"count\",\n",
    "    color=\"count\",\n",
    "    color_continuous_scale=px.colors.sequential.Sunset,\n",
    "    text_auto=True,\n",
    ")\n",
    "\n",
    "fig.update_layout(\n",
    "    title={\"text\": \"Count of songs per decade\", \"font\": {\"size\": 24}},\n",
    "    coloraxis_colorbar={\n",
    "        \"title\": \"Count\",\n",
    "        \"thicknessmode\": \"pixels\",\n",
    "        \"thickness\": 20,\n",
    "        \"lenmode\": \"pixels\",\n",
    "        \"len\": 500,\n",
    "        \"yanchor\": \"top\",\n",
    "        \"xanchor\": \"right\",\n",
    "        \"y\": 1.15,\n",
    "        \"x\": 0.95,\n",
    "        \"orientation\": \"h\",\n",
    "    },\n",
    "    margin={\"r\": 10},\n",
    ")\n",
    "\n",
    "fig.update_xaxes(title=\"Count\")\n",
    "fig.update_yaxes(title=\"Decades\")\n",
    "fig.show()\n",
    "\n",
    "del decade_counts"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "df = df.query(\"duration_min <= 5\")"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Header 1.2\n",
    "\n",
    "## Header 2.2\n",
    "\n",
    "### Header 3.4"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "decade_counts = (\n",
    "    df[\"decade\"].value_counts().reset_index().sort_values(by=\"decade\", ascending=True)\n",
    ")\n",
    "\n",
    "fig = px.bar(\n",
    "    data_frame=decade_counts,\n",
    "    y=\"decade\",\n",
    "    x=\"count\",\n",
    "    color=\"count\",\n",
    "    color_continuous_scale=px.colors.sequential.Sunset,\n",
    "    text_auto=True,\n",
    ")\n",
    "\n",
    "fig.update_layout(\n",
    "    title={\"text\": \"Count of songs per decade (< 5min)\", \"font\": {\"size\": 24}},\n",
    "    coloraxis_colorbar={\n",
    "        \"title\": \"Count\",\n",
    "        \"thicknessmode\": \"pixels\",\n",
    "        \"thickness\": 20,\n",
    "        \"lenmode\": \"pixels\",\n",
    "        \"len\": 500,\n",
    "        \"yanchor\": \"top\",\n",
    "        \"xanchor\": \"right\",\n",
    "        \"y\": 1.15,\n",
    "        \"x\": 0.95,\n",
    "        \"orientation\": \"h\",\n",
    "    },\n",
    "    margin={\"r\": 10},\n",
    ")\n",
    "\n",
    "fig.update_xaxes(title=\"Count\")\n",
    "fig.update_yaxes(title=\"Decades\")\n",
    "fig.show()\n",
    "\n",
    "del decade_counts"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "cols = [\n",
    "    \"valence\",\n",
    "    \"acousticness\",\n",
    "    \"danceability\",\n",
    "    \"duration_min\",\n",
    "    \"energy\",\n",
    "    \"instrumentalness\",\n",
    "    \"liveness\",\n",
    "    \"loudness\",\n",
    "    \"popularity\",\n",
    "    \"speechiness\",\n",
    "    \"tempo\",\n",
    "]\n",
    "for col in cols:\n",
    "    fig = px.histogram(\n",
    "        data_frame=df,\n",
    "        x=col,\n",
    "        color=\"decade\",\n",
    "        color_discrete_sequence=px.colors.qualitative.Light24,\n",
    "    )\n",
    "    fig.update_traces(opacity=0.7)\n",
    "    fig.update_layout(\n",
    "        bargap=0.1,\n",
    "        bargroupgap=0.05,\n",
    "        barmode=\"stack\",\n",
    "        title={\"text\": f\"Histogram of {col} per decade\", \"font\": {\"size\": 24}},\n",
    "        legend={\"title\": \"Decade\"},\n",
    "    )\n",
    "    fig.update_yaxes(title=\"Count\")\n",
    "    fig.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "decade_mean = df.groupby(\"decade\")[cols].mean()\n",
    "\n",
    "fig = make_subplots(\n",
    "    rows=4,\n",
    "    cols=3,\n",
    "    subplot_titles=(\n",
    "        decade_mean.columns[0],\n",
    "        decade_mean.columns[1],\n",
    "        decade_mean.columns[2],\n",
    "        decade_mean.columns[3],\n",
    "        decade_mean.columns[4],\n",
    "        decade_mean.columns[5],\n",
    "        decade_mean.columns[6],\n",
    "        decade_mean.columns[7],\n",
    "        decade_mean.columns[8],\n",
    "        decade_mean.columns[9],\n",
    "        decade_mean.columns[10],\n",
    "    ),\n",
    "    vertical_spacing=0.1,\n",
    ")\n",
    "\n",
    "fig.add_trace(\n",
    "    go.Bar(\n",
    "        y=decade_mean.index,\n",
    "        x=decade_mean.iloc[:, 0],\n",
    "        name=decade_mean.columns[0],\n",
    "        orientation=\"h\",\n",
    "    ),\n",
    "    row=1,\n",
    "    col=1,\n",
    ")\n",
    "\n",
    "fig.add_trace(\n",
    "    go.Bar(\n",
    "        y=decade_mean.index,\n",
    "        x=decade_mean.iloc[:, 1],\n",
    "        name=decade_mean.columns[1],\n",
    "        orientation=\"h\",\n",
    "    ),\n",
    "    row=1,\n",
    "    col=2,\n",
    ")\n",
    "\n",
    "fig.add_trace(\n",
    "    go.Bar(\n",
    "        y=decade_mean.index,\n",
    "        x=decade_mean.iloc[:, 2],\n",
    "        name=decade_mean.columns[2],\n",
    "        orientation=\"h\",\n",
    "    ),\n",
    "    row=1,\n",
    "    col=3,\n",
    ")\n",
    "\n",
    "fig.add_trace(\n",
    "    go.Bar(\n",
    "        y=decade_mean.index,\n",
    "        x=decade_mean.iloc[:, 3],\n",
    "        name=decade_mean.columns[3],\n",
    "        orientation=\"h\",\n",
    "    ),\n",
    "    row=2,\n",
    "    col=1,\n",
    ")\n",
    "\n",
    "fig.add_trace(\n",
    "    go.Bar(\n",
    "        y=decade_mean.index,\n",
