notebooks/6 - Pandas Data Manipulation.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Pandas\n",
    "\n",
    "Jay Urbain, PhD\n",
    "\n",
    "6/30/2018\n",
    "\n",
    "Pandas is a package built on top of NumPy, and provides an efficient implementation of a `DataFrame`.\n",
    "\n",
    "`DataFrames` are essentially multidimensional arrays with row and column labels, and often with heterogeneous types and missing data.\n",
    "\n",
    "In addition to providing storage interface for labeled data, Pandas implements a number of  data operations similar to operations provided by database frameworks and spreadsheet programs.\n",
    "\n",
    "NumPy's ``ndarray`` data structure provides features for the type of clean, well-organized data typically seen in numerical computing tasks. While it serves this purpose well, its limitations become clear when we need more flexibility, e.g., attaching labels to data, working with missing data, etc. NumPy operations that do not map well to element-wise broadcasting, e.g., groupings, pivots, etc., each of which is an important piece of analyzing less structured data available.\n",
    "\n",
    "Pandas ``Series`` and ``DataFrame`` objects build on the NumPy array structure and provide efficient access to these sorts of \"data munging\" tasks that occupy much of a data scientist's time.\n",
    "\n",
    "References:  \n",
    "http://pandas.pydata.org/  \n",
    "http://pandas.pydata.org/pandas-docs/stable/10min.html   \n",
    "https://jakevdp.github.io/PythonDataScienceHandbook/   \n",
    "http://shop.oreilly.com/product/0636920033400.do  "
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "#### Data structures\n",
    "\n",
    "- Series  \n",
    "- Dataframe\n",
    "\n",
    "Quick overview of the fundamental data structures in Pandas:   \n",
    "- The fundamental behavior about data types, indexing, and axis labeling / alignment apply across all of the objects.  \n",
    "- Maintaining an intrinsic link between labels and data.  \n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "#### Series data structure\n",
    "\n",
    "Series is a one-dimensional labeled array capable of holding any data type (integers, strings, floating point numbers, Python objects, etc.). \n",
    "\n",
    "The axis labels are collectively referred to as the index. \n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Can create data from:\n",
    "- a Python dict  \n",
    "- an ndarray  \n",
    "- a scalar value   "
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "#### Standard imports"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "'0.23.1'"
      ]
     },
     "execution_count": 1,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "import pandas as pd\n",
    "import numpy as np\n",
    "import matplotlib.pyplot as plt\n",
    "\n",
    "pd.__version__"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [],
   "source": [
    "pd.crosstab?"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "#### Pandas Series object\n",
    "\n",
    "A series can be creted from a list, array, dictionary, etc.\n",
    "\n",
    "Creating a series from an ndarray"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [],
   "source": [
    "np.random.randn?"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 37,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "a   -1.788708\n",
       "b   -0.102754\n",
       "c   -0.468151\n",
       "d    0.145755\n",
       "e   -0.316287\n",
       "dtype: float64"
      ]
     },
     "execution_count": 37,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# index must be same length as data\n",
    "data = np.random.randn(5)\n",
    "index = ['a', 'b', 'c', 'd', 'e']\n",
    "s = pd.Series(data, index=index)\n",
    "s"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "The Series wraps both a sequence of values and a sequence of indices, which can accessed with the `values` and `index` attributes. The values are a familiar NumPy array."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "[0.80473722 0.74082922 0.55581732 1.13562725 0.42238903]\n",
      "Index(['a', 'b', 'c', 'd', 'e'], dtype='object')\n"
     ]
    }
   ],
   "source": [
    "print(s.values)\n",
    "print(s.index)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Creating a series from a list"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "a    1\n",
       "b    2\n",
       "c    3\n",
       "d    4\n",
       "e    5\n",
       "dtype: int64"
      ]
     },
     "execution_count": 6,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# index must be same length as data\n",
    "data = [1,2,3,4,5]\n",
    "index = ['a', 'b', 'c', 'd', 'e']\n",
    "r = pd.Series(data, index=index)\n",
    "r"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "*Note: Pandas allows duplicate index keys (for performance reasons)*\n",
    "\n",
    "If an index is not provided, one will be created."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0    1\n",
       "1    2\n",
       "2    3\n",
       "3    4\n",
       "4    5\n",
       "dtype: int64"
      ]
     },
     "execution_count": 7,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# index must be same length as data\n",
    "data = [1,2,3,4,5]\n",
    "r = pd.Series(data)\n",
    "r"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "From dict\n",
    "\n",
    "If no index is provided, the labels will be used and placed in the order of the dict."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "b    1\n",
       "a    0\n",
       "c    2\n",
       "dtype: int64"
      ]
     },
     "execution_count": 8,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "d = {'b' : 1, 'a' : 0, 'c' : 2}\n",
    "pd.Series(d)\n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "From scalar\n",
    "\n",
    "An index is require for scalar data."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 23,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "a    5.0\n",
       "b    5.0\n",
       "c    5.0\n",
       "d    5.0\n",
       "e    5.0\n",
       "dtype: float64"
      ]
     },
     "execution_count": 23,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "pd.Series(5., index=['a', 'b', 'c', 'd', 'e'])"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Series are similar to NumPy ndarray and can be accessed using indexing `[]`,"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 38,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "-0.10275365630710048"
      ]
     },
     "execution_count": 38,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "s.iloc[1]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 39,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "-1.788707531313005"
      ]
     },
     "execution_count": 39,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "s['a']"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 40,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "a   -1.788708\n",
       "b   -0.102754\n",
       "dtype: float64"
      ]
     },
     "execution_count": 40,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "s[:-3]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 41,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "-1.788707531313005"
      ]
     },
     "execution_count": 41,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "s.iloc[0]"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Implicit indexing versus explicit indexing"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 42,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "1    1\n",
       "2    2\n",
       "3    3\n",
       "4    4\n",
       "5    5\n",
       "dtype: int64"
      ]
     },
     "execution_count": 42,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "r.index = [1,2,3,4,5]\n",
    "r"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 26,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "1"
      ]
     },
     "execution_count": 26,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "r[1]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 27,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "1"
      ]
     },
     "execution_count": 27,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "r.loc[1]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 28,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "1"
      ]
     },
     "execution_count": 28,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "r.iloc[0]"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Filter / mask selection"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 29,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "1     True\n",
       "2    False\n",
       "3    False\n",
       "4     True\n",
       "5    False\n",
       "dtype: bool"
      ]
     },
     "execution_count": 29,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "s > s.median()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 30,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "1    0.804737\n",
       "4    1.135627\n",
       "dtype: float64"
      ]
     },
     "execution_count": 30,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "s[s > s.median()]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 31,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "4    1.135627\n",
       "3    0.555817\n",
       "1    0.804737\n",
       "dtype: float64"
      ]
     },
     "execution_count": 31,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "s[[4, 3, 1]]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 33,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "4    1.135627\n",
       "dtype: float64"
      ]
     },
     "execution_count": 33,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "s[[4]]"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Series are also dict-like.\n",
    "\n",
    "A Series is like a fixed-size `dict` in that you can get and set values by index label:\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 43,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "-1.788707531313005"
      ]
     },
     "execution_count": 43,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "s['a']"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 44,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "a    -1.788708\n",
       "b    -0.102754\n",
       "c    -0.468151\n",
       "d     0.145755\n",
       "e    12.000000\n",
       "dtype: float64"
      ]
     },
     "execution_count": 44,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "s['e'] = 12.\n",
    "s"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 45,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "True"
      ]
     },
     "execution_count": 45,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "'e' in s"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 46,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "False"
      ]
     },
     "execution_count": 46,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "'f' in s"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 47,
   "metadata": {},
   "outputs": [],
   "source": [
    "s.get('f')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 48,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "nan"
      ]
     },
     "execution_count": 48,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "s.get('f', np.nan)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 49,
   "metadata": {},
   "outputs": [
    {
     "ename": "KeyError",
     "evalue": "'f'",
     "output_type": "error",
     "traceback": [
      "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
      "\u001b[0;31mTypeError\u001b[0m                                 Traceback (most recent call last)",
      "\u001b[0;32m/Applications/anaconda/envs/py3.6tf1.3keras/lib/python3.6/site-packages/pandas/core/indexes/base.py\u001b[0m in \u001b[0;36mget_value\u001b[0;34m(self, series, key)\u001b[0m\n\u001b[1;32m   3109\u001b[0m             \u001b[0;32mtry\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m-> 3110\u001b[0;31m                 \u001b[0;32mreturn\u001b[0m \u001b[0mlibindex\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mget_value_box\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0ms\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mkey\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m   3111\u001b[0m             \u001b[0;32mexcept\u001b[0m \u001b[0mIndexError\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
      "\u001b[0;32mpandas/_libs/index.pyx\u001b[0m in \u001b[0;36mpandas._libs.index.get_value_box\u001b[0;34m()\u001b[0m\n",
      "\u001b[0;32mpandas/_libs/index.pyx\u001b[0m in \u001b[0;36mpandas._libs.index.get_value_box\u001b[0;34m()\u001b[0m\n",
      "\u001b[0;31mTypeError\u001b[0m: 'str' object cannot be interpreted as an integer",
      "\nDuring handling of the above exception, another exception occurred:\n",
      "\u001b[0;31mKeyError\u001b[0m                                  Traceback (most recent call last)",
      "\u001b[0;32m<ipython-input-49-c23937ec966b>\u001b[0m in \u001b[0;36m<module>\u001b[0;34m()\u001b[0m\n\u001b[0;32m----> 1\u001b[0;31m \u001b[0ms\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0;34m'f'\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m",
      "\u001b[0;32m/Applications/anaconda/envs/py3.6tf1.3keras/lib/python3.6/site-packages/pandas/core/series.py\u001b[0m in \u001b[0;36m__getitem__\u001b[0;34m(self, key)\u001b[0m\n\u001b[1;32m    765\u001b[0m         \u001b[0mkey\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mcom\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_apply_if_callable\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mkey\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    766\u001b[0m         \u001b[0;32mtry\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 767\u001b[0;31m             \u001b[0mresult\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mindex\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mget_value\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mkey\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m    768\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    769\u001b[0m             \u001b[0;32mif\u001b[0m \u001b[0;32mnot\u001b[0m \u001b[0mis_scalar\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mresult\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
      "\u001b[0;32m/Applications/anaconda/envs/py3.6tf1.3keras/lib/python3.6/site-packages/pandas/core/indexes/base.py\u001b[0m in \u001b[0;36mget_value\u001b[0;34m(self, series, key)\u001b[0m\n\u001b[1;32m   3116\u001b[0m                     \u001b[0;32mraise\u001b[0m \u001b[0mInvalidIndexError\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mkey\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   3117\u001b[0m                 \u001b[0;32melse\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m-> 3118\u001b[0;31m                     \u001b[0;32mraise\u001b[0m \u001b[0me1\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m   3119\u001b[0m             \u001b[0;32mexcept\u001b[0m \u001b[0mException\u001b[0m\u001b[0;34m:\u001b[0m  \u001b[0;31m# pragma: no cover\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   3120\u001b[0m                 \u001b[0;32mraise\u001b[0m \u001b[0me1\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
      "\u001b[0;32m/Applications/anaconda/envs/py3.6tf1.3keras/lib/python3.6/site-packages/pandas/core/indexes/base.py\u001b[0m in \u001b[0;36mget_value\u001b[0;34m(self, series, key)\u001b[0m\n\u001b[1;32m   3102\u001b[0m         \u001b[0;32mtry\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   3103\u001b[0m             return self._engine.get_value(s, k,\n\u001b[0;32m-> 3104\u001b[0;31m                                           tz=getattr(series.dtype, 'tz', None))\n\u001b[0m\u001b[1;32m   3105\u001b[0m         \u001b[0;32mexcept\u001b[0m \u001b[0mKeyError\u001b[0m \u001b[0;32mas\u001b[0m \u001b[0me1\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   3106\u001b[0m             \u001b[0;32mif\u001b[0m \u001b[0mlen\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m)\u001b[0m \u001b[0;34m>\u001b[0m \u001b[0;36m0\u001b[0m \u001b[0;32mand\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0minferred_type\u001b[0m \u001b[0;32min\u001b[0m \u001b[0;34m[\u001b[0m\u001b[0;34m'integer'\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m'boolean'\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
      "\u001b[0;32mpandas/_libs/index.pyx\u001b[0m in \u001b[0;36mpandas._libs.index.IndexEngine.get_value\u001b[0;34m()\u001b[0m\n",
      "\u001b[0;32mpandas/_libs/index.pyx\u001b[0m in \u001b[0;36mpandas._libs.index.IndexEngine.get_value\u001b[0;34m()\u001b[0m\n",
      "\u001b[0;32mpandas/_libs/index.pyx\u001b[0m in \u001b[0;36mpandas._libs.index.IndexEngine.get_loc\u001b[0;34m()\u001b[0m\n",
      "\u001b[0;32mpandas/_libs/hashtable_class_helper.pxi\u001b[0m in \u001b[0;36mpandas._libs.hashtable.PyObjectHashTable.get_item\u001b[0;34m()\u001b[0m\n",
      "\u001b[0;32mpandas/_libs/hashtable_class_helper.pxi\u001b[0m in \u001b[0;36mpandas._libs.hashtable.PyObjectHashTable.get_item\u001b[0;34m()\u001b[0m\n",
      "\u001b[0;31mKeyError\u001b[0m: 'f'"
     ]
    }
   ],
   "source": [
    "s['f']"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "#### Vectorized operations\n",
    "\n",
    "Like numpy, you can use vectorized operations."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 50,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "a    -1.788708\n",
       "b    -0.102754\n",
       "c    -0.468151\n",
       "d     0.145755\n",
       "e    12.000000\n",
       "dtype: float64"
      ]
     },
     "execution_count": 50,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "s"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 51,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "a    -3.577415\n",
       "b    -0.205507\n",
       "c    -0.936302\n",
       "d     0.291511\n",
       "e    24.000000\n",
       "dtype: float64"
      ]
     },
     "execution_count": 51,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "s+s"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 52,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "a    -3.577415\n",
       "b    -0.205507\n",
       "c    -0.936302\n",
       "d     0.291511\n",
       "e    24.000000\n",
       "dtype: float64"
      ]
     },
     "execution_count": 52,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "s*2"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 56,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "9.786143298934832"
      ]
     },
     "execution_count": 56,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "s.sum(axis=0)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "A key difference between Series and ndarray is that operations between Series automatically align the data based on label. \n",