    "        x=decade_mean.iloc[:, 4],\n",
    "        name=decade_mean.columns[4],\n",
    "        orientation=\"h\",\n",
    "    ),\n",
    "    row=2,\n",
    "    col=2,\n",
    ")\n",
    "\n",
    "fig.add_trace(\n",
    "    go.Bar(\n",
    "        y=decade_mean.index,\n",
    "        x=decade_mean.iloc[:, 5],\n",
    "        name=decade_mean.columns[5],\n",
    "        orientation=\"h\",\n",
    "    ),\n",
    "    row=2,\n",
    "    col=3,\n",
    ")\n",
    "\n",
    "fig.add_trace(\n",
    "    go.Bar(\n",
    "        y=decade_mean.index,\n",
    "        x=decade_mean.iloc[:, 6],\n",
    "        name=decade_mean.columns[6],\n",
    "        orientation=\"h\",\n",
    "    ),\n",
    "    row=3,\n",
    "    col=1,\n",
    ")\n",
    "\n",
    "fig.add_trace(\n",
    "    go.Bar(\n",
    "        y=decade_mean.index,\n",
    "        x=decade_mean.iloc[:, 7],\n",
    "        name=decade_mean.columns[7],\n",
    "        orientation=\"h\",\n",
    "    ),\n",
    "    row=3,\n",
    "    col=2,\n",
    ")\n",
    "\n",
    "fig.add_trace(\n",
    "    go.Bar(\n",
    "        y=decade_mean.index,\n",
    "        x=decade_mean.iloc[:, 8],\n",
    "        name=decade_mean.columns[8],\n",
    "        orientation=\"h\",\n",
    "    ),\n",
    "    row=3,\n",
    "    col=3,\n",
    ")\n",
    "\n",
    "fig.add_trace(\n",
    "    go.Bar(\n",
    "        y=decade_mean.index,\n",
    "        x=decade_mean.iloc[:, 9],\n",
    "        name=decade_mean.columns[9],\n",
    "        orientation=\"h\",\n",
    "    ),\n",
    "    row=4,\n",
    "    col=1,\n",
    ")\n",
    "\n",
    "fig.add_trace(\n",
    "    go.Bar(\n",
    "        y=decade_mean.index,\n",
    "        x=decade_mean.iloc[:, 10],\n",
    "        name=decade_mean.columns[10],\n",
    "        orientation=\"h\",\n",
    "    ),\n",
    "    row=4,\n",
    "    col=2,\n",
    ")\n",
    "\n",
    "fig.update_layout(\n",
    "    title={\"text\": \"Mean Musical Values per Decade\", \"font\": {\"size\": 22}},\n",
    "    legend={\n",
    "        \"orientation\": \"v\",\n",
    "        \"yanchor\": \"top\",\n",
    "        \"y\": 0.2,\n",
    "        \"xanchor\": \"right\",\n",
    "        \"x\": 0.9,\n",
    "    },\n",
    "    margin={\"b\": 10, \"r\": 10},\n",
    "    height=980,\n",
    ")\n",
    "\n",
    "fig.show()\n",
    "\n",
    "del decade_mean"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "decade_median = df.groupby(\"decade\")[cols].median()\n",
    "\n",
    "fig = make_subplots(\n",
    "    rows=4,\n",
    "    cols=3,\n",
    "    subplot_titles=(\n",
    "        decade_median.columns[0],\n",
    "        decade_median.columns[1],\n",
    "        decade_median.columns[2],\n",
    "        decade_median.columns[3],\n",
    "        decade_median.columns[4],\n",
    "        decade_median.columns[5],\n",
    "        decade_median.columns[6],\n",
    "        decade_median.columns[7],\n",
    "        decade_median.columns[8],\n",
    "        decade_median.columns[9],\n",
    "        decade_median.columns[10],\n",
    "    ),\n",
    "    vertical_spacing=0.1,\n",
    ")\n",
    "\n",
    "fig.add_trace(\n",
    "    go.Bar(\n",
    "        y=decade_median.index,\n",
    "        x=decade_median.iloc[:, 0],\n",
    "        name=decade_median.columns[0],\n",
    "        orientation=\"h\",\n",
    "    ),\n",
    "    row=1,\n",
    "    col=1,\n",
    ")\n",
    "\n",
    "fig.add_trace(\n",
    "    go.Bar(\n",
    "        y=decade_median.index,\n",
    "        x=decade_median.iloc[:, 1],\n",
    "        name=decade_median.columns[1],\n",
    "        orientation=\"h\",\n",
    "    ),\n",
    "    row=1,\n",
    "    col=2,\n",
    ")\n",
    "\n",
    "fig.add_trace(\n",
    "    go.Bar(\n",
    "        y=decade_median.index,\n",
    "        x=decade_median.iloc[:, 2],\n",
    "        name=decade_median.columns[2],\n",
    "        orientation=\"h\",\n",
    "    ),\n",
    "    row=1,\n",
    "    col=3,\n",
    ")\n",
    "\n",
    "fig.add_trace(\n",
    "    go.Bar(\n",
    "        y=decade_median.index,\n",
    "        x=decade_median.iloc[:, 3],\n",
    "        name=decade_median.columns[3],\n",
    "        orientation=\"h\",\n",
    "    ),\n",
    "    row=2,\n",
    "    col=1,\n",
    ")\n",
    "\n",
    "fig.add_trace(\n",
    "    go.Bar(\n",
    "        y=decade_median.index,\n",
    "        x=decade_median.iloc[:, 4],\n",
    "        name=decade_median.columns[4],\n",
    "        orientation=\"h\",\n",
    "    ),\n",
    "    row=2,\n",
    "    col=2,\n",
    ")\n",
    "\n",
    "fig.add_trace(\n",
    "    go.Bar(\n",
    "        y=decade_median.index,\n",
    "        x=decade_median.iloc[:, 5],\n",
    "        name=decade_median.columns[5],\n",
    "        orientation=\"h\",\n",
    "    ),\n",
    "    row=2,\n",
    "    col=3,\n",
    ")\n",
    "\n",
    "fig.add_trace(\n",
    "    go.Bar(\n",
    "        y=decade_median.index,\n",
    "        x=decade_median.iloc[:, 6],\n",
    "        name=decade_median.columns[6],\n",
    "        orientation=\"h\",\n",
    "    ),\n",
    "    row=3,\n",
    "    col=1,\n",
    ")\n",
    "\n",
    "fig.add_trace(\n",
    "    go.Bar(\n",
    "        y=decade_median.index,\n",