    "\n",
    "So you can write computations without giving consideration to whether the Series involved have the same labels."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 57,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "a    -1.788708\n",
       "b    -0.102754\n",
       "c    -0.468151\n",
       "d     0.145755\n",
       "e    12.000000\n",
       "dtype: float64"
      ]
     },
     "execution_count": 57,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "s"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 58,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "b    -0.102754\n",
       "c    -0.468151\n",
       "d     0.145755\n",
       "e    12.000000\n",
       "dtype: float64"
      ]
     },
     "execution_count": 58,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "s[1:]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 59,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "a   -1.788708\n",
       "b   -0.102754\n",
       "c   -0.468151\n",
       "d    0.145755\n",
       "dtype: float64"
      ]
     },
     "execution_count": 59,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "s[:-1]"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "The result of an operation between unaligned Series will have the union of the indexes involved. "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 60,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "a         NaN\n",
       "b   -0.205507\n",
       "c   -0.936302\n",
       "d    0.291511\n",
       "e         NaN\n",
       "dtype: float64"
      ]
     },
     "execution_count": 60,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "s[1:] + s[:-1]\n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "#### Name attribute"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 61,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0   -1.251825\n",
       "1   -0.281578\n",
       "2   -0.511478\n",
       "3   -1.264711\n",
       "4    0.148580\n",
       "Name: Mel, dtype: float64"
      ]
     },
     "execution_count": 61,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "s = pd.Series(np.random.randn(5), name='Mel')\n",
    "s"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 62,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "'Mel'"
      ]
     },
     "execution_count": 62,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "s.name"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "#### Querying a Series"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 63,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "Archery           Bhutan\n",
       "Golf            Scotland\n",
       "Sumo               Japan\n",
       "Taekwondo    South Korea\n",
       "dtype: object"
      ]
     },
     "execution_count": 63,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "sports = {'Archery': 'Bhutan',\n",
    "          'Golf': 'Scotland',\n",
    "          'Sumo': 'Japan',\n",
    "          'Taekwondo': 'South Korea'}\n",
    "s = pd.Series(sports)\n",
    "s"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 64,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "'South Korea'"
      ]
     },
     "execution_count": 64,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "s.iloc[3] "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 65,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "'Scotland'"
      ]
     },
     "execution_count": 65,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "s.loc['Golf']"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "#### Series performance\n",
    "\n",
    "Create a large series to evaluate performance"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 66,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0    643\n",
       "1    589\n",
       "2    992\n",
       "3    444\n",
       "4    623\n",
       "dtype: int64"
      ]
     },
     "execution_count": 66,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "#this creates a big series of random numbers\n",
    "s = pd.Series(np.random.randint(0,1000,10000))\n",
    "s.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 67,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "10000"
      ]
     },
     "execution_count": 67,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "len(s)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 68,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "743 µs ± 39 µs per loop (mean ± std. dev. of 7 runs, 100 loops each)\n"
     ]
    }
   ],
   "source": [
    "%%timeit -n 100\n",
    "summary = 0\n",
    "for item in s:\n",
    "    summary+=item"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 69,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "171 µs ± 57.2 µs per loop (mean ± std. dev. of 7 runs, 100 loops each)\n"
     ]
    }
   ],
   "source": [
    "%%timeit -n 100\n",
    "summary = np.sum(s)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 70,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0    645\n",
       "1    591\n",
       "2    994\n",
       "3    446\n",
       "4    625\n",
       "dtype: int64"
      ]
     },
     "execution_count": 70,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "s+=2\n",
    "s.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 71,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "173 ms ± 6.58 ms per loop (mean ± std. dev. of 7 runs, 10 loops each)\n"
     ]
    }
   ],
   "source": [
    "%%timeit -n 10\n",
    "s = pd.Series(np.random.randint(0,100,1000))\n",
    "for label, value in s.iteritems():\n",
    "    s.loc[label]= value+2"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 72,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "288 µs ± 48.6 µs per loop (mean ± std. dev. of 7 runs, 10 loops each)\n"
     ]
    }
   ],
   "source": [
    "%%timeit -n 10\n",
    "s = pd.Series(np.random.randint(0,100,1000))\n",
    "s+=2"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "#### Dataframe"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "DataFrame is a 2-dimensional labeled data structure with columns of potentially different types. \n",
    "\n",
    "Similar to a database table, a spreadsheet, or a dict of Series objects. \n",
    "\n",
    "DataFrame accepts many different kinds of input:\n",
    "\n",
    "- Dict of 1D ndarrays, lists, dicts, or Series  \n",
    "- 2-D numpy.ndarray  \n",
    "- Structured or record ndarray  \n",
    "- A Series \n",
    "- Another DataFrame  "
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "DataFrame is an analog of a two-dimensional array with both flexible row indices and flexible column names.\n",
    "\n",
    "So a DataFrame as a sequence of aligned Series objects. E.g., a series of dictionaries.\n",
    "\n",
    "Construct new Series for population and area as disctionaries."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 73,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "California    38332521\n",
       "Texas         26448193\n",
       "New York      19651127\n",
       "Florida       19552860\n",
       "Illinois      12882135\n",
       "dtype: int64"
      ]
     },
     "execution_count": 73,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "population_dict = {'California': 38332521,\n",
    "                   'Texas': 26448193,\n",
    "                   'New York': 19651127,\n",
    "                   'Florida': 19552860,\n",
    "                   'Illinois': 12882135}\n",
    "population = pd.Series(population_dict)\n",
    "population"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 74,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "California    423967\n",
       "Texas         695662\n",
       "New York      141297\n",
       "Florida       170312\n",
       "Illinois      149995\n",
       "dtype: int64"
      ]
     },
     "execution_count": 74,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "area_dict = {'California': 423967, 'Texas': 695662, 'New York': 141297,\n",
    "             'Florida': 170312, 'Illinois': 149995}\n",
    "area = pd.Series(area_dict)\n",
    "area"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Now that we have this along with the population Series from before, we can use a dictionary to construct a single two-dimensional object containing this information:\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 75,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>population</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>California</th>\n",
       "      <td>38332521</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Texas</th>\n",
       "      <td>26448193</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>New York</th>\n",
       "      <td>19651127</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Florida</th>\n",
       "      <td>19552860</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Illinois</th>\n",
       "      <td>12882135</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "            population\n",
       "California    38332521\n",
       "Texas         26448193\n",
       "New York      19651127\n",
       "Florida       19552860\n",
       "Illinois      12882135"
      ]
     },
     "execution_count": 75,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "population_only = pd.DataFrame({'population': population})\n",
    "population_only"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 76,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>population</th>\n",
       "      <th>area</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>California</th>\n",
       "      <td>38332521</td>\n",
       "      <td>423967</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Texas</th>\n",
       "      <td>26448193</td>\n",
       "      <td>695662</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>New York</th>\n",
       "      <td>19651127</td>\n",
       "      <td>141297</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Florida</th>\n",
       "      <td>19552860</td>\n",
       "      <td>170312</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Illinois</th>\n",
       "      <td>12882135</td>\n",
       "      <td>149995</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "            population    area\n",
       "California    38332521  423967\n",
       "Texas         26448193  695662\n",
       "New York      19651127  141297\n",
       "Florida       19552860  170312\n",
       "Illinois      12882135  149995"
      ]
     },
     "execution_count": 76,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "states = pd.DataFrame({'population': population,\n",
    "                       'area': area})\n",
    "states"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Like the ``Series`` object, the ``DataFrame`` has an ``index`` attribute that gives access to the index labels:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 77,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "Index(['California', 'Texas', 'New York', 'Florida', 'Illinois'], dtype='object')"
      ]
     },
     "execution_count": 77,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "states.index"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Additionally, the DataFrame has a columns attribute, which is an Index object holding the column labels:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 78,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "Index(['population', 'area'], dtype='object')"
      ]
     },
     "execution_count": 78,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "states.columns"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Another example of a dataframe from dict of Series"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 79,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "{'one': a    1.0\n",
       " b    2.0\n",
       " c    3.0\n",
       " dtype: float64, 'two': a    1.0\n",
       " b    2.0\n",
       " c    3.0\n",
       " d    4.0\n",
       " dtype: float64}"
      ]
     },
     "execution_count": 79,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "d = {'one' : pd.Series([1., 2., 3.], index=['a', 'b', 'c']),\n",
    "    'two' : pd.Series([1., 2., 3., 4.], index=['a', 'b', 'c', 'd'])}\n",
    "d"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 80,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>one</th>\n",
       "      <th>two</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>d</th>\n",
       "      <td>NaN</td>\n",
       "      <td>4.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>b</th>\n",
       "      <td>2.0</td>\n",
       "      <td>2.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>a</th>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   one  two\n",
       "d  NaN  4.0\n",
       "b  2.0  2.0\n",
       "a  1.0  1.0"
      ]
     },
     "execution_count": 80,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "pd.DataFrame(d, index=['d', 'b', 'a'])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 81,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>two</th>\n",
       "      <th>three</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>d</th>\n",
       "      <td>4.0</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>b</th>\n",
       "      <td>2.0</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>a</th>\n",
       "      <td>1.0</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   two three\n",
       "d  4.0   NaN\n",
       "b  2.0   NaN\n",
       "a  1.0   NaN"
      ]
     },
     "execution_count": 81,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "pd.DataFrame(d, index=['d', 'b', 'a'], columns=['two', 'three'])"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "The row and column labels can be accessed using the index and columns attributes:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 82,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>one</th>\n",
       "      <th>two</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>a</th>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>b</th>\n",
       "      <td>2.0</td>\n",
       "      <td>2.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>c</th>\n",
       "      <td>3.0</td>\n",
       "      <td>3.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>d</th>\n",
       "      <td>NaN</td>\n",
       "      <td>4.0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   one  two\n",
       "a  1.0  1.0\n",
       "b  2.0  2.0\n",
       "c  3.0  3.0\n",
       "d  NaN  4.0"
      ]
     },
     "execution_count": 82,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "d = {'one' : pd.Series([1., 2., 3.], index=['a', 'b', 'c']),\n",
    "    'two' : pd.Series([1., 2., 3., 4.], index=['a', 'b', 'c', 'd'])}\n",
    "df = pd.DataFrame(d)\n",
    "df"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 83,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "Index(['one', 'two'], dtype='object')"
      ]
     },
     "execution_count": 83,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.columns"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 84,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "a    1.0\n",
       "b    2.0\n",
       "c    3.0\n",
       "d    NaN\n",
       "Name: one, dtype: float64"
      ]
     },
     "execution_count": 84,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df['one']"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 85,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>one</th>\n",
       "      <th>two</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>a</th>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   one  two\n",
       "a  1.0  1.0"
      ]
     },
     "execution_count": 85,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.loc[['a']]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 86,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "<class 'pandas.core.series.Series'>\n",
      "<class 'pandas.core.frame.DataFrame'>\n"
     ]
    }
   ],
   "source": [
    "print( type(df.loc['a']))\n",
    "print( type(df.loc[['a']]))"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Dataframe from dict of ndarrays or lists"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 87,
   "metadata": {},
   "outputs": [],
   "source": [
    "d = {'one' : [1., 2., 3., 4.],    \n",
    "     'two' : [4., 3., 2., 1.]}"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 88,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>one</th>\n",
       "      <th>two</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>1.0</td>\n",
       "      <td>4.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>2.0</td>\n",
       "      <td>3.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>3.0</td>\n",
       "      <td>2.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>4.0</td>\n",
       "      <td>1.0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   one  two\n",
       "0  1.0  4.0\n",
       "1  2.0  3.0\n",
       "2  3.0  2.0\n",
       "3  4.0  1.0"
      ]
     },
     "execution_count": 88,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "pd.DataFrame(d)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "DataFrame from a list of dicts"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 89,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>a</th>\n",
       "      <th>b</th>\n",
       "      <th>c</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>1</td>\n",
       "      <td>2</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>5</td>\n",
       "      <td>10</td>\n",
       "      <td>20.0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   a   b     c\n",
       "0  1   2   NaN\n",
       "1  5  10  20.0"
      ]
     },
     "execution_count": 89,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "data2 = [{'a': 1, 'b': 2}, {'a': 5, 'b': 10, 'c': 20}]\n",
    "pd.DataFrame(data2)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 90,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>a</th>\n",
       "      <th>b</th>\n",
       "      <th>c</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>first</th>\n",
       "      <td>1</td>\n",
       "      <td>2</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>second</th>\n",
       "      <td>5</td>\n",
       "      <td>10</td>\n",
       "      <td>20.0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "        a   b     c\n",
       "first   1   2   NaN\n",
       "second  5  10  20.0"
      ]
     },
     "execution_count": 90,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "pd.DataFrame(data2, index=['first', 'second'])"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "#### Column selection, addition, deletion\n",
    "\n",
    "Similar to a dict of like-indexed Series objects. "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 91,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "Archery           Bhutan\n",
       "Golf            Scotland\n",
       "Sumo               Japan\n",
       "Taekwondo    South Korea\n",
       "Cricket        Australia\n",
       "Cricket         Barbados\n",
       "Cricket         Pakistan\n",
       "Cricket          England\n",
       "dtype: object"
      ]
     },
     "execution_count": 91,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "original_sports = pd.Series({'Archery': 'Bhutan',\n",
    "                             'Golf': 'Scotland',\n",
    "                             'Sumo': 'Japan',\n",
    "                             'Taekwondo': 'South Korea'})\n",
    "cricket_loving_countries = pd.Series(['Australia',\n",
    "                                      'Barbados',\n",
    "                                      'Pakistan',\n",
    "                                      'England'], \n",
    "                                   index=['Cricket',\n",
    "                                          'Cricket',\n",
    "                                          'Cricket',\n",
    "                                          'Cricket'])\n",
    "all_countries = original_sports.append(cricket_loving_countries)\n",
    "all_countries"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 92,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>Name</th>\n",
       "      <th>Item Purchased</th>\n",
       "      <th>Cost</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>Store 1</th>\n",
       "      <td>Jay</td>\n",
       "      <td>Dog Food</td>\n",
       "      <td>22.5</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Store 1</th>\n",
       "      <td>Kim</td>\n",
       "      <td>Kitty Litter</td>\n",
       "      <td>2.5</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Store 2</th>\n",
       "      <td>Sergey</td>\n",
       "      <td>Bird Seed</td>\n",
       "      <td>5.0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "           Name Item Purchased  Cost\n",
       "Store 1     Jay       Dog Food  22.5\n",
       "Store 1     Kim   Kitty Litter   2.5\n",
       "Store 2  Sergey      Bird Seed   5.0"
      ]
     },
     "execution_count": 92,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "import pandas as pd\n",
    "purchase_1 = pd.Series({'Name': 'Jay',\n",
    "                        'Item Purchased': 'Dog Food',\n",
    "                        'Cost': 22.50})\n",
    "purchase_2 = pd.Series({'Name': 'Kim',\n",
    "                        'Item Purchased': 'Kitty Litter',\n",
    "                        'Cost': 2.50})\n",
    "purchase_3 = pd.Series({'Name': 'Sergey',\n",
    "                        'Item Purchased': 'Bird Seed',\n",
    "                        'Cost': 5.00})\n",
    "df = pd.DataFrame([purchase_1, purchase_2, purchase_3], \n",
    "                  index=['Store 1', 'Store 1', 'Store 2'])\n",
    "df.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 93,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "Name                 Sergey\n",
       "Item Purchased    Bird Seed\n",
       "Cost                      5\n",
       "Name: Store 2, dtype: object"
      ]
     },
     "execution_count": 93,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.loc['Store 2']"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 94,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "pandas.core.series.Series"
      ]
     },
     "execution_count": 94,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "type( df.loc['Store 2'] )"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 95,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "Store 1    22.5\n",
       "Store 1     2.5\n",
       "Name: Cost, dtype: float64"
      ]
     },
     "execution_count": 95,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.loc['Store 1','Cost'] "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 96,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "pandas.core.series.Series"
      ]
     },
     "execution_count": 96,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "type( df.loc['Store 1','Cost'] )"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 97,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>Store 1</th>\n",
       "      <th>Store 1</th>\n",
       "      <th>Store 2</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>Name</th>\n",
       "      <td>Jay</td>\n",
       "      <td>Kim</td>\n",
       "      <td>Sergey</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Item Purchased</th>\n",
       "      <td>Dog Food</td>\n",
       "      <td>Kitty Litter</td>\n",
       "      <td>Bird Seed</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Cost</th>\n",
       "      <td>22.5</td>\n",
       "      <td>2.5</td>\n",
       "      <td>5</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                 Store 1       Store 1    Store 2\n",
       "Name                 Jay           Kim     Sergey\n",
       "Item Purchased  Dog Food  Kitty Litter  Bird Seed\n",
       "Cost                22.5           2.5          5"
      ]
     },
     "execution_count": 97,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.T"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 98,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "Store 1    22.5\n",
       "Store 1     2.5\n",
       "Store 2       5\n",
       "Name: Cost, dtype: object"
      ]
     },
     "execution_count": 98,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.T.loc['Cost']"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 99,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "Store 1    22.5\n",
       "Store 1     2.5\n",
       "Name: Cost, dtype: float64"
      ]
     },
     "execution_count": 99,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.loc['Store 1']['Cost']"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Beware of the shallow copy"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 100,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>Name</th>\n",
       "      <th>Item Purchased</th>\n",
       "      <th>Cost</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>Store 1</th>\n",
       "      <td>Jay</td>\n",
       "      <td>Dog Food</td>\n",
       "      <td>22.5</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Store 1</th>\n",
       "      <td>Kim</td>\n",
       "      <td>Kitty Litter</td>\n",
       "      <td>2.5</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Store 2</th>\n",
       "      <td>Sergey</td>\n",
       "      <td>Bird Seed</td>\n",
       "      <td>5.0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "           Name Item Purchased  Cost\n",
       "Store 1     Jay       Dog Food  22.5\n",
       "Store 1     Kim   Kitty Litter   2.5\n",
       "Store 2  Sergey      Bird Seed   5.0"
      ]
     },
     "execution_count": 100,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 101,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>Name</th>\n",
       "      <th>Item Purchased</th>\n",
       "      <th>Cost</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>Store 2</th>\n",
       "      <td>Sergey</td>\n",
       "      <td>Bird Seed</td>\n",
       "      <td>5.0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "           Name Item Purchased  Cost\n",
       "Store 2  Sergey      Bird Seed   5.0"
      ]
     },
     "execution_count": 101,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "copy_df = df.copy()\n",
    "copy_df = copy_df.drop('Store 1')\n",
    "copy_df"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 102,
   "metadata": {},
   "outputs": [],
   "source": [
    "copy_df.drop?"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 103,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>Item Purchased</th>\n",
       "      <th>Cost</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>Store 2</th>\n",
       "      <td>Bird Seed</td>\n",
       "      <td>5.0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "        Item Purchased  Cost\n",
       "Store 2      Bird Seed   5.0"
      ]
     },
     "execution_count": 103,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "del copy_df['Name']\n",
    "copy_df"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 104,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>Name</th>\n",
       "      <th>Item Purchased</th>\n",
       "      <th>Cost</th>\n",
       "      <th>Location</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>Store 1</th>\n",
       "      <td>Jay</td>\n",
       "      <td>Dog Food</td>\n",
       "      <td>22.5</td>\n",
       "      <td>None</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Store 1</th>\n",
       "      <td>Kim</td>\n",
       "      <td>Kitty Litter</td>\n",
       "      <td>2.5</td>\n",
       "      <td>None</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Store 2</th>\n",
       "      <td>Sergey</td>\n",
       "      <td>Bird Seed</td>\n",
       "      <td>5.0</td>\n",
       "      <td>None</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "           Name Item Purchased  Cost Location\n",
       "Store 1     Jay       Dog Food  22.5     None\n",
       "Store 1     Kim   Kitty Litter   2.5     None\n",
       "Store 2  Sergey      Bird Seed   5.0     None"
      ]
     },
     "execution_count": 104,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df['Location'] = None\n",
    "df"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "#### Dataframe Indexing and Loading"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 105,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "Store 1    22.5\n",
       "Store 1     2.5\n",
       "Store 2     5.0\n",
       "Name: Cost, dtype: float64"
      ]
     },
     "execution_count": 105,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "costs = df['Cost']\n",
    "costs"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 106,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "Store 1    24.5\n",
       "Store 1     4.5\n",
       "Store 2     7.0\n",
       "Name: Cost, dtype: float64"
      ]
     },
     "execution_count": 106,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "costs+=2\n",
    "costs"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 107,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>Name</th>\n",
       "      <th>Item Purchased</th>\n",
       "      <th>Cost</th>\n",
       "      <th>Location</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>Store 1</th>\n",
       "      <td>Jay</td>\n",
       "      <td>Dog Food</td>\n",
       "      <td>24.5</td>\n",
       "      <td>None</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Store 1</th>\n",
       "      <td>Kim</td>\n",
       "      <td>Kitty Litter</td>\n",
       "      <td>4.5</td>\n",
       "      <td>None</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Store 2</th>\n",
       "      <td>Sergey</td>\n",
       "      <td>Bird Seed</td>\n",
       "      <td>7.0</td>\n",
       "      <td>None</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "           Name Item Purchased  Cost Location\n",
       "Store 1     Jay       Dog Food  24.5     None\n",
       "Store 1     Kim   Kitty Litter   4.5     None\n",
       "Store 2  Sergey      Bird Seed   7.0     None"
      ]
     },
     "execution_count": 107,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Inspect olympic data file"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 108,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "0,1,2,3,4,5,6,7,8,9,10,11,12,13,14,15\r\n",
      ",№ Summer,01 !,02 !,03 !,Total,№ Winter,01 !,02 !,03 !,Total,№ Games,01 !,02 !,03 !,Combined total\r\n",
      "Afghanistan (AFG),13,0,0,2,2,0,0,0,0,0,13,0,0,2,2\r\n",
      "Algeria (ALG),12,5,2,8,15,3,0,0,0,0,15,5,2,8,15\r\n",
      "Argentina (ARG),23,18,24,28,70,18,0,0,0,0,41,18,24,28,70\r\n",
      "Armenia (ARM),5,1,2,9,12,6,0,0,0,0,11,1,2,9,12\r\n",
      "Australasia (ANZ) [ANZ],2,3,4,5,12,0,0,0,0,0,2,3,4,5,12\r\n",
      "Australia (AUS) [AUS] [Z],25,139,152,177,468,18,5,3,4,12,43,144,155,181,480\r\n",
      "Austria (AUT),26,18,33,35,86,22,59,78,81,218,48,77,111,116,304\r\n",
      "Azerbaijan (AZE),5,6,5,15,26,5,0,0,0,0,10,6,5,15,26\r\n",
      "Bahamas (BAH),15,5,2,5,12,0,0,0,0,0,15,5,2,5,12\r\n",
      "Bahrain (BRN),8,0,0,1,1,0,0,0,0,0,8,0,0,1,1\r\n",
      "Barbados (BAR) [BAR],11,0,0,1,1,0,0,0,0,0,11,0,0,1,1\r\n",
      "Belarus (BLR),5,12,24,39,75,6,6,4,5,15,11,18,28,44,90\r\n",
      "Belgium (BEL),25,37,52,53,142,20,1,1,3,5,45,38,53,56,147\r\n",
      "Bermuda (BER),17,0,0,1,1,7,0,0,0,0,24,0,0,1,1\r\n",
      "Bohemia (BOH) [BOH] [Z],3,0,1,3,4,0,0,0,0,0,3,0,1,3,4\r\n",
      "Botswana (BOT),9,0,1,0,1,0,0,0,0,0,9,0,1,0,1\r\n",
      "Brazil (BRA),21,23,30,55,108,7,0,0,0,0,28,23,30,55,108\r\n",
      "British West Indies (BWI) [BWI],1,0,0,2,2,0,0,0,0,0,1,0,0,2,2\r\n",
      "Bulgaria (BUL) [H],19,51,85,78,214,19,1,2,3,6,38,52,87,81,220\r\n",
      "Burundi (BDI),5,1,0,0,1,0,0,0,0,0,5,1,0,0,1\r\n",
      "Cameroon (CMR),13,3,1,1,5,1,0,0,0,0,14,3,1,1,5\r\n",
      "Canada (CAN),25,59,99,121,279,22,62,56,52,170,47,121,155,173,449\r\n",
      "Chile (CHI) [I],22,2,7,4,13,16,0,0,0,0,38,2,7,4,13\r\n",
      "China (CHN) [CHN],9,201,146,126,473,10,12,22,19,53,19,213,168,145,526\r\n",
      "Colombia (COL),18,2,6,11,19,1,0,0,0,0,19,2,6,11,19\r\n",
      "Costa Rica (CRC),14,1,1,2,4,6,0,0,0,0,20,1,1,2,4\r\n",
      "Ivory Coast (CIV) [CIV],12,0,1,0,1,0,0,0,0,0,12,0,1,0,1\r\n",
      "Croatia (CRO),6,6,7,10,23,7,4,6,1,11,13,10,13,11,34\r\n",
      "Cuba (CUB) [Z],19,72,67,70,209,0,0,0,0,0,19,72,67,70,209\r\n",
      "Cyprus (CYP),9,0,1,0,1,10,0,0,0,0,19,0,1,0,1\r\n",
      "Czech Republic (CZE) [CZE],5,14,15,15,44,6,7,9,8,24,11,21,24,23,68\r\n",
      "Czechoslovakia (TCH) [TCH],16,49,49,45,143,16,2,8,15,25,32,51,57,60,168\r\n",
      "Denmark (DEN) [Z],26,43,68,68,179,13,0,1,0,1,39,43,69,68,180\r\n",
      "Djibouti (DJI) [B],7,0,0,1,1,0,0,0,0,0,7,0,0,1,1\r\n",
      "Dominican Republic (DOM),13,3,2,1,6,0,0,0,0,0,13,3,2,1,6\r\n",
      "Ecuador (ECU),13,1,1,0,2,0,0,0,0,0,13,1,1,0,2\r\n",
      "Egypt (EGY) [EGY] [Z],21,7,9,10,26,1,0,0,0,0,22,7,9,10,26\r\n",
      "Eritrea (ERI),4,0,0,1,1,0,0,0,0,0,4,0,0,1,1\r\n",
      "Estonia (EST),11,9,9,15,33,9,4,2,1,7,20,13,11,16,40\r\n",
      "Ethiopia (ETH),12,21,7,17,45,2,0,0,0,0,14,21,7,17,45\r\n",
      "Finland (FIN),24,101,84,117,302,22,42,62,57,161,46,143,146,174,463\r\n",
      "France (FRA) [O] [P] [Z],27,202,223,246,671,22,31,31,47,109,49,233,254,293,780\r\n",
      "Gabon (GAB),9,0,1,0,1,0,0,0,0,0,9,0,1,0,1\r\n",
      "Georgia (GEO),5,6,5,14,25,6,0,0,0,0,11,6,5,14,25\r\n",
      "Germany (GER) [GER] [Z],15,174,182,217,573,11,78,78,53,209,26,252,260,270,782\r\n",
      "United Team of Germany (EUA) [EUA],3,28,54,36,118,3,8,6,5,19,6,36,60,41,137\r\n",
      "East Germany (GDR) [GDR],5,153,129,127,409,6,39,36,35,110,11,192,165,162,519\r\n",
      "West Germany (FRG) [FRG],5,56,67,81,204,6,11,15,13,39,11,67,82,94,243\r\n",
      "Ghana (GHA) [GHA],13,0,1,3,4,1,0,0,0,0,14,0,1,3,4\r\n",
      "Great Britain (GBR) [GBR] [Z],27,236,272,272,780,22,10,4,12,26,49,246,276,284,806\r\n",
      "Greece (GRE) [Z],27,30,42,39,111,18,0,0,0,0,45,30,42,39,111\r\n",
      "Grenada (GRN),8,1,0,0,1,0,0,0,0,0,8,1,0,0,1\r\n",
      "Guatemala (GUA),13,0,1,0,1,1,0,0,0,0,14,0,1,0,1\r\n",
      "Guyana (GUY) [GUY],16,0,0,1,1,0,0,0,0,0,16,0,0,1,1\r\n",
      "Haiti (HAI) [J],14,0,1,1,2,0,0,0,0,0,14,0,1,1,2\r\n",
      "Hong Kong (HKG) [HKG],15,1,1,1,3,4,0,0,0,0,19,1,1,1,3\r\n",
      "Hungary (HUN),25,167,144,165,476,22,0,2,4,6,47,167,146,169,482\r\n",
      "Iceland (ISL),19,0,2,2,4,17,0,0,0,0,36,0,2,2,4\r\n",
      "India (IND) [F],23,9,6,11,26,9,0,0,0,0,32,9,6,11,26\r\n",
      "Indonesia (INA),14,6,10,11,27,0,0,0,0,0,14,6,10,11,27\r\n",
      "Iran (IRI) [K],15,15,20,25,60,10,0,0,0,0,25,15,20,25,60\r\n",
      "Iraq (IRQ),13,0,0,1,1,0,0,0,0,0,13,0,0,1,1\r\n",
      "Ireland (IRL),20,9,8,12,29,6,0,0,0,0,26,9,8,12,29\r\n",
      "Israel (ISR),15,1,1,5,7,6,0,0,0,0,21,1,1,5,7\r\n",
      "Italy (ITA) [M] [S],26,198,166,185,549,22,37,34,43,114,48,235,200,228,663\r\n",
      "Jamaica (JAM) [JAM],16,17,30,20,67,7,0,0,0,0,23,17,30,20,67\r\n",
      "Japan (JPN),21,130,126,142,398,20,10,17,18,45,41,140,143,160,443\r\n",
      "Kazakhstan (KAZ),5,16,17,19,52,6,1,3,3,7,11,17,20,22,59\r\n",
      "Kenya (KEN),13,25,32,29,86,3,0,0,0,0,16,25,32,29,86\r\n",
      "North Korea (PRK),9,14,12,21,47,8,0,1,1,2,17,14,13,22,49\r\n",
      "South Korea (KOR),16,81,82,80,243,17,26,17,10,53,33,107,99,90,296\r\n",
      "Kuwait (KUW),12,0,0,2,2,0,0,0,0,0,12,0,0,2,2\r\n",
      "Kyrgyzstan (KGZ),5,0,1,2,3,6,0,0,0,0,11,0,1,2,3\r\n",
      "Latvia (LAT),10,3,11,5,19,10,0,4,3,7,20,3,15,8,26\r\n",
      "Lebanon (LIB),16,0,2,2,4,16,0,0,0,0,32,0,2,2,4\r\n",
      "Liechtenstein (LIE),16,0,0,0,0,18,2,2,5,9,34,2,2,5,9\r\n",
      "Lithuania (LTU),8,6,5,10,21,8,0,0,0,0,16,6,5,10,21\r\n",
      "Luxembourg (LUX) [O],22,1,1,0,2,8,0,2,0,2,30,1,3,0,4\r\n",
      "Macedonia (MKD),5,0,0,1,1,5,0,0,0,0,10,0,0,1,1\r\n",
      "Malaysia (MAS) [MAS],12,0,3,3,6,0,0,0,0,0,12,0,3,3,6\r\n",
      "Mauritius (MRI),8,0,0,1,1,0,0,0,0,0,8,0,0,1,1\r\n",
      "Mexico (MEX),22,13,21,28,62,8,0,0,0,0,30,13,21,28,62\r\n",
      "Moldova (MDA),5,0,2,5,7,6,0,0,0,0,11,0,2,5,7\r\n",
      "Mongolia (MGL),12,2,9,13,24,13,0,0,0,0,25,2,9,13,24\r\n",
      "Montenegro (MNE),2,0,1,0,1,2,0,0,0,0,4,0,1,0,1\r\n",
      "Morocco (MAR),13,6,5,11,22,6,0,0,0,0,19,6,5,11,22\r\n",
      "Mozambique (MOZ),9,1,0,1,2,0,0,0,0,0,9,1,0,1,2\r\n",
      "Namibia (NAM),6,0,4,0,4,0,0,0,0,0,6,0,4,0,4\r\n",
      "Netherlands (NED) [Z],25,77,85,104,266,20,37,38,35,110,45,114,123,139,376\r\n",
      "Netherlands Antilles (AHO) [AHO] [I],13,0,1,0,1,2,0,0,0,0,15,0,1,0,1\r\n",
      "New Zealand (NZL) [NZL],22,42,18,39,99,15,0,1,0,1,37,42,19,39,100\r\n",
      "Niger (NIG),11,0,0,1,1,0,0,0,0,0,11,0,0,1,1\r\n",
      "Nigeria (NGR),15,3,8,12,23,0,0,0,0,0,15,3,8,12,23\r\n",
      "Norway (NOR) [Q],24,56,49,43,148,22,118,111,100,329,46,174,160,143,477\r\n",
      "Pakistan (PAK),16,3,3,4,10,2,0,0,0,0,18,3,3,4,10\r\n",
      "Panama (PAN),16,1,0,2,3,0,0,0,0,0,16,1,0,2,3\r\n",
      "Paraguay (PAR),11,0,1,0,1,1,0,0,0,0,12,0,1,0,1\r\n",
      "Peru (PER) [L],17,1,3,0,4,2,0,0,0,0,19,1,3,0,4\r\n",
      "Philippines (PHI),20,0,2,7,9,4,0,0,0,0,24,0,2,7,9\r\n",
      "Poland (POL),20,64,82,125,271,22,6,7,7,20,42,70,89,132,291\r\n",
      "Portugal (POR),23,4,8,11,23,7,0,0,0,0,30,4,8,11,23\r\n",
      "Puerto Rico (PUR),17,0,2,6,8,6,0,0,0,0,23,0,2,6,8\r\n",
      "Qatar (QAT),8,0,0,4,4,0,0,0,0,0,8,0,0,4,4\r\n",
      "Romania (ROU),20,88,94,119,301,20,0,0,1,1,40,88,94,120,302\r\n",
      "Russia (RUS) [RUS],5,132,121,142,395,6,49,40,35,124,11,181,161,177,519\r\n",
      "Russian Empire (RU1) [RU1],3,1,4,3,8,0,0,0,0,0,3,1,4,3,8\r\n",
      "Soviet Union (URS) [URS],9,395,319,296,1010,9,78,57,59,194,18,473,376,355,1204\r\n",