    "        x=decade_median.iloc[:, 7],\n",
    "        name=decade_median.columns[7],\n",
    "        orientation=\"h\",\n",
    "    ),\n",
    "    row=3,\n",
    "    col=2,\n",
    ")\n",
    "\n",
    "fig.add_trace(\n",
    "    go.Bar(\n",
    "        y=decade_median.index,\n",
    "        x=decade_median.iloc[:, 8],\n",
    "        name=decade_median.columns[8],\n",
    "        orientation=\"h\",\n",
    "    ),\n",
    "    row=3,\n",
    "    col=3,\n",
    ")\n",
    "\n",
    "fig.add_trace(\n",
    "    go.Bar(\n",
    "        y=decade_median.index,\n",
    "        x=decade_median.iloc[:, 9],\n",
    "        name=decade_median.columns[9],\n",
    "        orientation=\"h\",\n",
    "    ),\n",
    "    row=4,\n",
    "    col=1,\n",
    ")\n",
    "\n",
    "fig.add_trace(\n",
    "    go.Bar(\n",
    "        y=decade_median.index,\n",
    "        x=decade_median.iloc[:, 10],\n",
    "        name=decade_median.columns[10],\n",
    "        orientation=\"h\",\n",
    "    ),\n",
    "    row=4,\n",
    "    col=2,\n",
    ")\n",
    "\n",
    "fig.update_layout(\n",
    "    title={\"text\": \"Median Musical Values per Decade\", \"font\": {\"size\": 22}},\n",
    "    legend={\n",
    "        \"orientation\": \"v\",\n",
    "        \"yanchor\": \"top\",\n",
    "        \"y\": 0.2,\n",
    "        \"xanchor\": \"right\",\n",
    "        \"x\": 0.9,\n",
    "    },\n",
    "    margin={\"b\": 10, \"r\": 10},\n",
    "    height=980,\n",
    ")\n",
    "\n",
    "fig.show()\n",
    "\n",
    "del decade_median"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "explicit_count = (\n",
    "    df.groupby([\"decade\", \"explicit\"], as_index=False)[\"year\"]\n",
    "    .count()\n",
    "    .rename(columns={\"year\": \"count\"})\n",
    ")\n",
    "key_count = (\n",
    "    df.groupby([\"decade\", \"key\"], as_index=False)[\"year\"]\n",
    "    .count()\n",
    "    .rename(columns={\"year\": \"count\"})\n",
    ")\n",
    "mode_count = (\n",
    "    df.groupby([\"decade\", \"mode\"], as_index=False)[\"year\"]\n",
    "    .count()\n",
    "    .rename(columns={\"year\": \"count\"})\n",
    ")\n",
    "\n",
    "fig = px.histogram(\n",
    "    data_frame=explicit_count,\n",
    "    x=\"decade\",\n",
    "    y=\"count\",\n",
    "    color=\"explicit\",\n",
    "    histfunc=\"sum\",\n",
    "    color_discrete_sequence=px.colors.qualitative.Pastel,\n",
    "    text_auto=True,\n",
    ")\n",
    "fig.update_layout(\n",
    "    title={\"text\": \"Explicit Count per Decade\", \"font\": {\"size\": 24}},\n",
    "    bargap=0.2,\n",
    "    bargroupgap=0.1,\n",
    "    barmode=\"group\",\n",
    "    xaxis_title=\"Decade\",\n",
    "    yaxis_title=\"Count\",\n",
    ")\n",
    "fig.show()\n",
    "\n",
    "fig = px.histogram(\n",
    "    data_frame=mode_count,\n",
    "    x=\"decade\",\n",
    "    y=\"count\",\n",
    "    color=\"mode\",\n",
    "    histfunc=\"sum\",\n",
    "    color_discrete_sequence=px.colors.qualitative.Pastel,\n",
    "    text_auto=True,\n",
    ")\n",
    "fig.update_layout(\n",
    "    title={\"text\": \"Mode Count per Decade\", \"font\": {\"size\": 24}},\n",
    "    bargap=0.2,\n",
    "    bargroupgap=0.1,\n",
    "    barmode=\"group\",\n",
    "    xaxis_title=\"Decade\",\n",
    "    yaxis_title=\"Count\",\n",
    ")\n",
    "fig.show()\n",
    "\n",
    "fig = px.histogram(\n",
    "    data_frame=key_count,\n",
    "    x=\"decade\",\n",
    "    y=\"count\",\n",
    "    color=\"key\",\n",
    "    histfunc=\"sum\",\n",
    "    color_discrete_sequence=px.colors.qualitative.Pastel,\n",
    "    text_auto=True,\n",
    ")\n",
    "fig.update_layout(\n",
    "    title={\"text\": \"Key Count per Decade\", \"font\": {\"size\": 24}},\n",
    "    bargap=0.2,\n",
    "    bargroupgap=0.1,\n",
    "    barmode=\"stack\",\n",
    "    xaxis_title=\"Decade\",\n",
    "    yaxis_title=\"Count\",\n",
    ")\n",
    "fig.show()\n",
    "\n",
    "del (mode_count, key_count, explicit_count)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "cols = [\n",
    "    \"valence\",\n",
    "    \"acousticness\",\n",
    "    \"danceability\",\n",
    "    \"duration_min\",\n",
    "    \"energy\",\n",
    "    \"instrumentalness\",\n",
    "    \"liveness\",\n",
    "    \"loudness\",\n",
    "    \"year\",\n",
    "    \"speechiness\",\n",
    "    \"tempo\",\n",
    "]\n",
    "\n",
    "for col in cols:\n",
    "\n",
    "    fig = px.scatter(\n",
    "        data_frame=df,\n",
    "        x=col,\n",
    "        y=\"popularity\",\n",
    "        trendline=\"ols\",\n",
    "        trendline_color_override=\"#A6E3A1\",\n",
    "    )\n",
    "    fig.update_traces(marker={\"opacity\": 0.3, \"size\": 3, \"color\": \"#B4BEFE\"})\n",
    "    fig.update_layout(title={\"text\": f\"{col} vs popularity\", \"font\": {\"size\": 24}})\n",
    "    fig.show()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Header 1\n",
    "\n",
    "## Header 2\n",
    "\n",
    "### Header 3.1"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "cols = [\n",
    "    \"valence\",\n",
    "    \"acousticness\",\n",
    "    \"danceability\",\n",
    "    \"duration_min\",\n",
    "    \"energy\",\n",
    "    \"instrumentalness\",\n",
    "    \"liveness\",\n",
    "    \"loudness\",\n",