      "Unified Team (EUN) [EUN],1,45,38,29,112,1,9,6,8,23,2,54,44,37,135\r\n",
      "Saudi Arabia (KSA),10,0,1,2,3,0,0,0,0,0,10,0,1,2,3\r\n",
      "Senegal (SEN),13,0,1,0,1,5,0,0,0,0,18,0,1,0,1\r\n",
      "Serbia (SRB) [SRB],3,1,2,4,7,2,0,0,0,0,5,1,2,4,7\r\n",
      "Serbia and Montenegro (SCG) [SCG],3,2,4,3,9,3,0,0,0,0,6,2,4,3,9\r\n",
      "Singapore (SIN),15,0,2,2,4,0,0,0,0,0,15,0,2,2,4\r\n",
      "Slovakia (SVK) [SVK],5,7,9,8,24,6,2,2,1,5,11,9,11,9,29\r\n",
      "Slovenia (SLO),6,4,6,9,19,7,2,4,9,15,13,6,10,18,34\r\n",
      "South Africa (RSA),18,23,26,27,76,6,0,0,0,0,24,23,26,27,76\r\n",
      "Spain (ESP) [Z],22,37,59,35,131,19,1,0,1,2,41,38,59,36,133\r\n",
      "Sri Lanka (SRI) [SRI],16,0,2,0,2,0,0,0,0,0,16,0,2,0,2\r\n",
      "Sudan (SUD),11,0,1,0,1,0,0,0,0,0,11,0,1,0,1\r\n",
      "Suriname (SUR) [E],11,1,0,1,2,0,0,0,0,0,11,1,0,1,2\r\n",
      "Sweden (SWE) [Z],26,143,164,176,483,22,50,40,54,144,48,193,204,230,627\r\n",
      "Switzerland (SUI),27,47,73,65,185,22,50,40,48,138,49,97,113,113,323\r\n",
      "Syria (SYR),12,1,1,1,3,0,0,0,0,0,12,1,1,1,3\r\n",
      "Chinese Taipei (TPE) [TPE] [TPE2],13,2,7,12,21,11,0,0,0,0,24,2,7,12,21\r\n",
      "Tajikistan (TJK),5,0,1,2,3,4,0,0,0,0,9,0,1,2,3\r\n",
      "Tanzania (TAN) [TAN],12,0,2,0,2,0,0,0,0,0,12,0,2,0,2\r\n",
      "Thailand (THA),15,7,6,11,24,3,0,0,0,0,18,7,6,11,24\r\n",
      "Togo (TOG),9,0,0,1,1,1,0,0,0,0,10,0,0,1,1\r\n",
      "Tonga (TGA),8,0,1,0,1,1,0,0,0,0,9,0,1,0,1\r\n",
      "Trinidad and Tobago (TRI) [TRI],16,2,5,11,18,3,0,0,0,0,19,2,5,11,18\r\n",
      "Tunisia (TUN),13,3,3,4,10,0,0,0,0,0,13,3,3,4,10\r\n",
      "Turkey (TUR),21,39,25,24,88,16,0,0,0,0,37,39,25,24,88\r\n",
      "Uganda (UGA),14,2,3,2,7,0,0,0,0,0,14,2,3,2,7\r\n",
      "Ukraine (UKR),5,33,27,55,115,6,2,1,4,7,11,35,28,59,122\r\n",
      "United Arab Emirates (UAE),8,1,0,0,1,0,0,0,0,0,8,1,0,0,1\r\n",
      "United States (USA) [P] [Q] [R] [Z],26,976,757,666,2399,22,96,102,84,282,48,1072,859,750,2681\r\n",
      "Uruguay (URU),20,2,2,6,10,1,0,0,0,0,21,2,2,6,10\r\n",
      "Uzbekistan (UZB),5,5,5,10,20,6,1,0,0,1,11,6,5,10,21\r\n",
      "Venezuela (VEN),17,2,2,8,12,4,0,0,0,0,21,2,2,8,12\r\n",
      "Vietnam (VIE),14,0,2,0,2,0,0,0,0,0,14,0,2,0,2\r\n",
      "Virgin Islands (ISV),11,0,1,0,1,7,0,0,0,0,18,0,1,0,1\r\n",
      "Yugoslavia (YUG) [YUG],16,26,29,28,83,14,0,3,1,4,30,26,32,29,87\r\n",
      "Independent Olympic Participants (IOP) [IOP],1,0,1,2,3,0,0,0,0,0,1,0,1,2,3\r\n",
      "Zambia (ZAM) [ZAM],12,0,1,1,2,0,0,0,0,0,12,0,1,1,2\r\n",
      "Zimbabwe (ZIM) [ZIM],12,3,4,1,8,1,0,0,0,0,13,3,4,1,8\r\n",
      "Mixed team (ZZX) [ZZX],3,8,5,4,17,0,0,0,0,0,3,8,5,4,17\r\n",
      "Totals,27,4809,4775,5130,14714,22,959,958,948,2865,49,5768,5733,6078,17579\r\n"
     ]
    }
   ],
   "source": [
    "!cat data/olympics.csv"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Deal with header row"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 109,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>№ Summer</th>\n",
       "      <th>01 !</th>\n",
       "      <th>02 !</th>\n",
       "      <th>03 !</th>\n",
       "      <th>Total</th>\n",
       "      <th>№ Winter</th>\n",
       "      <th>01 !.1</th>\n",
       "      <th>02 !.1</th>\n",
       "      <th>03 !.1</th>\n",
       "      <th>Total.1</th>\n",
       "      <th>№ Games</th>\n",
       "      <th>01 !.2</th>\n",
       "      <th>02 !.2</th>\n",
       "      <th>03 !.2</th>\n",
       "      <th>Combined total</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>Afghanistan (AFG)</th>\n",
       "      <td>13</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>2</td>\n",
       "      <td>2</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>13</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>2</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Algeria (ALG)</th>\n",
       "      <td>12</td>\n",
       "      <td>5</td>\n",
       "      <td>2</td>\n",
       "      <td>8</td>\n",
       "      <td>15</td>\n",
       "      <td>3</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>15</td>\n",
       "      <td>5</td>\n",
       "      <td>2</td>\n",
       "      <td>8</td>\n",
       "      <td>15</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Argentina (ARG)</th>\n",
       "      <td>23</td>\n",
       "      <td>18</td>\n",
       "      <td>24</td>\n",
       "      <td>28</td>\n",
       "      <td>70</td>\n",
       "      <td>18</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>41</td>\n",
       "      <td>18</td>\n",
       "      <td>24</td>\n",
       "      <td>28</td>\n",
       "      <td>70</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Armenia (ARM)</th>\n",
       "      <td>5</td>\n",
       "      <td>1</td>\n",
       "      <td>2</td>\n",
       "      <td>9</td>\n",
       "      <td>12</td>\n",
       "      <td>6</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>11</td>\n",
       "      <td>1</td>\n",
       "      <td>2</td>\n",
       "      <td>9</td>\n",
       "      <td>12</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Australasia (ANZ) [ANZ]</th>\n",
       "      <td>2</td>\n",
       "      <td>3</td>\n",
       "      <td>4</td>\n",
       "      <td>5</td>\n",
       "      <td>12</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>2</td>\n",
       "      <td>3</td>\n",
       "      <td>4</td>\n",
       "      <td>5</td>\n",
       "      <td>12</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                         № Summer  01 !  02 !  03 !  Total  № Winter  01 !.1  \\\n",
       "Afghanistan (AFG)              13     0     0     2      2         0       0   \n",
       "Algeria (ALG)                  12     5     2     8     15         3       0   \n",
       "Argentina (ARG)                23    18    24    28     70        18       0   \n",
       "Armenia (ARM)                   5     1     2     9     12         6       0   \n",
       "Australasia (ANZ) [ANZ]         2     3     4     5     12         0       0   \n",
       "\n",
       "                         02 !.1  03 !.1  Total.1  № Games  01 !.2  02 !.2  \\\n",
       "Afghanistan (AFG)             0       0        0       13       0       0   \n",
       "Algeria (ALG)                 0       0        0       15       5       2   \n",
       "Argentina (ARG)               0       0        0       41      18      24   \n",
       "Armenia (ARM)                 0       0        0       11       1       2   \n",
       "Australasia (ANZ) [ANZ]       0       0        0        2       3       4   \n",
       "\n",
       "                         03 !.2  Combined total  \n",
       "Afghanistan (AFG)             2               2  \n",
       "Algeria (ALG)                 8              15  \n",
       "Argentina (ARG)              28              70  \n",
       "Armenia (ARM)                 9              12  \n",
       "Australasia (ANZ) [ANZ]       5              12  "
      ]
     },
     "execution_count": 109,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df = pd.read_csv('data/olympics.csv', index_col = 0, skiprows=1)\n",
    "df.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 110,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "Index(['№ Summer', '01 !', '02 !', '03 !', 'Total', '№ Winter', '01 !.1',\n",
       "       '02 !.1', '03 !.1', 'Total.1', '№ Games', '01 !.2', '02 !.2', '03 !.2',\n",
       "       'Combined total'],\n",
       "      dtype='object')"
      ]
     },
     "execution_count": 110,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.columns"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Clean up the header"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 112,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "# Summer\n",
      "Gold\n",
      "Silver\n",
      "Bronze\n",
      "Total\n",
      "# Winter\n",
      "Gold.1\n",
      "Silver.1\n",
      "Bronze.1\n",
      "Total.1\n",
      "# Games\n",
      "Gold.2\n",
      "Silver.2\n",
      "Bronze.2\n",
      "Combined total\n"
     ]
    },
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th># Summer</th>\n",
       "      <th>Gold</th>\n",
       "      <th>Silver</th>\n",
       "      <th>Bronze</th>\n",
       "      <th>Total</th>\n",
       "      <th># Winter</th>\n",
       "      <th>Gold.1</th>\n",
       "      <th>Silver.1</th>\n",
       "      <th>Bronze.1</th>\n",
       "      <th>Total.1</th>\n",
       "      <th># Games</th>\n",
       "      <th>Gold.2</th>\n",
       "      <th>Silver.2</th>\n",
       "      <th>Bronze.2</th>\n",
       "      <th>Combined total</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>Afghanistan (AFG)</th>\n",
       "      <td>13</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>2</td>\n",
       "      <td>2</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>13</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>2</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Algeria (ALG)</th>\n",
       "      <td>12</td>\n",
       "      <td>5</td>\n",
       "      <td>2</td>\n",
       "      <td>8</td>\n",
       "      <td>15</td>\n",
       "      <td>3</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>15</td>\n",
       "      <td>5</td>\n",
       "      <td>2</td>\n",
       "      <td>8</td>\n",
       "      <td>15</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Argentina (ARG)</th>\n",
       "      <td>23</td>\n",
       "      <td>18</td>\n",
       "      <td>24</td>\n",
       "      <td>28</td>\n",
       "      <td>70</td>\n",
       "      <td>18</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>41</td>\n",
       "      <td>18</td>\n",
       "      <td>24</td>\n",
       "      <td>28</td>\n",
       "      <td>70</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Armenia (ARM)</th>\n",
       "      <td>5</td>\n",
       "      <td>1</td>\n",
       "      <td>2</td>\n",
       "      <td>9</td>\n",
       "      <td>12</td>\n",
       "      <td>6</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>11</td>\n",
       "      <td>1</td>\n",
       "      <td>2</td>\n",
       "      <td>9</td>\n",
       "      <td>12</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Australasia (ANZ) [ANZ]</th>\n",
       "      <td>2</td>\n",
       "      <td>3</td>\n",
       "      <td>4</td>\n",
       "      <td>5</td>\n",
       "      <td>12</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>2</td>\n",
       "      <td>3</td>\n",
       "      <td>4</td>\n",
       "      <td>5</td>\n",
       "      <td>12</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Australia (AUS) [AUS] [Z]</th>\n",
       "      <td>25</td>\n",
       "      <td>139</td>\n",
       "      <td>152</td>\n",
       "      <td>177</td>\n",
       "      <td>468</td>\n",
       "      <td>18</td>\n",
       "      <td>5</td>\n",
       "      <td>3</td>\n",
       "      <td>4</td>\n",
       "      <td>12</td>\n",
       "      <td>43</td>\n",
       "      <td>144</td>\n",
       "      <td>155</td>\n",
       "      <td>181</td>\n",
       "      <td>480</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Austria (AUT)</th>\n",
       "      <td>26</td>\n",
       "      <td>18</td>\n",
       "      <td>33</td>\n",
       "      <td>35</td>\n",
       "      <td>86</td>\n",
       "      <td>22</td>\n",
       "      <td>59</td>\n",
       "      <td>78</td>\n",
       "      <td>81</td>\n",
       "      <td>218</td>\n",
       "      <td>48</td>\n",
       "      <td>77</td>\n",
       "      <td>111</td>\n",
       "      <td>116</td>\n",
       "      <td>304</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Azerbaijan (AZE)</th>\n",
       "      <td>5</td>\n",
       "      <td>6</td>\n",
       "      <td>5</td>\n",
       "      <td>15</td>\n",
       "      <td>26</td>\n",
       "      <td>5</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>10</td>\n",
       "      <td>6</td>\n",
       "      <td>5</td>\n",
       "      <td>15</td>\n",
       "      <td>26</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Bahamas (BAH)</th>\n",
       "      <td>15</td>\n",
       "      <td>5</td>\n",
       "      <td>2</td>\n",
       "      <td>5</td>\n",
       "      <td>12</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>15</td>\n",
       "      <td>5</td>\n",
       "      <td>2</td>\n",
       "      <td>5</td>\n",
       "      <td>12</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Bahrain (BRN)</th>\n",
       "      <td>8</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>8</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Barbados (BAR) [BAR]</th>\n",
       "      <td>11</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>11</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Belarus (BLR)</th>\n",
       "      <td>5</td>\n",
       "      <td>12</td>\n",
       "      <td>24</td>\n",
       "      <td>39</td>\n",
       "      <td>75</td>\n",
       "      <td>6</td>\n",
       "      <td>6</td>\n",
       "      <td>4</td>\n",
       "      <td>5</td>\n",
       "      <td>15</td>\n",
       "      <td>11</td>\n",
       "      <td>18</td>\n",
       "      <td>28</td>\n",
       "      <td>44</td>\n",
       "      <td>90</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Belgium (BEL)</th>\n",
       "      <td>25</td>\n",
       "      <td>37</td>\n",
       "      <td>52</td>\n",
       "      <td>53</td>\n",
       "      <td>142</td>\n",
       "      <td>20</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>3</td>\n",
       "      <td>5</td>\n",
       "      <td>45</td>\n",
       "      <td>38</td>\n",
       "      <td>53</td>\n",
       "      <td>56</td>\n",
       "      <td>147</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Bermuda (BER)</th>\n",
       "      <td>17</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>7</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>24</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Bohemia (BOH) [BOH] [Z]</th>\n",
       "      <td>3</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>3</td>\n",
       "      <td>4</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>3</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>3</td>\n",
       "      <td>4</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Botswana (BOT)</th>\n",
       "      <td>9</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>9</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Brazil (BRA)</th>\n",
       "      <td>21</td>\n",
       "      <td>23</td>\n",
       "      <td>30</td>\n",
       "      <td>55</td>\n",
       "      <td>108</td>\n",
       "      <td>7</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>28</td>\n",
       "      <td>23</td>\n",
       "      <td>30</td>\n",
       "      <td>55</td>\n",
       "      <td>108</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>British West Indies (BWI) [BWI]</th>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>2</td>\n",
       "      <td>2</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>2</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Bulgaria (BUL) [H]</th>\n",
       "      <td>19</td>\n",
       "      <td>51</td>\n",
       "      <td>85</td>\n",
       "      <td>78</td>\n",
       "      <td>214</td>\n",
       "      <td>19</td>\n",
       "      <td>1</td>\n",
       "      <td>2</td>\n",
       "      <td>3</td>\n",
       "      <td>6</td>\n",
       "      <td>38</td>\n",
       "      <td>52</td>\n",
       "      <td>87</td>\n",
       "      <td>81</td>\n",
       "      <td>220</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Burundi (BDI)</th>\n",
       "      <td>5</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>5</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                                 # Summer  Gold  Silver  Bronze  Total  \\\n",
       "Afghanistan (AFG)                      13     0       0       2      2   \n",
       "Algeria (ALG)                          12     5       2       8     15   \n",
       "Argentina (ARG)                        23    18      24      28     70   \n",
       "Armenia (ARM)                           5     1       2       9     12   \n",
       "Australasia (ANZ) [ANZ]                 2     3       4       5     12   \n",
       "Australia (AUS) [AUS] [Z]              25   139     152     177    468   \n",
       "Austria (AUT)                          26    18      33      35     86   \n",
       "Azerbaijan (AZE)                        5     6       5      15     26   \n",
       "Bahamas (BAH)                          15     5       2       5     12   \n",
       "Bahrain (BRN)                           8     0       0       1      1   \n",
       "Barbados (BAR) [BAR]                   11     0       0       1      1   \n",
       "Belarus (BLR)                           5    12      24      39     75   \n",
       "Belgium (BEL)                          25    37      52      53    142   \n",
       "Bermuda (BER)                          17     0       0       1      1   \n",
       "Bohemia (BOH) [BOH] [Z]                 3     0       1       3      4   \n",
       "Botswana (BOT)                          9     0       1       0      1   \n",
       "Brazil (BRA)                           21    23      30      55    108   \n",
       "British West Indies (BWI) [BWI]         1     0       0       2      2   \n",
       "Bulgaria (BUL) [H]                     19    51      85      78    214   \n",
       "Burundi (BDI)                           5     1       0       0      1   \n",
       "\n",
       "                                 # Winter  Gold.1  Silver.1  Bronze.1  \\\n",
       "Afghanistan (AFG)                       0       0         0         0   \n",
       "Algeria (ALG)                           3       0         0         0   \n",
       "Argentina (ARG)                        18       0         0         0   \n",
       "Armenia (ARM)                           6       0         0         0   \n",
       "Australasia (ANZ) [ANZ]                 0       0         0         0   \n",
       "Australia (AUS) [AUS] [Z]              18       5         3         4   \n",
       "Austria (AUT)                          22      59        78        81   \n",
       "Azerbaijan (AZE)                        5       0         0         0   \n",
       "Bahamas (BAH)                           0       0         0         0   \n",
       "Bahrain (BRN)                           0       0         0         0   \n",
       "Barbados (BAR) [BAR]                    0       0         0         0   \n",
       "Belarus (BLR)                           6       6         4         5   \n",
       "Belgium (BEL)                          20       1         1         3   \n",
       "Bermuda (BER)                           7       0         0         0   \n",