    "    \"year\",\n",
    "    \"speechiness\",\n",
    "    \"tempo\",\n",
    "]\n",
    "\n",
    "plt.figure(figsize=(15, 10))\n",
    "\n",
    "for i, col in enumerate(cols):\n",
    "    ax = plt.subplot(3, 4, i + 1)\n",
    "    sns.regplot(\n",
    "        data=df,\n",
    "        x=\"popularity\",\n",
    "        y=col,\n",
    "        ax=ax,\n",
    "        scatter_kws={\"alpha\": 0.5},\n",
    "        line_kws={\"color\": \"#F38BA8\"},\n",
    "    )\n",
    "\n",
    "plt.tight_layout()\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "cols = [\n",
    "    \"valence\",\n",
    "    \"acousticness\",\n",
    "    \"danceability\",\n",
    "    \"duration_min\",\n",
    "    \"energy\",\n",
    "    \"instrumentalness\",\n",
    "    \"liveness\",\n",
    "    \"loudness\",\n",
    "    \"year\",\n",
    "    \"speechiness\",\n",
    "    \"tempo\",\n",
    "    \"popularity\",\n",
    "]\n",
    "\n",
    "plt.figure(figsize=(10, 7))\n",
    "mask = np.triu(np.ones_like(df[cols].corr()))\n",
    "sns.heatmap(\n",
    "    df[cols].corr(),\n",
    "    annot=True,\n",
    "    fmt=\".2f\",\n",
    "    cmap=\"Blues\",\n",
    "    mask=mask,\n",
    ")\n",
    "plt.grid(visible=False)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "df[\"first_artist\"] = (\n",
    "    df[\"artists\"]\n",
    "    .apply(lambda x: str(x).split(\"x\")[0])\n",
    "    .apply(lambda x: str(x).replace(\"[\", \"\"))\n",
    "    .apply(lambda x: str(x).replace(\"]\", \"\"))\n",
    "    .apply(lambda x: str(x).replace(\"'\", \"\"))\n",
    ")\n",
    "df = df.drop(\"artists\", axis=1)\n",
    "df[\"first_artist\"] = df[\"first_artist\"].apply(lambda x: str(x).split(\",\")[0])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "popularity_check = (\n",
    "    df.groupby([\"first_artist\"], as_index=False)[\"popularity\"]\n",
    "    .agg({\"mean\", \"count\", \"median\"})\n",
    "    .sort_values(by=\"mean\", ascending=False)\n",
    "    .reset_index(drop=True)\n",
    ")\n",
    "\n",
    "popularity_check = popularity_check.drop(16091, axis=0)\n",
    "popularity_check = popularity_check.drop(16086, axis=0)\n",
    "popularity_check = popularity_check.drop(16429, axis=0)\n",
    "\n",
    "to_drop = popularity_check[popularity_check[\"count\"] <= 45].index\n",
    "popularity_check = popularity_check.drop(to_drop)\n",
    "popularity_check = popularity_check.sort_values(by=\"mean\", ascending=False).head(50)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Header 1\n",
    "\n",
    "## Header 2\n",
    "\n",
    "### Header 3.1"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "top_50_artists = pd.DataFrame()\n",
    "\n",
    "for i in popularity_check[\"first_artist\"].unique():\n",
    "    artist = df.query(\"first_artist == @i\")\n",
    "    top_50_artists = pd.concat([top_50_artists, artist], axis=0)\n",
    "\n",
    "top_50_artists = top_50_artists.reset_index(drop=True)\n",
    "top_50_artists.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "plt.figure(figsize=(12, 8))\n",
    "(\n",
    "    top_50_artists[\"first_artist\"]\n",
    "    .value_counts()\n",
    "    .sort_values(ascending=True)\n",
    "    .plot(kind=\"barh\")\n",
    ")\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "top_50_artists[\"decade\"].value_counts().sort_values(ascending=True).plot(kind=\"barh\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "cols = [\n",
    "    \"valence\",\n",
    "    \"acousticness\",\n",
    "    \"danceability\",\n",
    "    \"duration_min\",\n",
    "    \"energy\",\n",
    "    \"instrumentalness\",\n",
    "    \"liveness\",\n",
    "    \"loudness\",\n",
    "    \"year\",\n",
    "    \"speechiness\",\n",
    "    \"tempo\",\n",
    "]\n",
    "\n",
    "plt.figure(figsize=(15, 10))\n",
    "\n",
    "for i, col in enumerate(cols):\n",
    "    ax = plt.subplot(3, 4, i + 1)\n",
    "    sns.kdeplot(data=top_50_artists, x=col, hue=\"first_artist\", legend=False)\n",
    "\n",
    "plt.tight_layout()\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Header 1\n",
    "\n",
    "## Header 2\n",
    "\n",
    "### Header 3.1"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "metadata": {}
   },
   "outputs": [],
   "source": [
    "bins = pd.IntervalIndex.from_breaks(\n",
    "    [1920, 1930, 1940, 1950, 1960, 1970, 1980, 1990, 2000, 2010, 2020]\n",
    ")\n",
    "\n",
    "df[\"decade\"] = pd.cut(df[\"year\"], bins).astype(\"str\")\n",
    "\n",
    "map_decade = {\n",
    "    \"(1920, 1930]\": \"1920s\",\n",
    "    \"(1930, 1940]\": \"1930s\",\n",
    "    \"(1940, 1950]\": \"1940s\",\n",
    "    \"(1950, 1960]\": \"1950s\",\n",
    "    \"(1960, 1970]\": \"1960s\",\n",
    "    \"(1970, 1980]\": \"1970s\",\n",
    "    \"(1980, 1990]\": \"1980s\",\n",
    "    \"(1990, 2000]\": \"1990s\",\n",
    "    \"(2000, 2010]\": \"2000s\",\n",
    "    \"(2010, 2020]\": \"2010s\",\n",
    "}\n",
    "\n",
    "df[\"decade\"] = df[\"decade\"].map(map_decade)\n",
    "\n",
    "df.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "metadata": {}
   },
   "outputs": [],
   "source": [
    "decade_counts = (\n",
    "    df[\"decade\"].value_counts().reset_index().sort_values(by=\"decade\", ascending=True)\n",
    ")\n",
    "\n",
    "fig = px.bar(\n",
    "    data_frame=decade_counts,\n",
    "    y=\"decade\",\n",
    "    x=\"count\",\n",
    "    color=\"count\",\n",
    "    color_continuous_scale=px.colors.sequential.Sunset,\n",
    "    text_auto=True,\n",
    ")\n",
    "\n",
    "fig.update_layout(\n",
    "    title={\"text\": \"Count of songs per decade\", \"font\": {\"size\": 24}},\n",
    "    coloraxis_colorbar={\n",
    "        \"title\": \"Count\",\n",
    "        \"thicknessmode\": \"pixels\",\n",
    "        \"thickness\": 20,\n",
    "        \"lenmode\": \"pixels\",\n",
    "        \"len\": 500,\n",
    "        \"yanchor\": \"top\",\n",
    "        \"xanchor\": \"right\",\n",
    "        \"y\": 1.15,\n",
    "        \"x\": 0.95,\n",
    "        \"orientation\": \"h\",\n",
    "    },\n",
    "    margin={\"r\": 10},\n",
    ")\n",
    "\n",
    "fig.update_xaxes(title=\"Count\")\n",
    "fig.update_yaxes(title=\"Decades\")\n",
    "fig.show()\n",
    "\n",
    "del decade_counts"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "metadata": {}
   },
   "outputs": [],
   "source": [
    "df = df.query(\"duration_min <= 5\")"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Header 1.2\n",
    "\n",
    "## Header 2.2\n",
    "\n",
    "### Header 3.4"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "metadata": {}
   },
   "outputs": [],
   "source": [
    "decade_counts = (\n",
    "    df[\"decade\"].value_counts().reset_index().sort_values(by=\"decade\", ascending=True)\n",
    ")\n",
    "\n",
    "fig = px.bar(\n",
    "    data_frame=decade_counts,\n",
    "    y=\"decade\",\n",
    "    x=\"count\",\n",
    "    color=\"count\",\n",
    "    color_continuous_scale=px.colors.sequential.Sunset,\n",
    "    text_auto=True,\n",
    ")\n",
    "\n",
    "fig.update_layout(\n",
    "    title={\"text\": \"Count of songs per decade (< 5min)\", \"font\": {\"size\": 24}},\n",
    "    coloraxis_colorbar={\n",
    "        \"title\": \"Count\",\n",
    "        \"thicknessmode\": \"pixels\",\n",
    "        \"thickness\": 20,\n",
    "        \"lenmode\": \"pixels\",\n",
    "        \"len\": 500,\n",
    "        \"yanchor\": \"top\",\n",
    "        \"xanchor\": \"right\",\n",
    "        \"y\": 1.15,\n",
    "        \"x\": 0.95,\n",
    "        \"orientation\": \"h\",\n",
    "    },\n",
    "    margin={\"r\": 10},\n",
    ")\n",
    "\n",
    "fig.update_xaxes(title=\"Count\")\n",
    "fig.update_yaxes(title=\"Decades\")\n",
    "fig.show()\n",
    "\n",
    "del decade_counts"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "metadata": {}
   },
   "outputs": [],
   "source": [
    "cols = [\n",
    "    \"valence\",\n",
    "    \"acousticness\",\n",
    "    \"danceability\",\n",
    "    \"duration_min\",\n",
    "    \"energy\",\n",
    "    \"instrumentalness\",\n",
    "    \"liveness\",\n",
    "    \"loudness\",\n",
    "    \"popularity\",\n",
    "    \"speechiness\",\n",
    "    \"tempo\",\n",
    "]\n",
    "for col in cols:\n",
    "    fig = px.histogram(\n",
    "        data_frame=df,\n",
    "        x=col,\n",
    "        color=\"decade\",\n",
    "        color_discrete_sequence=px.colors.qualitative.Light24,\n",
    "    )\n",
    "    fig.update_traces(opacity=0.7)\n",
    "    fig.update_layout(\n",
    "        bargap=0.1,\n",
    "        bargroupgap=0.05,\n",
    "        barmode=\"stack\",\n",
    "        title={\"text\": f\"Histogram of {col} per decade\", \"font\": {\"size\": 24}},\n",
    "        legend={\"title\": \"Decade\"},\n",
    "    )\n",
    "    fig.update_yaxes(title=\"Count\")\n",
    "    fig.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "metadata": {}
   },
   "outputs": [],
   "source": [
    "decade_mean = df.groupby(\"decade\")[cols].mean()\n",
    "\n",
    "fig = make_subplots(\n",
    "    rows=4,\n",
    "    cols=3,\n",
    "    subplot_titles=(\n",
    "        decade_mean.columns[0],\n",
    "        decade_mean.columns[1],\n",
    "        decade_mean.columns[2],\n",
    "        decade_mean.columns[3],\n",
    "        decade_mean.columns[4],\n",
    "        decade_mean.columns[5],\n",
    "        decade_mean.columns[6],\n",
    "        decade_mean.columns[7],\n",
    "        decade_mean.columns[8],\n",
    "        decade_mean.columns[9],\n",
    "        decade_mean.columns[10],\n",
    "    ),\n",
    "    vertical_spacing=0.1,\n",
    ")\n",
    "\n",
    "fig.add_trace(\n",
    "    go.Bar(\n",
    "        y=decade_mean.index,\n",
    "        x=decade_mean.iloc[:, 0],\n",
    "        name=decade_mean.columns[0],\n",
    "        orientation=\"h\",\n",
    "    ),\n",
    "    row=1,\n",
    "    col=1,\n",
    ")\n",
    "\n",
    "fig.add_trace(\n",
    "    go.Bar(\n",
    "        y=decade_mean.index,\n",
    "        x=decade_mean.iloc[:, 1],\n",
    "        name=decade_mean.columns[1],\n",
    "        orientation=\"h\",\n",
    "    ),\n",
    "    row=1,\n",
    "    col=2,\n",
    ")\n",
    "\n",
    "fig.add_trace(\n",
    "    go.Bar(\n",
    "        y=decade_mean.index,\n",
    "        x=decade_mean.iloc[:, 2],\n",
    "        name=decade_mean.columns[2],\n",
    "        orientation=\"h\",\n",
    "    ),\n",
    "    row=1,\n",
    "    col=3,\n",
    ")\n",
    "\n",
    "fig.add_trace(\n",
    "    go.Bar(\n",