       "Bohemia (BOH) [BOH] [Z]                 0       0         0         0   \n",
       "Botswana (BOT)                          0       0         0         0   \n",
       "Brazil (BRA)                            7       0         0         0   \n",
       "British West Indies (BWI) [BWI]         0       0         0         0   \n",
       "Bulgaria (BUL) [H]                     19       1         2         3   \n",
       "Burundi (BDI)                           0       0         0         0   \n",
       "\n",
       "                                 Total.1  # Games  Gold.2  Silver.2  Bronze.2  \\\n",
       "Afghanistan (AFG)                      0       13       0         0         2   \n",
       "Algeria (ALG)                          0       15       5         2         8   \n",
       "Argentina (ARG)                        0       41      18        24        28   \n",
       "Armenia (ARM)                          0       11       1         2         9   \n",
       "Australasia (ANZ) [ANZ]                0        2       3         4         5   \n",
       "Australia (AUS) [AUS] [Z]             12       43     144       155       181   \n",
       "Austria (AUT)                        218       48      77       111       116   \n",
       "Azerbaijan (AZE)                       0       10       6         5        15   \n",
       "Bahamas (BAH)                          0       15       5         2         5   \n",
       "Bahrain (BRN)                          0        8       0         0         1   \n",
       "Barbados (BAR) [BAR]                   0       11       0         0         1   \n",
       "Belarus (BLR)                         15       11      18        28        44   \n",
       "Belgium (BEL)                          5       45      38        53        56   \n",
       "Bermuda (BER)                          0       24       0         0         1   \n",
       "Bohemia (BOH) [BOH] [Z]                0        3       0         1         3   \n",
       "Botswana (BOT)                         0        9       0         1         0   \n",
       "Brazil (BRA)                           0       28      23        30        55   \n",
       "British West Indies (BWI) [BWI]        0        1       0         0         2   \n",
       "Bulgaria (BUL) [H]                     6       38      52        87        81   \n",
       "Burundi (BDI)                          0        5       1         0         0   \n",
       "\n",
       "                                 Combined total  \n",
       "Afghanistan (AFG)                             2  \n",
       "Algeria (ALG)                                15  \n",
       "Argentina (ARG)                              70  \n",
       "Armenia (ARM)                                12  \n",
       "Australasia (ANZ) [ANZ]                      12  \n",
       "Australia (AUS) [AUS] [Z]                   480  \n",
       "Austria (AUT)                               304  \n",
       "Azerbaijan (AZE)                             26  \n",
       "Bahamas (BAH)                                12  \n",
       "Bahrain (BRN)                                 1  \n",
       "Barbados (BAR) [BAR]                          1  \n",
       "Belarus (BLR)                                90  \n",
       "Belgium (BEL)                               147  \n",
       "Bermuda (BER)                                 1  \n",
       "Bohemia (BOH) [BOH] [Z]                       4  \n",
       "Botswana (BOT)                                1  \n",
       "Brazil (BRA)                                108  \n",
       "British West Indies (BWI) [BWI]               2  \n",
       "Bulgaria (BUL) [H]                          220  \n",
       "Burundi (BDI)                                 1  "
      ]
     },
     "execution_count": 112,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "for col in df.columns:\n",
    "    print(col)\n",
    "    if col[:2]=='01':\n",
    "        df.rename(columns={col:'Gold' + col[4:]}, inplace=True)\n",
    "    if col[:2]=='02':\n",
    "        df.rename(columns={col:'Silver' + col[4:]}, inplace=True)\n",
    "    if col[:2]=='03':\n",
    "        df.rename(columns={col:'Bronze' + col[4:]}, inplace=True)\n",
    "    if col[:1]=='№':\n",
    "        df.rename(columns={col:'#' + col[1:]}, inplace=True) \n",
    "\n",
    "df.head(20)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "#### Querying a DataFrame"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 113,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "Afghanistan (AFG)                               False\n",
       "Algeria (ALG)                                    True\n",
       "Argentina (ARG)                                  True\n",
       "Armenia (ARM)                                    True\n",
       "Australasia (ANZ) [ANZ]                          True\n",
       "Australia (AUS) [AUS] [Z]                        True\n",
       "Austria (AUT)                                    True\n",
       "Azerbaijan (AZE)                                 True\n",
       "Bahamas (BAH)                                    True\n",
       "Bahrain (BRN)                                   False\n",
       "Barbados (BAR) [BAR]                            False\n",
       "Belarus (BLR)                                    True\n",
       "Belgium (BEL)                                    True\n",
       "Bermuda (BER)                                   False\n",
       "Bohemia (BOH) [BOH] [Z]                         False\n",
       "Botswana (BOT)                                  False\n",
       "Brazil (BRA)                                     True\n",
       "British West Indies (BWI) [BWI]                 False\n",
       "Bulgaria (BUL) [H]                               True\n",
       "Burundi (BDI)                                    True\n",
       "Cameroon (CMR)                                   True\n",
       "Canada (CAN)                                     True\n",
       "Chile (CHI) [I]                                  True\n",
       "China (CHN) [CHN]                                True\n",
       "Colombia (COL)                                   True\n",
       "Costa Rica (CRC)                                 True\n",
       "Ivory Coast (CIV) [CIV]                         False\n",
       "Croatia (CRO)                                    True\n",
       "Cuba (CUB) [Z]                                   True\n",
       "Cyprus (CYP)                                    False\n",
       "                                                ...  \n",
       "Sri Lanka (SRI) [SRI]                           False\n",
       "Sudan (SUD)                                     False\n",
       "Suriname (SUR) [E]                               True\n",
       "Sweden (SWE) [Z]                                 True\n",
       "Switzerland (SUI)                                True\n",
       "Syria (SYR)                                      True\n",
       "Chinese Taipei (TPE) [TPE] [TPE2]                True\n",
       "Tajikistan (TJK)                                False\n",
       "Tanzania (TAN) [TAN]                            False\n",
       "Thailand (THA)                                   True\n",
       "Togo (TOG)                                      False\n",
       "Tonga (TGA)                                     False\n",
       "Trinidad and Tobago (TRI) [TRI]                  True\n",
       "Tunisia (TUN)                                    True\n",
       "Turkey (TUR)                                     True\n",
       "Uganda (UGA)                                     True\n",
       "Ukraine (UKR)                                    True\n",
       "United Arab Emirates (UAE)                       True\n",
       "United States (USA) [P] [Q] [R] [Z]              True\n",
       "Uruguay (URU)                                    True\n",
       "Uzbekistan (UZB)                                 True\n",
       "Venezuela (VEN)                                  True\n",
       "Vietnam (VIE)                                   False\n",
       "Virgin Islands (ISV)                            False\n",
       "Yugoslavia (YUG) [YUG]                           True\n",
       "Independent Olympic Participants (IOP) [IOP]    False\n",
       "Zambia (ZAM) [ZAM]                              False\n",
       "Zimbabwe (ZIM) [ZIM]                             True\n",
       "Mixed team (ZZX) [ZZX]                           True\n",
       "Totals                                           True\n",
       "Name: Gold, Length: 147, dtype: bool"
      ]
     },
     "execution_count": 113,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Which countries have received gold medals?\n",
    "df['Gold'] > 0"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 114,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th># Summer</th>\n",
       "      <th>Gold</th>\n",
       "      <th>Silver</th>\n",
       "      <th>Bronze</th>\n",
       "      <th>Total</th>\n",
       "      <th># Winter</th>\n",
       "      <th>Gold.1</th>\n",
       "      <th>Silver.1</th>\n",
       "      <th>Bronze.1</th>\n",
       "      <th>Total.1</th>\n",
       "      <th># Games</th>\n",
       "      <th>Gold.2</th>\n",
       "      <th>Silver.2</th>\n",
       "      <th>Bronze.2</th>\n",
       "      <th>Combined total</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>Afghanistan (AFG)</th>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Algeria (ALG)</th>\n",
       "      <td>12.0</td>\n",
       "      <td>5.0</td>\n",
       "      <td>2.0</td>\n",
       "      <td>8.0</td>\n",
       "      <td>15.0</td>\n",
       "      <td>3.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>15.0</td>\n",
       "      <td>5.0</td>\n",
       "      <td>2.0</td>\n",
       "      <td>8.0</td>\n",
       "      <td>15.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Argentina (ARG)</th>\n",
       "      <td>23.0</td>\n",
       "      <td>18.0</td>\n",
       "      <td>24.0</td>\n",
       "      <td>28.0</td>\n",
       "      <td>70.0</td>\n",
       "      <td>18.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>41.0</td>\n",
       "      <td>18.0</td>\n",
       "      <td>24.0</td>\n",
       "      <td>28.0</td>\n",
       "      <td>70.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Armenia (ARM)</th>\n",
       "      <td>5.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>2.0</td>\n",
       "      <td>9.0</td>\n",
       "      <td>12.0</td>\n",
       "      <td>6.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>11.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>2.0</td>\n",
       "      <td>9.0</td>\n",
       "      <td>12.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Australasia (ANZ) [ANZ]</th>\n",
       "      <td>2.0</td>\n",
       "      <td>3.0</td>\n",
       "      <td>4.0</td>\n",
       "      <td>5.0</td>\n",
       "      <td>12.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>2.0</td>\n",
       "      <td>3.0</td>\n",
       "      <td>4.0</td>\n",
       "      <td>5.0</td>\n",
       "      <td>12.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Australia (AUS) [AUS] [Z]</th>\n",
       "      <td>25.0</td>\n",
       "      <td>139.0</td>\n",
       "      <td>152.0</td>\n",
       "      <td>177.0</td>\n",
       "      <td>468.0</td>\n",
       "      <td>18.0</td>\n",
       "      <td>5.0</td>\n",
       "      <td>3.0</td>\n",
       "      <td>4.0</td>\n",
       "      <td>12.0</td>\n",
       "      <td>43.0</td>\n",
       "      <td>144.0</td>\n",
       "      <td>155.0</td>\n",
       "      <td>181.0</td>\n",
       "      <td>480.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Austria (AUT)</th>\n",
       "      <td>26.0</td>\n",
       "      <td>18.0</td>\n",
       "      <td>33.0</td>\n",
       "      <td>35.0</td>\n",
       "      <td>86.0</td>\n",
       "      <td>22.0</td>\n",
       "      <td>59.0</td>\n",
       "      <td>78.0</td>\n",
       "      <td>81.0</td>\n",
       "      <td>218.0</td>\n",
       "      <td>48.0</td>\n",
       "      <td>77.0</td>\n",
       "      <td>111.0</td>\n",
       "      <td>116.0</td>\n",
       "      <td>304.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Azerbaijan (AZE)</th>\n",
       "      <td>5.0</td>\n",
       "      <td>6.0</td>\n",
       "      <td>5.0</td>\n",
       "      <td>15.0</td>\n",
       "      <td>26.0</td>\n",
       "      <td>5.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>10.0</td>\n",
       "      <td>6.0</td>\n",
       "      <td>5.0</td>\n",
       "      <td>15.0</td>\n",
       "      <td>26.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Bahamas (BAH)</th>\n",
       "      <td>15.0</td>\n",
       "      <td>5.0</td>\n",
       "      <td>2.0</td>\n",
       "      <td>5.0</td>\n",
       "      <td>12.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>15.0</td>\n",
       "      <td>5.0</td>\n",
       "      <td>2.0</td>\n",
       "      <td>5.0</td>\n",
       "      <td>12.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Bahrain (BRN)</th>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                           # Summer   Gold  Silver  Bronze  Total  # Winter  \\\n",
       "Afghanistan (AFG)               NaN    NaN     NaN     NaN    NaN       NaN   \n",
       "Algeria (ALG)                  12.0    5.0     2.0     8.0   15.0       3.0   \n",
       "Argentina (ARG)                23.0   18.0    24.0    28.0   70.0      18.0   \n",
       "Armenia (ARM)                   5.0    1.0     2.0     9.0   12.0       6.0   \n",
       "Australasia (ANZ) [ANZ]         2.0    3.0     4.0     5.0   12.0       0.0   \n",
       "Australia (AUS) [AUS] [Z]      25.0  139.0   152.0   177.0  468.0      18.0   \n",
       "Austria (AUT)                  26.0   18.0    33.0    35.0   86.0      22.0   \n",
       "Azerbaijan (AZE)                5.0    6.0     5.0    15.0   26.0       5.0   \n",
       "Bahamas (BAH)                  15.0    5.0     2.0     5.0   12.0       0.0   \n",
       "Bahrain (BRN)                   NaN    NaN     NaN     NaN    NaN       NaN   \n",
       "\n",
       "                           Gold.1  Silver.1  Bronze.1  Total.1  # Games  \\\n",
       "Afghanistan (AFG)             NaN       NaN       NaN      NaN      NaN   \n",
       "Algeria (ALG)                 0.0       0.0       0.0      0.0     15.0   \n",
       "Argentina (ARG)               0.0       0.0       0.0      0.0     41.0   \n",
       "Armenia (ARM)                 0.0       0.0       0.0      0.0     11.0   \n",
       "Australasia (ANZ) [ANZ]       0.0       0.0       0.0      0.0      2.0   \n",
       "Australia (AUS) [AUS] [Z]     5.0       3.0       4.0     12.0     43.0   \n",
       "Austria (AUT)                59.0      78.0      81.0    218.0     48.0   \n",
       "Azerbaijan (AZE)              0.0       0.0       0.0      0.0     10.0   \n",
       "Bahamas (BAH)                 0.0       0.0       0.0      0.0     15.0   \n",
       "Bahrain (BRN)                 NaN       NaN       NaN      NaN      NaN   \n",
       "\n",
       "                           Gold.2  Silver.2  Bronze.2  Combined total  \n",
       "Afghanistan (AFG)             NaN       NaN       NaN             NaN  \n",
       "Algeria (ALG)                 5.0       2.0       8.0            15.0  \n",
       "Argentina (ARG)              18.0      24.0      28.0            70.0  \n",
       "Armenia (ARM)                 1.0       2.0       9.0            12.0  \n",
       "Australasia (ANZ) [ANZ]       3.0       4.0       5.0            12.0  \n",
       "Australia (AUS) [AUS] [Z]   144.0     155.0     181.0           480.0  \n",
       "Austria (AUT)                77.0     111.0     116.0           304.0  \n",
       "Azerbaijan (AZE)              6.0       5.0      15.0            26.0  \n",
       "Bahamas (BAH)                 5.0       2.0       5.0            12.0  \n",
       "Bahrain (BRN)                 NaN       NaN       NaN             NaN  "
      ]
     },
     "execution_count": 114,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Use binary mask to restrict results\n",
    "only_gold = df.where(df['Gold'] > 0)\n",
    "only_gold.head(10)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 115,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th># Summer</th>\n",
       "      <th>Gold</th>\n",
       "      <th>Silver</th>\n",
       "      <th>Bronze</th>\n",
       "      <th>Total</th>\n",
       "      <th># Winter</th>\n",
       "      <th>Gold.1</th>\n",
       "      <th>Silver.1</th>\n",
       "      <th>Bronze.1</th>\n",
       "      <th>Total.1</th>\n",
       "      <th># Games</th>\n",
       "      <th>Gold.2</th>\n",
       "      <th>Silver.2</th>\n",
       "      <th>Bronze.2</th>\n",
       "      <th>Combined total</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>Algeria (ALG)</th>\n",
       "      <td>12.0</td>\n",
       "      <td>5.0</td>\n",
       "      <td>2.0</td>\n",
       "      <td>8.0</td>\n",
       "      <td>15.0</td>\n",
       "      <td>3.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>15.0</td>\n",
       "      <td>5.0</td>\n",
       "      <td>2.0</td>\n",
       "      <td>8.0</td>\n",
       "      <td>15.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Argentina (ARG)</th>\n",
       "      <td>23.0</td>\n",
       "      <td>18.0</td>\n",
       "      <td>24.0</td>\n",
       "      <td>28.0</td>\n",
       "      <td>70.0</td>\n",
       "      <td>18.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>41.0</td>\n",
       "      <td>18.0</td>\n",
       "      <td>24.0</td>\n",
       "      <td>28.0</td>\n",
       "      <td>70.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Armenia (ARM)</th>\n",
       "      <td>5.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>2.0</td>\n",
       "      <td>9.0</td>\n",
       "      <td>12.0</td>\n",
       "      <td>6.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>11.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>2.0</td>\n",
       "      <td>9.0</td>\n",
       "      <td>12.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Australasia (ANZ) [ANZ]</th>\n",
       "      <td>2.0</td>\n",
       "      <td>3.0</td>\n",
       "      <td>4.0</td>\n",
       "      <td>5.0</td>\n",
       "      <td>12.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>2.0</td>\n",
       "      <td>3.0</td>\n",
       "      <td>4.0</td>\n",
       "      <td>5.0</td>\n",
       "      <td>12.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Australia (AUS) [AUS] [Z]</th>\n",
       "      <td>25.0</td>\n",
       "      <td>139.0</td>\n",
       "      <td>152.0</td>\n",
       "      <td>177.0</td>\n",
       "      <td>468.0</td>\n",