    "        y=decade_mean.index,\n",
    "        x=decade_mean.iloc[:, 3],\n",
    "        name=decade_mean.columns[3],\n",
    "        orientation=\"h\",\n",
    "    ),\n",
    "    row=2,\n",
    "    col=1,\n",
    ")\n",
    "\n",
    "fig.add_trace(\n",
    "    go.Bar(\n",
    "        y=decade_mean.index,\n",
    "        x=decade_mean.iloc[:, 4],\n",
    "        name=decade_mean.columns[4],\n",
    "        orientation=\"h\",\n",
    "    ),\n",
    "    row=2,\n",
    "    col=2,\n",
    ")\n",
    "\n",
    "fig.add_trace(\n",
    "    go.Bar(\n",
    "        y=decade_mean.index,\n",
    "        x=decade_mean.iloc[:, 5],\n",
    "        name=decade_mean.columns[5],\n",
    "        orientation=\"h\",\n",
    "    ),\n",
    "    row=2,\n",
    "    col=3,\n",
    ")\n",
    "\n",
    "fig.add_trace(\n",
    "    go.Bar(\n",
    "        y=decade_mean.index,\n",
    "        x=decade_mean.iloc[:, 6],\n",
    "        name=decade_mean.columns[6],\n",
    "        orientation=\"h\",\n",
    "    ),\n",
    "    row=3,\n",
    "    col=1,\n",
    ")\n",
    "\n",
    "fig.add_trace(\n",
    "    go.Bar(\n",
    "        y=decade_mean.index,\n",
    "        x=decade_mean.iloc[:, 7],\n",
    "        name=decade_mean.columns[7],\n",
    "        orientation=\"h\",\n",
    "    ),\n",
    "    row=3,\n",
    "    col=2,\n",
    ")\n",
    "\n",
    "fig.add_trace(\n",
    "    go.Bar(\n",
    "        y=decade_mean.index,\n",
    "        x=decade_mean.iloc[:, 8],\n",
    "        name=decade_mean.columns[8],\n",
    "        orientation=\"h\",\n",
    "    ),\n",
    "    row=3,\n",
    "    col=3,\n",
    ")\n",
    "\n",
    "fig.add_trace(\n",
    "    go.Bar(\n",
    "        y=decade_mean.index,\n",
    "        x=decade_mean.iloc[:, 9],\n",
    "        name=decade_mean.columns[9],\n",
    "        orientation=\"h\",\n",
    "    ),\n",
    "    row=4,\n",
    "    col=1,\n",
    ")\n",
    "\n",
    "fig.add_trace(\n",
    "    go.Bar(\n",
    "        y=decade_mean.index,\n",
    "        x=decade_mean.iloc[:, 10],\n",
    "        name=decade_mean.columns[10],\n",
    "        orientation=\"h\",\n",
    "    ),\n",
    "    row=4,\n",
    "    col=2,\n",
    ")\n",
    "\n",
    "fig.update_layout(\n",
    "    title={\"text\": \"Mean Musical Values per Decade\", \"font\": {\"size\": 22}},\n",
    "    legend={\n",
    "        \"orientation\": \"v\",\n",
    "        \"yanchor\": \"top\",\n",
    "        \"y\": 0.2,\n",
    "        \"xanchor\": \"right\",\n",
    "        \"x\": 0.9,\n",
    "    },\n",
    "    margin={\"b\": 10, \"r\": 10},\n",
    "    height=980,\n",
    ")\n",
    "\n",
    "fig.show()\n",
    "\n",
    "del decade_mean"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "metadata": {}
   },
   "outputs": [],
   "source": [
    "decade_median = df.groupby(\"decade\")[cols].median()\n",
    "\n",
    "fig = make_subplots(\n",
    "    rows=4,\n",
    "    cols=3,\n",
    "    subplot_titles=(\n",
    "        decade_median.columns[0],\n",
    "        decade_median.columns[1],\n",
    "        decade_median.columns[2],\n",
    "        decade_median.columns[3],\n",
    "        decade_median.columns[4],\n",
    "        decade_median.columns[5],\n",
    "        decade_median.columns[6],\n",
    "        decade_median.columns[7],\n",
    "        decade_median.columns[8],\n",
    "        decade_median.columns[9],\n",
    "        decade_median.columns[10],\n",
    "    ),\n",
    "    vertical_spacing=0.1,\n",
    ")\n",
    "\n",
    "fig.add_trace(\n",
    "    go.Bar(\n",
    "        y=decade_median.index,\n",
    "        x=decade_median.iloc[:, 0],\n",
    "        name=decade_median.columns[0],\n",
    "        orientation=\"h\",\n",
    "    ),\n",
    "    row=1,\n",
    "    col=1,\n",
    ")\n",
    "\n",
    "fig.add_trace(\n",
    "    go.Bar(\n",
    "        y=decade_median.index,\n",
    "        x=decade_median.iloc[:, 1],\n",
    "        name=decade_median.columns[1],\n",
    "        orientation=\"h\",\n",
    "    ),\n",
    "    row=1,\n",
    "    col=2,\n",
    ")\n",
    "\n",
    "fig.add_trace(\n",
    "    go.Bar(\n",
    "        y=decade_median.index,\n",
    "        x=decade_median.iloc[:, 2],\n",
    "        name=decade_median.columns[2],\n",
    "        orientation=\"h\",\n",
    "    ),\n",
    "    row=1,\n",
    "    col=3,\n",
    ")\n",
    "\n",
    "fig.add_trace(\n",
    "    go.Bar(\n",
    "        y=decade_median.index,\n",
    "        x=decade_median.iloc[:, 3],\n",
    "        name=decade_median.columns[3],\n",
    "        orientation=\"h\",\n",
    "    ),\n",
    "    row=2,\n",
    "    col=1,\n",
    ")\n",
    "\n",
    "fig.add_trace(\n",
    "    go.Bar(\n",
    "        y=decade_median.index,\n",
    "        x=decade_median.iloc[:, 4],\n",
    "        name=decade_median.columns[4],\n",
    "        orientation=\"h\",\n",
    "    ),\n",
    "    row=2,\n",
    "    col=2,\n",
    ")\n",
    "\n",
    "fig.add_trace(\n",
    "    go.Bar(\n",
    "        y=decade_median.index,\n",
    "        x=decade_median.iloc[:, 5],\n",
    "        name=decade_median.columns[5],\n",
    "        orientation=\"h\",\n",
    "    ),\n",
    "    row=2,\n",
    "    col=3,\n",
    ")\n",
    "\n",
    "fig.add_trace(\n",
    "    go.Bar(\n",
    "        y=decade_median.index,\n",
    "        x=decade_median.iloc[:, 6],\n",
    "        name=decade_median.columns[6],\n",
    "        orientation=\"h\",\n",
    "    ),\n",
    "    row=3,\n",
    "    col=1,\n",
    ")\n",
    "\n",
    "fig.add_trace(\n",
    "    go.Bar(\n",
    "        y=decade_median.index,\n",
    "        x=decade_median.iloc[:, 7],\n",
    "        name=decade_median.columns[7],\n",
    "        orientation=\"h\",\n",
    "    ),\n",
    "    row=3,\n",
    "    col=2,\n",
    ")\n",
    "\n",
    "fig.add_trace(\n",
    "    go.Bar(\n",
    "        y=decade_median.index,\n",
    "        x=decade_median.iloc[:, 8],\n",
    "        name=decade_median.columns[8],\n",
    "        orientation=\"h\",\n",
    "    ),\n",
    "    row=3,\n",
    "    col=3,\n",
    ")\n",
    "\n",
    "fig.add_trace(\n",
    "    go.Bar(\n",
    "        y=decade_median.index,\n",
    "        x=decade_median.iloc[:, 9],\n",
    "        name=decade_median.columns[9],\n",
    "        orientation=\"h\",\n",
    "    ),\n",
    "    row=4,\n",
    "    col=1,\n",
    ")\n",
    "\n",
    "fig.add_trace(\n",
    "    go.Bar(\n",
    "        y=decade_median.index,\n",
    "        x=decade_median.iloc[:, 10],\n",
    "        name=decade_median.columns[10],\n",
    "        orientation=\"h\",\n",
    "    ),\n",
    "    row=4,\n",
    "    col=2,\n",
    ")\n",
    "\n",
    "fig.update_layout(\n",
    "    title={\"text\": \"Median Musical Values per Decade\", \"font\": {\"size\": 22}},\n",
    "    legend={\n",
    "        \"orientation\": \"v\",\n",
    "        \"yanchor\": \"top\",\n",
    "        \"y\": 0.2,\n",
    "        \"xanchor\": \"right\",\n",
    "        \"x\": 0.9,\n",
    "    },\n",
    "    margin={\"b\": 10, \"r\": 10},\n",
    "    height=980,\n",
    ")\n",
    "\n",
    "fig.show()\n",
    "\n",
    "del decade_median"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "metadata": {}
   },
   "outputs": [],
   "source": [
    "explicit_count = (\n",
    "    df.groupby([\"decade\", \"explicit\"], as_index=False)[\"year\"]\n",
    "    .count()\n",
    "    .rename(columns={\"year\": \"count\"})\n",
    ")\n",
    "key_count = (\n",
    "    df.groupby([\"decade\", \"key\"], as_index=False)[\"year\"]\n",
    "    .count()\n",
    "    .rename(columns={\"year\": \"count\"})\n",
    ")\n",
    "mode_count = (\n",
    "    df.groupby([\"decade\", \"mode\"], as_index=False)[\"year\"]\n",
    "    .count()\n",
    "    .rename(columns={\"year\": \"count\"})\n",
    ")\n",
    "\n",
    "fig = px.histogram(\n",
    "    data_frame=explicit_count,\n",
    "    x=\"decade\",\n",
    "    y=\"count\",\n",
    "    color=\"explicit\",\n",
    "    histfunc=\"sum\",\n",
    "    color_discrete_sequence=px.colors.qualitative.Pastel,\n",
    "    text_auto=True,\n",
    ")\n",
    "fig.update_layout(\n",
    "    title={\"text\": \"Explicit Count per Decade\", \"font\": {\"size\": 24}},\n",
    "    bargap=0.2,\n",
    "    bargroupgap=0.1,\n",
    "    barmode=\"group\",\n",
    "    xaxis_title=\"Decade\",\n",
    "    yaxis_title=\"Count\",\n",
    ")\n",
    "fig.show()\n",
    "\n",
    "fig = px.histogram(\n",
    "    data_frame=mode_count,\n",
    "    x=\"decade\",\n",
    "    y=\"count\",\n",
    "    color=\"mode\",\n",
    "    histfunc=\"sum\",\n",
    "    color_discrete_sequence=px.colors.qualitative.Pastel,\n",
    "    text_auto=True,\n",
    ")\n",
    "fig.update_layout(\n",
    "    title={\"text\": \"Mode Count per Decade\", \"font\": {\"size\": 24}},\n",
    "    bargap=0.2,\n",
    "    bargroupgap=0.1,\n",
    "    barmode=\"group\",\n",
    "    xaxis_title=\"Decade\",\n",
    "    yaxis_title=\"Count\",\n",
    ")\n",
    "fig.show()\n",
    "\n",
    "fig = px.histogram(\n",
    "    data_frame=key_count,\n",
    "    x=\"decade\",\n",
    "    y=\"count\",\n",
    "    color=\"key\",\n",
    "    histfunc=\"sum\",\n",
    "    color_discrete_sequence=px.colors.qualitative.Pastel,\n",
    "    text_auto=True,\n",
    ")\n",
    "fig.update_layout(\n",
    "    title={\"text\": \"Key Count per Decade\", \"font\": {\"size\": 24}},\n",
    "    bargap=0.2,\n",
    "    bargroupgap=0.1,\n",
    "    barmode=\"stack\",\n",
    "    xaxis_title=\"Decade\",\n",
    "    yaxis_title=\"Count\",\n",
    ")\n",
    "fig.show()\n",
    "\n",
    "del (mode_count, key_count, explicit_count)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "metadata": {}
   },
   "outputs": [],
   "source": [
    "cols = [\n",
    "    \"valence\",\n",
    "    \"acousticness\",\n",
    "    \"danceability\",\n",
    "    \"duration_min\",\n",
    "    \"energy\",\n",
    "    \"instrumentalness\",\n",
    "    \"liveness\",\n",
    "    \"loudness\",\n",
    "    \"year\",\n",
    "    \"speechiness\",\n",
    "    \"tempo\",\n",
    "]\n",
    "\n",
    "for col in cols:\n",
    "\n",
    "    fig = px.scatter(\n",
    "        data_frame=df,\n",
    "        x=col,\n",
    "        y=\"popularity\",\n",
    "        trendline=\"ols\",\n",
    "        trendline_color_override=\"#A6E3A1\",\n",
    "    )\n",
    "    fig.update_traces(marker={\"opacity\": 0.3, \"size\": 3, \"color\": \"#B4BEFE\"})\n",