       "      <td>18.0</td>\n",
       "      <td>5.0</td>\n",
       "      <td>3.0</td>\n",
       "      <td>4.0</td>\n",
       "      <td>12.0</td>\n",
       "      <td>43.0</td>\n",
       "      <td>144.0</td>\n",
       "      <td>155.0</td>\n",
       "      <td>181.0</td>\n",
       "      <td>480.0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                           # Summer   Gold  Silver  Bronze  Total  # Winter  \\\n",
       "Algeria (ALG)                  12.0    5.0     2.0     8.0   15.0       3.0   \n",
       "Argentina (ARG)                23.0   18.0    24.0    28.0   70.0      18.0   \n",
       "Armenia (ARM)                   5.0    1.0     2.0     9.0   12.0       6.0   \n",
       "Australasia (ANZ) [ANZ]         2.0    3.0     4.0     5.0   12.0       0.0   \n",
       "Australia (AUS) [AUS] [Z]      25.0  139.0   152.0   177.0  468.0      18.0   \n",
       "\n",
       "                           Gold.1  Silver.1  Bronze.1  Total.1  # Games  \\\n",
       "Algeria (ALG)                 0.0       0.0       0.0      0.0     15.0   \n",
       "Argentina (ARG)               0.0       0.0       0.0      0.0     41.0   \n",
       "Armenia (ARM)                 0.0       0.0       0.0      0.0     11.0   \n",
       "Australasia (ANZ) [ANZ]       0.0       0.0       0.0      0.0      2.0   \n",
       "Australia (AUS) [AUS] [Z]     5.0       3.0       4.0     12.0     43.0   \n",
       "\n",
       "                           Gold.2  Silver.2  Bronze.2  Combined total  \n",
       "Algeria (ALG)                 5.0       2.0       8.0            15.0  \n",
       "Argentina (ARG)              18.0      24.0      28.0            70.0  \n",
       "Armenia (ARM)                 1.0       2.0       9.0            12.0  \n",
       "Australasia (ANZ) [ANZ]       3.0       4.0       5.0            12.0  \n",
       "Australia (AUS) [AUS] [Z]   144.0     155.0     181.0           480.0  "
      ]
     },
     "execution_count": 115,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "only_gold = only_gold.dropna()\n",
    "only_gold.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 116,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "147"
      ]
     },
     "execution_count": 116,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df['Gold'].count()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Slightly more comlex binary mask"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 117,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th># Summer</th>\n",
       "      <th>Gold</th>\n",
       "      <th>Silver</th>\n",
       "      <th>Bronze</th>\n",
       "      <th>Total</th>\n",
       "      <th># Winter</th>\n",
       "      <th>Gold.1</th>\n",
       "      <th>Silver.1</th>\n",
       "      <th>Bronze.1</th>\n",
       "      <th>Total.1</th>\n",
       "      <th># Games</th>\n",
       "      <th>Gold.2</th>\n",
       "      <th>Silver.2</th>\n",
       "      <th>Bronze.2</th>\n",
       "      <th>Combined total</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>Liechtenstein (LIE)</th>\n",
       "      <td>16</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>18</td>\n",
       "      <td>2</td>\n",
       "      <td>2</td>\n",
       "      <td>5</td>\n",
       "      <td>9</td>\n",
       "      <td>34</td>\n",
       "      <td>2</td>\n",
       "      <td>2</td>\n",
       "      <td>5</td>\n",
       "      <td>9</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                     # Summer  Gold  Silver  Bronze  Total  # Winter  Gold.1  \\\n",
       "Liechtenstein (LIE)        16     0       0       0      0        18       2   \n",
       "\n",
       "                     Silver.1  Bronze.1  Total.1  # Games  Gold.2  Silver.2  \\\n",
       "Liechtenstein (LIE)         2         5        9       34       2         2   \n",
       "\n",
       "                     Bronze.2  Combined total  \n",
       "Liechtenstein (LIE)         5               9  "
      ]
     },
     "execution_count": 117,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# winter gold, no summer gold\n",
    "df[(df['Gold.1'] > 0) & (df['Gold'] == 0)]"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "#### Indexing dataframes"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 118,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th># Summer</th>\n",
       "      <th>Gold</th>\n",
       "      <th>Silver</th>\n",
       "      <th>Bronze</th>\n",
       "      <th>Total</th>\n",
       "      <th># Winter</th>\n",
       "      <th>Gold.1</th>\n",
       "      <th>Silver.1</th>\n",
       "      <th>Bronze.1</th>\n",
       "      <th>Total.1</th>\n",
       "      <th># Games</th>\n",
       "      <th>Gold.2</th>\n",
       "      <th>Silver.2</th>\n",
       "      <th>Bronze.2</th>\n",
       "      <th>Combined total</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>Afghanistan (AFG)</th>\n",
       "      <td>13</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>2</td>\n",
       "      <td>2</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>13</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>2</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Algeria (ALG)</th>\n",
       "      <td>12</td>\n",
       "      <td>5</td>\n",
       "      <td>2</td>\n",
       "      <td>8</td>\n",
       "      <td>15</td>\n",
       "      <td>3</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>15</td>\n",
       "      <td>5</td>\n",
       "      <td>2</td>\n",
       "      <td>8</td>\n",
       "      <td>15</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Argentina (ARG)</th>\n",
       "      <td>23</td>\n",
       "      <td>18</td>\n",
       "      <td>24</td>\n",
       "      <td>28</td>\n",
       "      <td>70</td>\n",
       "      <td>18</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>41</td>\n",
       "      <td>18</td>\n",
       "      <td>24</td>\n",
       "      <td>28</td>\n",
       "      <td>70</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Armenia (ARM)</th>\n",
       "      <td>5</td>\n",
       "      <td>1</td>\n",
       "      <td>2</td>\n",
       "      <td>9</td>\n",
       "      <td>12</td>\n",
       "      <td>6</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>11</td>\n",
       "      <td>1</td>\n",
       "      <td>2</td>\n",
       "      <td>9</td>\n",
       "      <td>12</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Australasia (ANZ) [ANZ]</th>\n",
       "      <td>2</td>\n",
       "      <td>3</td>\n",
       "      <td>4</td>\n",
       "      <td>5</td>\n",
       "      <td>12</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>2</td>\n",
       "      <td>3</td>\n",
       "      <td>4</td>\n",
       "      <td>5</td>\n",
       "      <td>12</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                         # Summer  Gold  Silver  Bronze  Total  # Winter  \\\n",
       "Afghanistan (AFG)              13     0       0       2      2         0   \n",
       "Algeria (ALG)                  12     5       2       8     15         3   \n",
       "Argentina (ARG)                23    18      24      28     70        18   \n",
       "Armenia (ARM)                   5     1       2       9     12         6   \n",
       "Australasia (ANZ) [ANZ]         2     3       4       5     12         0   \n",
       "\n",
       "                         Gold.1  Silver.1  Bronze.1  Total.1  # Games  Gold.2  \\\n",
       "Afghanistan (AFG)             0         0         0        0       13       0   \n",
       "Algeria (ALG)                 0         0         0        0       15       5   \n",
       "Argentina (ARG)               0         0         0        0       41      18   \n",
       "Armenia (ARM)                 0         0         0        0       11       1   \n",
       "Australasia (ANZ) [ANZ]       0         0         0        0        2       3   \n",
       "\n",
       "                         Silver.2  Bronze.2  Combined total  \n",
       "Afghanistan (AFG)               0         2               2  \n",
       "Algeria (ALG)                   2         8              15  \n",
       "Argentina (ARG)                24        28              70  \n",
       "Armenia (ARM)                   2         9              12  \n",
       "Australasia (ANZ) [ANZ]         4         5              12  "
      ]
     },
     "execution_count": 118,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 119,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th># Summer</th>\n",
       "      <th>Silver</th>\n",
       "      <th>Bronze</th>\n",
       "      <th>Total</th>\n",
       "      <th># Winter</th>\n",
       "      <th>Gold.1</th>\n",
       "      <th>Silver.1</th>\n",
       "      <th>Bronze.1</th>\n",
       "      <th>Total.1</th>\n",
       "      <th># Games</th>\n",
       "      <th>Gold.2</th>\n",
       "      <th>Silver.2</th>\n",
       "      <th>Bronze.2</th>\n",
       "      <th>Combined total</th>\n",
       "      <th>country</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Gold</th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>13</td>\n",
       "      <td>0</td>\n",
       "      <td>2</td>\n",
       "      <td>2</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>13</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>2</td>\n",
       "      <td>2</td>\n",
       "      <td>Afghanistan (AFG)</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5</th>\n",
       "      <td>12</td>\n",
       "      <td>2</td>\n",
       "      <td>8</td>\n",
       "      <td>15</td>\n",
       "      <td>3</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>15</td>\n",
       "      <td>5</td>\n",
       "      <td>2</td>\n",
       "      <td>8</td>\n",
       "      <td>15</td>\n",
       "      <td>Algeria (ALG)</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>18</th>\n",
       "      <td>23</td>\n",
       "      <td>24</td>\n",
       "      <td>28</td>\n",
       "      <td>70</td>\n",
       "      <td>18</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>41</td>\n",
       "      <td>18</td>\n",
       "      <td>24</td>\n",
       "      <td>28</td>\n",
       "      <td>70</td>\n",
       "      <td>Argentina (ARG)</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>5</td>\n",
       "      <td>2</td>\n",
       "      <td>9</td>\n",
       "      <td>12</td>\n",
       "      <td>6</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>11</td>\n",
       "      <td>1</td>\n",
       "      <td>2</td>\n",
       "      <td>9</td>\n",
       "      <td>12</td>\n",
       "      <td>Armenia (ARM)</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>2</td>\n",
       "      <td>4</td>\n",
       "      <td>5</td>\n",
       "      <td>12</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>2</td>\n",
       "      <td>3</td>\n",
       "      <td>4</td>\n",
       "      <td>5</td>\n",
       "      <td>12</td>\n",
       "      <td>Australasia (ANZ) [ANZ]</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "      # Summer  Silver  Bronze  Total  # Winter  Gold.1  Silver.1  Bronze.1  \\\n",
       "Gold                                                                          \n",
       "0           13       0       2      2         0       0         0         0   \n",
       "5           12       2       8     15         3       0         0         0   \n",
       "18          23      24      28     70        18       0         0         0   \n",
       "1            5       2       9     12         6       0         0         0   \n",
       "3            2       4       5     12         0       0         0         0   \n",
       "\n",
       "      Total.1  # Games  Gold.2  Silver.2  Bronze.2  Combined total  \\\n",
       "Gold                                                                 \n",
       "0           0       13       0         0         2               2   \n",
       "5           0       15       5         2         8              15   \n",
       "18          0       41      18        24        28              70   \n",
       "1           0       11       1         2         9              12   \n",
       "3           0        2       3         4         5              12   \n",
       "\n",
       "                      country  \n",
       "Gold                           \n",
       "0           Afghanistan (AFG)  \n",
       "5               Algeria (ALG)  \n",
       "18            Argentina (ARG)  \n",
       "1               Armenia (ARM)  \n",
       "3     Australasia (ANZ) [ANZ]  "
      ]
     },
     "execution_count": 119,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df['country'] = df.index\n",
    "df = df.set_index('Gold')\n",
    "df.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 120,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>Gold</th>\n",
       "      <th># Summer</th>\n",
       "      <th>Silver</th>\n",
       "      <th>Bronze</th>\n",
       "      <th>Total</th>\n",
       "      <th># Winter</th>\n",
       "      <th>Gold.1</th>\n",
       "      <th>Silver.1</th>\n",
       "      <th>Bronze.1</th>\n",
       "      <th>Total.1</th>\n",
       "      <th># Games</th>\n",
       "      <th>Gold.2</th>\n",
       "      <th>Silver.2</th>\n",
       "      <th>Bronze.2</th>\n",
       "      <th>Combined total</th>\n",
       "      <th>country</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>0</td>\n",
       "      <td>13</td>\n",
       "      <td>0</td>\n",
       "      <td>2</td>\n",
       "      <td>2</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>13</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>2</td>\n",
       "      <td>2</td>\n",
       "      <td>Afghanistan (AFG)</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>5</td>\n",
       "      <td>12</td>\n",
       "      <td>2</td>\n",
       "      <td>8</td>\n",
       "      <td>15</td>\n",
       "      <td>3</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>15</td>\n",
       "      <td>5</td>\n",
       "      <td>2</td>\n",
       "      <td>8</td>\n",
       "      <td>15</td>\n",
       "      <td>Algeria (ALG)</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>18</td>\n",
       "      <td>23</td>\n",
       "      <td>24</td>\n",
       "      <td>28</td>\n",
       "      <td>70</td>\n",
       "      <td>18</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>41</td>\n",
       "      <td>18</td>\n",
       "      <td>24</td>\n",
       "      <td>28</td>\n",
       "      <td>70</td>\n",
       "      <td>Argentina (ARG)</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>1</td>\n",
       "      <td>5</td>\n",
       "      <td>2</td>\n",
       "      <td>9</td>\n",
       "      <td>12</td>\n",
       "      <td>6</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>11</td>\n",
       "      <td>1</td>\n",
       "      <td>2</td>\n",
       "      <td>9</td>\n",
       "      <td>12</td>\n",
       "      <td>Armenia (ARM)</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>3</td>\n",
       "      <td>2</td>\n",
       "      <td>4</td>\n",
       "      <td>5</td>\n",
       "      <td>12</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>2</td>\n",
       "      <td>3</td>\n",
       "      <td>4</td>\n",
       "      <td>5</td>\n",
       "      <td>12</td>\n",
       "      <td>Australasia (ANZ) [ANZ]</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   Gold  # Summer  Silver  Bronze  Total  # Winter  Gold.1  Silver.1  \\\n",
       "0     0        13       0       2      2         0       0         0   \n",
       "1     5        12       2       8     15         3       0         0   \n",
       "2    18        23      24      28     70        18       0         0   \n",
       "3     1         5       2       9     12         6       0         0   \n",
       "4     3         2       4       5     12         0       0         0   \n",
       "\n",
       "   Bronze.1  Total.1  # Games  Gold.2  Silver.2  Bronze.2  Combined total  \\\n",
       "0         0        0       13       0         0         2               2   \n",
       "1         0        0       15       5         2         8              15   \n",
       "2         0        0       41      18        24        28              70   \n",
       "3         0        0       11       1         2         9              12   \n",
       "4         0        0        2       3         4         5              12   \n",
       "\n",
       "                   country  \n",
       "0        Afghanistan (AFG)  \n",
       "1            Algeria (ALG)  \n",
       "2          Argentina (ARG)  \n",
       "3            Armenia (ARM)  \n",
       "4  Australasia (ANZ) [ANZ]  "
      ]
     },
     "execution_count": 120,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df = df.reset_index()\n",
    "df.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 121,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>SUMLEV</th>\n",
       "      <th>REGION</th>\n",
       "      <th>DIVISION</th>\n",
       "      <th>STATE</th>\n",
       "      <th>COUNTY</th>\n",
       "      <th>STNAME</th>\n",
       "      <th>CTYNAME</th>\n",
       "      <th>CENSUS2010POP</th>\n",
       "      <th>ESTIMATESBASE2010</th>\n",
       "      <th>POPESTIMATE2010</th>\n",
       "      <th>...</th>\n",
       "      <th>RDOMESTICMIG2011</th>\n",
       "      <th>RDOMESTICMIG2012</th>\n",
       "      <th>RDOMESTICMIG2013</th>\n",
       "      <th>RDOMESTICMIG2014</th>\n",
       "      <th>RDOMESTICMIG2015</th>\n",
       "      <th>RNETMIG2011</th>\n",
       "      <th>RNETMIG2012</th>\n",
       "      <th>RNETMIG2013</th>\n",
       "      <th>RNETMIG2014</th>\n",
       "      <th>RNETMIG2015</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>40</td>\n",
       "      <td>3</td>\n",
       "      <td>6</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>Alabama</td>\n",
       "      <td>Alabama</td>\n",
       "      <td>4779736</td>\n",
       "      <td>4780127</td>\n",
       "      <td>4785161</td>\n",
       "      <td>...</td>\n",
       "      <td>0.002295</td>\n",
       "      <td>-0.193196</td>\n",
       "      <td>0.381066</td>\n",
       "      <td>0.582002</td>\n",
       "      <td>-0.467369</td>\n",
       "      <td>1.030015</td>\n",
       "      <td>0.826644</td>\n",
       "      <td>1.383282</td>\n",
       "      <td>1.724718</td>\n",
       "      <td>0.712594</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>50</td>\n",
       "      <td>3</td>\n",
       "      <td>6</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>Alabama</td>\n",
       "      <td>Autauga County</td>\n",
       "      <td>54571</td>\n",
       "      <td>54571</td>\n",