    "    fig.update_layout(title={\"text\": f\"{col} vs popularity\", \"font\": {\"size\": 24}})\n",
    "    fig.show()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Header 1\n",
    "\n",
    "## Header 2\n",
    "\n",
    "### Header 3.1"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "metadata": {}
   },
   "outputs": [],
   "source": [
    "cols = [\n",
    "    \"valence\",\n",
    "    \"acousticness\",\n",
    "    \"danceability\",\n",
    "    \"duration_min\",\n",
    "    \"energy\",\n",
    "    \"instrumentalness\",\n",
    "    \"liveness\",\n",
    "    \"loudness\",\n",
    "    \"year\",\n",
    "    \"speechiness\",\n",
    "    \"tempo\",\n",
    "]\n",
    "\n",
    "plt.figure(figsize=(15, 10))\n",
    "\n",
    "for i, col in enumerate(cols):\n",
    "    ax = plt.subplot(3, 4, i + 1)\n",
    "    sns.regplot(\n",
    "        data=df,\n",
    "        x=\"popularity\",\n",
    "        y=col,\n",
    "        ax=ax,\n",
    "        scatter_kws={\"alpha\": 0.5},\n",
    "        line_kws={\"color\": \"#F38BA8\"},\n",
    "    )\n",
    "\n",
    "plt.tight_layout()\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "metadata": {}
   },
   "outputs": [],
   "source": [
    "cols = [\n",
    "    \"valence\",\n",
    "    \"acousticness\",\n",
    "    \"danceability\",\n",
    "    \"duration_min\",\n",
    "    \"energy\",\n",
    "    \"instrumentalness\",\n",
    "    \"liveness\",\n",
    "    \"loudness\",\n",
    "    \"year\",\n",
    "    \"speechiness\",\n",
    "    \"tempo\",\n",
    "    \"popularity\",\n",
    "]\n",
    "\n",
    "plt.figure(figsize=(10, 7))\n",
    "mask = np.triu(np.ones_like(df[cols].corr()))\n",
    "sns.heatmap(\n",
    "    df[cols].corr(),\n",
    "    annot=True,\n",
    "    fmt=\".2f\",\n",
    "    cmap=\"Blues\",\n",
    "    mask=mask,\n",
    ")\n",
    "plt.grid(visible=False)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "metadata": {}
   },
   "outputs": [],
   "source": [
    "df[\"first_artist\"] = (\n",
    "    df[\"artists\"]\n",
    "    .apply(lambda x: str(x).split(\"x\")[0])\n",
    "    .apply(lambda x: str(x).replace(\"[\", \"\"))\n",
    "    .apply(lambda x: str(x).replace(\"]\", \"\"))\n",
    "    .apply(lambda x: str(x).replace(\"'\", \"\"))\n",
    ")\n",
    "df = df.drop(\"artists\", axis=1)\n",
    "df[\"first_artist\"] = df[\"first_artist\"].apply(lambda x: str(x).split(\",\")[0])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "metadata": {}
   },
   "outputs": [],
   "source": [
    "popularity_check = (\n",
    "    df.groupby([\"first_artist\"], as_index=False)[\"popularity\"]\n",
    "    .agg({\"mean\", \"count\", \"median\"})\n",
    "    .sort_values(by=\"mean\", ascending=False)\n",
    "    .reset_index(drop=True)\n",
    ")\n",
    "\n",
    "popularity_check = popularity_check.drop(16091, axis=0)\n",
    "popularity_check = popularity_check.drop(16086, axis=0)\n",
    "popularity_check = popularity_check.drop(16429, axis=0)\n",
    "\n",
    "to_drop = popularity_check[popularity_check[\"count\"] <= 45].index\n",
    "popularity_check = popularity_check.drop(to_drop)\n",
    "popularity_check = popularity_check.sort_values(by=\"mean\", ascending=False).head(50)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Header 1\n",
    "\n",
    "## Header 2\n",
    "\n",
    "### Header 3.1"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "metadata": {}
   },
   "outputs": [],
   "source": [
    "top_50_artists = pd.DataFrame()\n",
    "\n",
    "for i in popularity_check[\"first_artist\"].unique():\n",
    "    artist = df.query(\"first_artist == @i\")\n",
    "    top_50_artists = pd.concat([top_50_artists, artist], axis=0)\n",
    "\n",
    "top_50_artists = top_50_artists.reset_index(drop=True)\n",
    "top_50_artists.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "metadata": {}
   },
   "outputs": [],
   "source": [
    "plt.figure(figsize=(12, 8))\n",
    "(\n",
    "    top_50_artists[\"first_artist\"]\n",
    "    .value_counts()\n",
    "    .sort_values(ascending=True)\n",
    "    .plot(kind=\"barh\")\n",
    ")\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "metadata": {}
   },
   "outputs": [],
   "source": [
    "top_50_artists[\"decade\"].value_counts().sort_values(ascending=True).plot(kind=\"barh\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "metadata": {}
   },
   "outputs": [],
   "source": [
    "cols = [\n",
    "    \"valence\",\n",
    "    \"acousticness\",\n",
    "    \"danceability\",\n",
    "    \"duration_min\",\n",
    "    \"energy\",\n",
    "    \"instrumentalness\",\n",
    "    \"liveness\",\n",
    "    \"loudness\",\n",
    "    \"year\",\n",
    "    \"speechiness\",\n",
    "    \"tempo\",\n",
    "]\n",
    "\n",
    "plt.figure(figsize=(15, 10))\n",
    "\n",
    "for i, col in enumerate(cols):\n",
    "    ax = plt.subplot(3, 4, i + 1)\n",
    "    sns.kdeplot(data=top_50_artists, x=col, hue=\"first_artist\", legend=False)\n",
    "\n",
    "plt.tight_layout()\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Header 1\n",
    "\n",
    "## Header 2\n",
    "\n",
    "### Header 3.1"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "metadata": {}
   },
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.9.13"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}