       "      <td>54660</td>\n",
       "      <td>...</td>\n",
       "      <td>7.242091</td>\n",
       "      <td>-2.915927</td>\n",
       "      <td>-3.012349</td>\n",
       "      <td>2.265971</td>\n",
       "      <td>-2.530799</td>\n",
       "      <td>7.606016</td>\n",
       "      <td>-2.626146</td>\n",
       "      <td>-2.722002</td>\n",
       "      <td>2.592270</td>\n",
       "      <td>-2.187333</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>50</td>\n",
       "      <td>3</td>\n",
       "      <td>6</td>\n",
       "      <td>1</td>\n",
       "      <td>3</td>\n",
       "      <td>Alabama</td>\n",
       "      <td>Baldwin County</td>\n",
       "      <td>182265</td>\n",
       "      <td>182265</td>\n",
       "      <td>183193</td>\n",
       "      <td>...</td>\n",
       "      <td>14.832960</td>\n",
       "      <td>17.647293</td>\n",
       "      <td>21.845705</td>\n",
       "      <td>19.243287</td>\n",
       "      <td>17.197872</td>\n",
       "      <td>15.844176</td>\n",
       "      <td>18.559627</td>\n",
       "      <td>22.727626</td>\n",
       "      <td>20.317142</td>\n",
       "      <td>18.293499</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>50</td>\n",
       "      <td>3</td>\n",
       "      <td>6</td>\n",
       "      <td>1</td>\n",
       "      <td>5</td>\n",
       "      <td>Alabama</td>\n",
       "      <td>Barbour County</td>\n",
       "      <td>27457</td>\n",
       "      <td>27457</td>\n",
       "      <td>27341</td>\n",
       "      <td>...</td>\n",
       "      <td>-4.728132</td>\n",
       "      <td>-2.500690</td>\n",
       "      <td>-7.056824</td>\n",
       "      <td>-3.904217</td>\n",
       "      <td>-10.543299</td>\n",
       "      <td>-4.874741</td>\n",
       "      <td>-2.758113</td>\n",
       "      <td>-7.167664</td>\n",
       "      <td>-3.978583</td>\n",
       "      <td>-10.543299</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>50</td>\n",
       "      <td>3</td>\n",
       "      <td>6</td>\n",
       "      <td>1</td>\n",
       "      <td>7</td>\n",
       "      <td>Alabama</td>\n",
       "      <td>Bibb County</td>\n",
       "      <td>22915</td>\n",
       "      <td>22919</td>\n",
       "      <td>22861</td>\n",
       "      <td>...</td>\n",
       "      <td>-5.527043</td>\n",
       "      <td>-5.068871</td>\n",
       "      <td>-6.201001</td>\n",
       "      <td>-0.177537</td>\n",
       "      <td>0.177258</td>\n",
       "      <td>-5.088389</td>\n",
       "      <td>-4.363636</td>\n",
       "      <td>-5.403729</td>\n",
       "      <td>0.754533</td>\n",
       "      <td>1.107861</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>5 rows × 100 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "   SUMLEV  REGION  DIVISION  STATE  COUNTY   STNAME         CTYNAME  \\\n",
       "0      40       3         6      1       0  Alabama         Alabama   \n",
       "1      50       3         6      1       1  Alabama  Autauga County   \n",
       "2      50       3         6      1       3  Alabama  Baldwin County   \n",
       "3      50       3         6      1       5  Alabama  Barbour County   \n",
       "4      50       3         6      1       7  Alabama     Bibb County   \n",
       "\n",
       "   CENSUS2010POP  ESTIMATESBASE2010  POPESTIMATE2010     ...       \\\n",
       "0        4779736            4780127          4785161     ...        \n",
       "1          54571              54571            54660     ...        \n",
       "2         182265             182265           183193     ...        \n",
       "3          27457              27457            27341     ...        \n",
       "4          22915              22919            22861     ...        \n",
       "\n",
       "   RDOMESTICMIG2011  RDOMESTICMIG2012  RDOMESTICMIG2013  RDOMESTICMIG2014  \\\n",
       "0          0.002295         -0.193196          0.381066          0.582002   \n",
       "1          7.242091         -2.915927         -3.012349          2.265971   \n",
       "2         14.832960         17.647293         21.845705         19.243287   \n",
       "3         -4.728132         -2.500690         -7.056824         -3.904217   \n",
       "4         -5.527043         -5.068871         -6.201001         -0.177537   \n",
       "\n",
       "   RDOMESTICMIG2015  RNETMIG2011  RNETMIG2012  RNETMIG2013  RNETMIG2014  \\\n",
       "0         -0.467369     1.030015     0.826644     1.383282     1.724718   \n",
       "1         -2.530799     7.606016    -2.626146    -2.722002     2.592270   \n",
       "2         17.197872    15.844176    18.559627    22.727626    20.317142   \n",
       "3        -10.543299    -4.874741    -2.758113    -7.167664    -3.978583   \n",
       "4          0.177258    -5.088389    -4.363636    -5.403729     0.754533   \n",
       "\n",
       "   RNETMIG2015  \n",
       "0     0.712594  \n",
       "1    -2.187333  \n",
       "2    18.293499  \n",
       "3   -10.543299  \n",
       "4     1.107861  \n",
       "\n",
       "[5 rows x 100 columns]"
      ]
     },
     "execution_count": 121,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df = pd.read_csv('data/census.csv')\n",
    "df.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 122,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([40, 50])"
      ]
     },
     "execution_count": 122,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df['SUMLEV'].unique()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 123,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>SUMLEV</th>\n",
       "      <th>REGION</th>\n",
       "      <th>DIVISION</th>\n",
       "      <th>STATE</th>\n",
       "      <th>COUNTY</th>\n",
       "      <th>STNAME</th>\n",
       "      <th>CTYNAME</th>\n",
       "      <th>CENSUS2010POP</th>\n",
       "      <th>ESTIMATESBASE2010</th>\n",
       "      <th>POPESTIMATE2010</th>\n",
       "      <th>...</th>\n",
       "      <th>RDOMESTICMIG2011</th>\n",
       "      <th>RDOMESTICMIG2012</th>\n",
       "      <th>RDOMESTICMIG2013</th>\n",
       "      <th>RDOMESTICMIG2014</th>\n",
       "      <th>RDOMESTICMIG2015</th>\n",
       "      <th>RNETMIG2011</th>\n",
       "      <th>RNETMIG2012</th>\n",
       "      <th>RNETMIG2013</th>\n",
       "      <th>RNETMIG2014</th>\n",
       "      <th>RNETMIG2015</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>50</td>\n",
       "      <td>3</td>\n",
       "      <td>6</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>Alabama</td>\n",
       "      <td>Autauga County</td>\n",
       "      <td>54571</td>\n",
       "      <td>54571</td>\n",
       "      <td>54660</td>\n",
       "      <td>...</td>\n",
       "      <td>7.242091</td>\n",
       "      <td>-2.915927</td>\n",
       "      <td>-3.012349</td>\n",
       "      <td>2.265971</td>\n",
       "      <td>-2.530799</td>\n",
       "      <td>7.606016</td>\n",
       "      <td>-2.626146</td>\n",
       "      <td>-2.722002</td>\n",
       "      <td>2.592270</td>\n",
       "      <td>-2.187333</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>50</td>\n",
       "      <td>3</td>\n",
       "      <td>6</td>\n",
       "      <td>1</td>\n",
       "      <td>3</td>\n",
       "      <td>Alabama</td>\n",
       "      <td>Baldwin County</td>\n",
       "      <td>182265</td>\n",
       "      <td>182265</td>\n",
       "      <td>183193</td>\n",
       "      <td>...</td>\n",
       "      <td>14.832960</td>\n",
       "      <td>17.647293</td>\n",
       "      <td>21.845705</td>\n",
       "      <td>19.243287</td>\n",
       "      <td>17.197872</td>\n",
       "      <td>15.844176</td>\n",
       "      <td>18.559627</td>\n",
       "      <td>22.727626</td>\n",
       "      <td>20.317142</td>\n",
       "      <td>18.293499</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>50</td>\n",
       "      <td>3</td>\n",
       "      <td>6</td>\n",
       "      <td>1</td>\n",
       "      <td>5</td>\n",
       "      <td>Alabama</td>\n",
       "      <td>Barbour County</td>\n",
       "      <td>27457</td>\n",
       "      <td>27457</td>\n",
       "      <td>27341</td>\n",
       "      <td>...</td>\n",
       "      <td>-4.728132</td>\n",
       "      <td>-2.500690</td>\n",
       "      <td>-7.056824</td>\n",
       "      <td>-3.904217</td>\n",
       "      <td>-10.543299</td>\n",
       "      <td>-4.874741</td>\n",
       "      <td>-2.758113</td>\n",
       "      <td>-7.167664</td>\n",
       "      <td>-3.978583</td>\n",
       "      <td>-10.543299</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>50</td>\n",
       "      <td>3</td>\n",
       "      <td>6</td>\n",
       "      <td>1</td>\n",
       "      <td>7</td>\n",
       "      <td>Alabama</td>\n",
       "      <td>Bibb County</td>\n",
       "      <td>22915</td>\n",
       "      <td>22919</td>\n",
       "      <td>22861</td>\n",
       "      <td>...</td>\n",
       "      <td>-5.527043</td>\n",
       "      <td>-5.068871</td>\n",
       "      <td>-6.201001</td>\n",
       "      <td>-0.177537</td>\n",
       "      <td>0.177258</td>\n",
       "      <td>-5.088389</td>\n",
       "      <td>-4.363636</td>\n",
       "      <td>-5.403729</td>\n",
       "      <td>0.754533</td>\n",
       "      <td>1.107861</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5</th>\n",
       "      <td>50</td>\n",
       "      <td>3</td>\n",
       "      <td>6</td>\n",
       "      <td>1</td>\n",
       "      <td>9</td>\n",
       "      <td>Alabama</td>\n",
       "      <td>Blount County</td>\n",
       "      <td>57322</td>\n",
       "      <td>57322</td>\n",
       "      <td>57373</td>\n",
       "      <td>...</td>\n",
       "      <td>1.807375</td>\n",
       "      <td>-1.177622</td>\n",
       "      <td>-1.748766</td>\n",
       "      <td>-2.062535</td>\n",
       "      <td>-1.369970</td>\n",
       "      <td>1.859511</td>\n",
       "      <td>-0.848580</td>\n",
       "      <td>-1.402476</td>\n",
       "      <td>-1.577232</td>\n",
       "      <td>-0.884411</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>5 rows × 100 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "   SUMLEV  REGION  DIVISION  STATE  COUNTY   STNAME         CTYNAME  \\\n",
       "1      50       3         6      1       1  Alabama  Autauga County   \n",
       "2      50       3         6      1       3  Alabama  Baldwin County   \n",
       "3      50       3         6      1       5  Alabama  Barbour County   \n",
       "4      50       3         6      1       7  Alabama     Bibb County   \n",
       "5      50       3         6      1       9  Alabama   Blount County   \n",
       "\n",
       "   CENSUS2010POP  ESTIMATESBASE2010  POPESTIMATE2010     ...       \\\n",
       "1          54571              54571            54660     ...        \n",
       "2         182265             182265           183193     ...        \n",
       "3          27457              27457            27341     ...        \n",
       "4          22915              22919            22861     ...        \n",
       "5          57322              57322            57373     ...        \n",
       "\n",
       "   RDOMESTICMIG2011  RDOMESTICMIG2012  RDOMESTICMIG2013  RDOMESTICMIG2014  \\\n",
       "1          7.242091         -2.915927         -3.012349          2.265971   \n",
       "2         14.832960         17.647293         21.845705         19.243287   \n",
       "3         -4.728132         -2.500690         -7.056824         -3.904217   \n",
       "4         -5.527043         -5.068871         -6.201001         -0.177537   \n",
       "5          1.807375         -1.177622         -1.748766         -2.062535   \n",
       "\n",
       "   RDOMESTICMIG2015  RNETMIG2011  RNETMIG2012  RNETMIG2013  RNETMIG2014  \\\n",
       "1         -2.530799     7.606016    -2.626146    -2.722002     2.592270   \n",
       "2         17.197872    15.844176    18.559627    22.727626    20.317142   \n",
       "3        -10.543299    -4.874741    -2.758113    -7.167664    -3.978583   \n",
       "4          0.177258    -5.088389    -4.363636    -5.403729     0.754533   \n",
       "5         -1.369970     1.859511    -0.848580    -1.402476    -1.577232   \n",
       "\n",
       "   RNETMIG2015  \n",
       "1    -2.187333  \n",
       "2    18.293499  \n",
       "3   -10.543299  \n",
       "4     1.107861  \n",
       "5    -0.884411  \n",
       "\n",
       "[5 rows x 100 columns]"
      ]
     },
     "execution_count": 123,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df=df[df['SUMLEV'] == 50]\n",
    "df.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 124,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>STNAME</th>\n",
       "      <th>CTYNAME</th>\n",
       "      <th>BIRTHS2010</th>\n",
       "      <th>BIRTHS2011</th>\n",
       "      <th>BIRTHS2012</th>\n",
       "      <th>BIRTHS2013</th>\n",
       "      <th>BIRTHS2014</th>\n",
       "      <th>BIRTHS2015</th>\n",
       "      <th>POPESTIMATE2010</th>\n",
       "      <th>POPESTIMATE2011</th>\n",
       "      <th>POPESTIMATE2012</th>\n",
       "      <th>POPESTIMATE2013</th>\n",
       "      <th>POPESTIMATE2014</th>\n",
       "      <th>POPESTIMATE2015</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>Alabama</td>\n",
       "      <td>Autauga County</td>\n",
       "      <td>151</td>\n",
       "      <td>636</td>\n",
       "      <td>615</td>\n",
       "      <td>574</td>\n",
       "      <td>623</td>\n",
       "      <td>600</td>\n",
       "      <td>54660</td>\n",
       "      <td>55253</td>\n",
       "      <td>55175</td>\n",
       "      <td>55038</td>\n",
       "      <td>55290</td>\n",
       "      <td>55347</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>Alabama</td>\n",
       "      <td>Baldwin County</td>\n",
       "      <td>517</td>\n",
       "      <td>2187</td>\n",
       "      <td>2092</td>\n",
       "      <td>2160</td>\n",
       "      <td>2186</td>\n",
       "      <td>2240</td>\n",
       "      <td>183193</td>\n",
       "      <td>186659</td>\n",
       "      <td>190396</td>\n",
       "      <td>195126</td>\n",
       "      <td>199713</td>\n",
       "      <td>203709</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>Alabama</td>\n",
       "      <td>Barbour County</td>\n",
       "      <td>70</td>\n",
       "      <td>335</td>\n",
       "      <td>300</td>\n",
       "      <td>283</td>\n",
       "      <td>260</td>\n",
       "      <td>269</td>\n",
       "      <td>27341</td>\n",
       "      <td>27226</td>\n",
       "      <td>27159</td>\n",
       "      <td>26973</td>\n",
       "      <td>26815</td>\n",
       "      <td>26489</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>Alabama</td>\n",
       "      <td>Bibb County</td>\n",
       "      <td>44</td>\n",
       "      <td>266</td>\n",
       "      <td>245</td>\n",
       "      <td>259</td>\n",
       "      <td>247</td>\n",
       "      <td>253</td>\n",
       "      <td>22861</td>\n",
       "      <td>22733</td>\n",
       "      <td>22642</td>\n",
       "      <td>22512</td>\n",
       "      <td>22549</td>\n",
       "      <td>22583</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5</th>\n",
       "      <td>Alabama</td>\n",
       "      <td>Blount County</td>\n",
       "      <td>183</td>\n",
       "      <td>744</td>\n",
       "      <td>710</td>\n",
       "      <td>646</td>\n",
       "      <td>618</td>\n",
       "      <td>603</td>\n",
       "      <td>57373</td>\n",
       "      <td>57711</td>\n",
       "      <td>57776</td>\n",
       "      <td>57734</td>\n",
       "      <td>57658</td>\n",
       "      <td>57673</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "    STNAME         CTYNAME  BIRTHS2010  BIRTHS2011  BIRTHS2012  BIRTHS2013  \\\n",
       "1  Alabama  Autauga County         151         636         615         574   \n",
       "2  Alabama  Baldwin County         517        2187        2092        2160   \n",
       "3  Alabama  Barbour County          70         335         300         283   \n",
       "4  Alabama     Bibb County          44         266         245         259   \n",
       "5  Alabama   Blount County         183         744         710         646   \n",
       "\n",
       "   BIRTHS2014  BIRTHS2015  POPESTIMATE2010  POPESTIMATE2011  POPESTIMATE2012  \\\n",
       "1         623         600            54660            55253            55175   \n",
       "2        2186        2240           183193           186659           190396   \n",
       "3         260         269            27341            27226            27159   \n",
       "4         247         253            22861            22733            22642   \n",
       "5         618         603            57373            57711            57776   \n",
       "\n",
       "   POPESTIMATE2013  POPESTIMATE2014  POPESTIMATE2015  \n",
       "1            55038            55290            55347  \n",
       "2           195126           199713           203709  \n",
       "3            26973            26815            26489  \n",
       "4            22512            22549            22583  \n",
       "5            57734            57658            57673  "
      ]
     },
     "execution_count": 124,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "columns_to_keep = ['STNAME',\n",
    "                   'CTYNAME',\n",
    "                   'BIRTHS2010',\n",
    "                   'BIRTHS2011',\n",
    "                   'BIRTHS2012',\n",
    "                   'BIRTHS2013',\n",
    "                   'BIRTHS2014',\n",
    "                   'BIRTHS2015',\n",
    "                   'POPESTIMATE2010',\n",
    "                   'POPESTIMATE2011',\n",
    "                   'POPESTIMATE2012',\n",
    "                   'POPESTIMATE2013',\n",
    "                   'POPESTIMATE2014',\n",
    "                   'POPESTIMATE2015']\n",
    "df = df[columns_to_keep]\n",
    "df.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 125,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th>BIRTHS2010</th>\n",
       "      <th>BIRTHS2011</th>\n",
       "      <th>BIRTHS2012</th>\n",
       "      <th>BIRTHS2013</th>\n",
       "      <th>BIRTHS2014</th>\n",
       "      <th>BIRTHS2015</th>\n",
       "      <th>POPESTIMATE2010</th>\n",
       "      <th>POPESTIMATE2011</th>\n",
       "      <th>POPESTIMATE2012</th>\n",
       "      <th>POPESTIMATE2013</th>\n",
       "      <th>POPESTIMATE2014</th>\n",
       "      <th>POPESTIMATE2015</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>STNAME</th>\n",
       "      <th>CTYNAME</th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th rowspan=\"5\" valign=\"top\">Alabama</th>\n",
       "      <th>Autauga County</th>\n",
       "      <td>151</td>\n",
       "      <td>636</td>\n",
       "      <td>615</td>\n",
       "      <td>574</td>\n",
       "      <td>623</td>\n",
       "      <td>600</td>\n",
       "      <td>54660</td>\n",
       "      <td>55253</td>\n",
       "      <td>55175</td>\n",
       "      <td>55038</td>\n",
       "      <td>55290</td>\n",
       "      <td>55347</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Baldwin County</th>\n",
       "      <td>517</td>\n",
       "      <td>2187</td>\n",
       "      <td>2092</td>\n",
       "      <td>2160</td>\n",
       "      <td>2186</td>\n",
       "      <td>2240</td>\n",
       "      <td>183193</td>\n",
       "      <td>186659</td>\n",
       "      <td>190396</td>\n",
       "      <td>195126</td>\n",
       "      <td>199713</td>\n",
       "      <td>203709</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Barbour County</th>\n",
       "      <td>70</td>\n",
       "      <td>335</td>\n",
       "      <td>300</td>\n",
       "      <td>283</td>\n",
       "      <td>260</td>\n",
       "      <td>269</td>\n",
       "      <td>27341</td>\n",
       "      <td>27226</td>\n",
       "      <td>27159</td>\n",
       "      <td>26973</td>\n",
       "      <td>26815</td>\n",
       "      <td>26489</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Bibb County</th>\n",
       "      <td>44</td>\n",
       "      <td>266</td>\n",
       "      <td>245</td>\n",
       "      <td>259</td>\n",
       "      <td>247</td>\n",
       "      <td>253</td>\n",
       "      <td>22861</td>\n",
       "      <td>22733</td>\n",
       "      <td>22642</td>\n",
       "      <td>22512</td>\n",
       "      <td>22549</td>\n",
       "      <td>22583</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Blount County</th>\n",
       "      <td>183</td>\n",
       "      <td>744</td>\n",
       "      <td>710</td>\n",
       "      <td>646</td>\n",
       "      <td>618</td>\n",
       "      <td>603</td>\n",
       "      <td>57373</td>\n",
       "      <td>57711</td>\n",
       "      <td>57776</td>\n",
       "      <td>57734</td>\n",
       "      <td>57658</td>\n",
       "      <td>57673</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                        BIRTHS2010  BIRTHS2011  BIRTHS2012  BIRTHS2013  \\\n",
       "STNAME  CTYNAME                                                          \n",
       "Alabama Autauga County         151         636         615         574   \n",
       "        Baldwin County         517        2187        2092        2160   \n",
       "        Barbour County          70         335         300         283   \n",
       "        Bibb County             44         266         245         259   \n",
       "        Blount County          183         744         710         646   \n",
       "\n",
       "                        BIRTHS2014  BIRTHS2015  POPESTIMATE2010  \\\n",
       "STNAME  CTYNAME                                                   \n",
       "Alabama Autauga County         623         600            54660   \n",
       "        Baldwin County        2186        2240           183193   \n",
       "        Barbour County         260         269            27341   \n",
       "        Bibb County            247         253            22861   \n",
       "        Blount County          618         603            57373   \n",
       "\n",
       "                        POPESTIMATE2011  POPESTIMATE2012  POPESTIMATE2013  \\\n",
       "STNAME  CTYNAME                                                             \n",
       "Alabama Autauga County            55253            55175            55038   \n",
       "        Baldwin County           186659           190396           195126   \n",
       "        Barbour County            27226            27159            26973   \n",
       "        Bibb County               22733            22642            22512   \n",
       "        Blount County             57711            57776            57734   \n",
       "\n",
       "                        POPESTIMATE2014  POPESTIMATE2015  \n",
       "STNAME  CTYNAME                                           \n",
       "Alabama Autauga County            55290            55347  \n",
       "        Baldwin County           199713           203709  \n",
       "        Barbour County            26815            26489  \n",
       "        Bibb County               22549            22583  \n",
       "        Blount County             57658            57673  "
      ]
     },
     "execution_count": 125,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df = df.set_index(['STNAME', 'CTYNAME'])\n",
    "df.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 126,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "BIRTHS2010            977\n",
       "BIRTHS2011           3826\n",
       "BIRTHS2012           3780\n",
       "BIRTHS2013           3662\n",
       "BIRTHS2014           3683\n",
       "BIRTHS2015           3709\n",
       "POPESTIMATE2010    345563\n",
       "POPESTIMATE2011    349048\n",
       "POPESTIMATE2012    351213\n",
       "POPESTIMATE2013    354289\n",
       "POPESTIMATE2014    357029\n",
       "POPESTIMATE2015    358880\n",
       "Name: (Michigan, Washtenaw County), dtype: int64"
      ]
     },
     "execution_count": 126,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.loc['Michigan', 'Washtenaw County']\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 127,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th>BIRTHS2010</th>\n",
       "      <th>BIRTHS2011</th>\n",
       "      <th>BIRTHS2012</th>\n",
       "      <th>BIRTHS2013</th>\n",
       "      <th>BIRTHS2014</th>\n",
       "      <th>BIRTHS2015</th>\n",
       "      <th>POPESTIMATE2010</th>\n",
       "      <th>POPESTIMATE2011</th>\n",
       "      <th>POPESTIMATE2012</th>\n",
       "      <th>POPESTIMATE2013</th>\n",
       "      <th>POPESTIMATE2014</th>\n",
       "      <th>POPESTIMATE2015</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>STNAME</th>\n",
       "      <th>CTYNAME</th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th rowspan=\"2\" valign=\"top\">Michigan</th>\n",
       "      <th>Washtenaw County</th>\n",
       "      <td>977</td>\n",
       "      <td>3826</td>\n",
       "      <td>3780</td>\n",
       "      <td>3662</td>\n",
       "      <td>3683</td>\n",
       "      <td>3709</td>\n",
       "      <td>345563</td>\n",
       "      <td>349048</td>\n",
       "      <td>351213</td>\n",
       "      <td>354289</td>\n",
       "      <td>357029</td>\n",
       "      <td>358880</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Wayne County</th>\n",
       "      <td>5918</td>\n",
       "      <td>23819</td>\n",
       "      <td>23270</td>\n",
       "      <td>23377</td>\n",
       "      <td>23607</td>\n",
       "      <td>23586</td>\n",
       "      <td>1815199</td>\n",
       "      <td>1801273</td>\n",
       "      <td>1792514</td>\n",
       "      <td>1775713</td>\n",
       "      <td>1766008</td>\n",
       "      <td>1759335</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                           BIRTHS2010  BIRTHS2011  BIRTHS2012  BIRTHS2013  \\\n",
       "STNAME   CTYNAME                                                            \n",
       "Michigan Washtenaw County         977        3826        3780        3662   \n",
       "         Wayne County            5918       23819       23270       23377   \n",
       "\n",
       "                           BIRTHS2014  BIRTHS2015  POPESTIMATE2010  \\\n",
       "STNAME   CTYNAME                                                     \n",
       "Michigan Washtenaw County        3683        3709           345563   \n",
       "         Wayne County           23607       23586          1815199   \n",
       "\n",
       "                           POPESTIMATE2011  POPESTIMATE2012  POPESTIMATE2013  \\\n",
       "STNAME   CTYNAME                                                               \n",
       "Michigan Washtenaw County           349048           351213           354289   \n",
       "         Wayne County              1801273          1792514          1775713   \n",
       "\n",
       "                           POPESTIMATE2014  POPESTIMATE2015  \n",
       "STNAME   CTYNAME                                             \n",
       "Michigan Washtenaw County           357029           358880  \n",
       "         Wayne County              1766008          1759335  "
      ]
     },
     "execution_count": 127,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.loc[ [('Michigan', 'Washtenaw County'),\n",
    "         ('Michigan', 'Wayne County')] ]\n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "#### Missing values"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "df = pd.read_csv('data/log.csv')\n",
    "df\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "df.fillna?"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "df = df.set_index('time')\n",
    "df = df.sort_index()\n",
    "df"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "df = df.reset_index()\n",
    "df = df.set_index(['time', 'user'])\n",
    "df"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "df = df.fillna(method='ffill')\n",
    "df.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "sports = {99: 'Bhutan',\n",
    "          100: 'Scotland',\n",
    "          101: 'Japan',\n",
    "          102: 'South Korea'}\n",
    "s = pd.Series(sports)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "scrolled": true
   },
   "outputs": [],
   "source": [
    "s[0] #This won't call s.iloc[0] as one might expect, it generates an error instead"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "s = pd.Series([100.00, 120.00, 101.00, 3.00])\n",
    "s"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "total = 0\n",
    "for item in s:\n",
    "    total+=item\n",
    "print(total)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "import numpy as np\n",
    "\n",
    "total = np.sum(s)\n",
    "print(total)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "#this creates a big series of random numbers\n",
    "s = pd.Series(np.random.randint(0,1000,10000))\n",
    "s.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "len(s)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "%%timeit -n 100\n",
    "summary = 0\n",
    "for item in s:\n",
    "    summary+=item"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "%%timeit -n 100\n",
    "summary = np.sum(s)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "s+=2 #adds two to each item in s using broadcasting\n",
    "s.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "for label, value in s.iteritems():\n",
    "    s.set_value(label, value+2)\n",
    "s.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "%%timeit -n 10\n",
    "s = pd.Series(np.random.randint(0,1000,10000))\n",
    "for label, value in s.iteritems():\n",
    "    s.loc[label]= value+2"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "%%timeit -n 10\n",
    "s = pd.Series(np.random.randint(0,1000,10000))\n",
    "s+=2\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "s = pd.Series([1, 2, 3])\n",
    "s.loc['Animal'] = 'Bears'\n",
    "s"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "original_sports = pd.Series({'Archery': 'Bhutan',\n",
    "                             'Golf': 'Scotland',\n",
    "                             'Sumo': 'Japan',\n",
    "                             'Taekwondo': 'South Korea'})\n",
    "cricket_loving_countries = pd.Series(['Australia',\n",
    "                                      'Barbados',\n",
    "                                      'Pakistan',\n",
    "                                      'England'], \n",
    "                                   index=['Cricket',\n",
    "                                          'Cricket',\n",
    "                                          'Cricket',\n",
    "                                          'Cricket'])\n",
    "all_countries = original_sports.append(cricket_loving_countries)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "original_sports"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "cricket_loving_countries"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "all_countries"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "all_countries.loc['Cricket']"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "collapsed": true
   },
   "source": [
    "# The DataFrame Data Structure"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "import pandas as pd\n",
    "purchase_1 = pd.Series({'Name': 'Chris',\n",
    "                        'Item Purchased': 'Dog Food',\n",
    "                        'Cost': 22.50})\n",
    "purchase_2 = pd.Series({'Name': 'Kevyn',\n",
    "                        'Item Purchased': 'Kitty Litter',\n",
    "                        'Cost': 2.50})\n",
    "purchase_3 = pd.Series({'Name': 'Vinod',\n",
    "                        'Item Purchased': 'Bird Seed',\n",
    "                        'Cost': 5.00})\n",
    "df = pd.DataFrame([purchase_1, purchase_2, purchase_3], index=['Store 1', 'Store 1', 'Store 2'])\n",
    "df.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "df.loc['Store 2']"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "type(df.loc['Store 2'])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "df.loc['Store 1']"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "df.loc['Store 1', 'Cost']"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "df.T"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "df.T.loc['Cost']"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "df['Cost']"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "df.loc['Store 1']['Cost']"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "df.loc[:,['Name', 'Cost']]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "df.drop('Store 1')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "df"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "copy_df = df.copy()\n",
    "copy_df = copy_df.drop('Store 1')\n",
    "copy_df"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "copy_df.drop?"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "del copy_df['Name']\n",
    "copy_df"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "df['Location'] = None\n",
    "df"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "collapsed": true
   },
   "source": [
    "# Dataframe Indexing and Loading"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "costs = df['Cost']\n",
    "costs"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "costs+=2\n",
    "costs"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "df"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "!cat olympics.csv"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "df = pd.read_csv('olympics.csv')\n",
    "df.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "df = pd.read_csv('olympics.csv', index_col = 0, skiprows=1)\n",
    "df.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "df.columns"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "for col in df.columns:\n",
    "    if col[:2]=='01':\n",
    "        df.rename(columns={col:'Gold' + col[4:]}, inplace=True)\n",
    "    if col[:2]=='02':\n",
    "        df.rename(columns={col:'Silver' + col[4:]}, inplace=True)\n",
    "    if col[:2]=='03':\n",
    "        df.rename(columns={col:'Bronze' + col[4:]}, inplace=True)\n",
    "    if col[:1]=='№':\n",
    "        df.rename(columns={col:'#' + col[1:]}, inplace=True) \n",
    "\n",
    "df.head()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Querying a DataFrame"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "df['Gold'] > 0"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "only_gold = df.where(df['Gold'] > 0)\n",
    "only_gold.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "only_gold['Gold'].count()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "df['Gold'].count()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "only_gold = only_gold.dropna()\n",
    "only_gold.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "only_gold = df[df['Gold'] > 0]\n",
    "only_gold.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "len(df[(df['Gold'] > 0) | (df['Gold.1'] > 0)])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "df[(df['Gold.1'] > 0) & (df['Gold'] == 0)]"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Indexing Dataframes"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "df.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "df['country'] = df.index\n",
    "df = df.set_index('Gold')\n",
    "df.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "df = df.reset_index()\n",
    "df.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "df = pd.read_csv('census.csv')\n",
    "df.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "df['SUMLEV'].unique()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "df=df[df['SUMLEV'] == 50]\n",
    "df.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "columns_to_keep = ['STNAME',\n",
    "                   'CTYNAME',\n",
    "                   'BIRTHS2010',\n",
    "                   'BIRTHS2011',\n",
    "                   'BIRTHS2012',\n",
    "                   'BIRTHS2013',\n",
    "                   'BIRTHS2014',\n",
    "                   'BIRTHS2015',\n",
    "                   'POPESTIMATE2010',\n",
    "                   'POPESTIMATE2011',\n",
    "                   'POPESTIMATE2012',\n",
    "                   'POPESTIMATE2013',\n",
    "                   'POPESTIMATE2014',\n",
    "                   'POPESTIMATE2015']\n",
    "df = df[columns_to_keep]\n",
    "df.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "df = df.set_index(['STNAME', 'CTYNAME'])\n",
    "df.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "df.loc['Michigan', 'Washtenaw County']"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "df.loc[ [('Michigan', 'Washtenaw County'),\n",
    "         ('Michigan', 'Wayne County')] ]"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Missing values"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "df = pd.read_csv('log.csv')\n",
    "df"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "df.fillna?"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "df = df.set_index('time')\n",
    "df = df.sort_index()\n",
    "df"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "df = df.reset_index()\n",
    "df = df.set_index(['time', 'user'])\n",
    "df"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "df = df.fillna(method='ffill')\n",
    "df.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python [conda env:py3.6tf1.3keras]",
   "language": "python",
   "name": "conda-env-py3.6tf1.3keras-py"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.6.4"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 1
}