MNIST.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 660
    },
    "colab_type": "code",
    "id": "1iP8gkaOVG-Z",
    "outputId": "b72af7f6-659f-4fa0-c887-10100276039b"
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Requirement already satisfied: tensorflow in /usr/local/lib/python3.6/dist-packages (2.2.0)\n",
      "Requirement already satisfied: absl-py>=0.7.0 in /usr/local/lib/python3.6/dist-packages (from tensorflow) (0.9.0)\n",
      "Requirement already satisfied: opt-einsum>=2.3.2 in /usr/local/lib/python3.6/dist-packages (from tensorflow) (3.2.1)\n",
      "Requirement already satisfied: six>=1.12.0 in /usr/local/lib/python3.6/dist-packages (from tensorflow) (1.12.0)\n",
      "Requirement already satisfied: gast==0.3.3 in /usr/local/lib/python3.6/dist-packages (from tensorflow) (0.3.3)\n",
      "Requirement already satisfied: termcolor>=1.1.0 in /usr/local/lib/python3.6/dist-packages (from tensorflow) (1.1.0)\n",
      "Requirement already satisfied: wheel>=0.26; python_version >= \"3\" in /usr/local/lib/python3.6/dist-packages (from tensorflow) (0.34.2)\n",
      "Requirement already satisfied: grpcio>=1.8.6 in /usr/local/lib/python3.6/dist-packages (from tensorflow) (1.29.0)\n",
      "Requirement already satisfied: protobuf>=3.8.0 in /usr/local/lib/python3.6/dist-packages (from tensorflow) (3.10.0)\n",
      "Requirement already satisfied: scipy==1.4.1; python_version >= \"3\" in /usr/local/lib/python3.6/dist-packages (from tensorflow) (1.4.1)\n",
      "Requirement already satisfied: google-pasta>=0.1.8 in /usr/local/lib/python3.6/dist-packages (from tensorflow) (0.2.0)\n",
      "Requirement already satisfied: tensorboard<2.3.0,>=2.2.0 in /usr/local/lib/python3.6/dist-packages (from tensorflow) (2.2.2)\n",
      "Requirement already satisfied: keras-preprocessing>=1.1.0 in /usr/local/lib/python3.6/dist-packages (from tensorflow) (1.1.2)\n",
      "Requirement already satisfied: tensorflow-estimator<2.3.0,>=2.2.0 in /usr/local/lib/python3.6/dist-packages (from tensorflow) (2.2.0)\n",
      "Requirement already satisfied: wrapt>=1.11.1 in /usr/local/lib/python3.6/dist-packages (from tensorflow) (1.12.1)\n",
      "Requirement already satisfied: astunparse==1.6.3 in /usr/local/lib/python3.6/dist-packages (from tensorflow) (1.6.3)\n",
      "Requirement already satisfied: h5py<2.11.0,>=2.10.0 in /usr/local/lib/python3.6/dist-packages (from tensorflow) (2.10.0)\n",
      "Requirement already satisfied: numpy<2.0,>=1.16.0 in /usr/local/lib/python3.6/dist-packages (from tensorflow) (1.18.4)\n",
      "Requirement already satisfied: setuptools in /usr/local/lib/python3.6/dist-packages (from protobuf>=3.8.0->tensorflow) (47.1.1)\n",
      "Requirement already satisfied: werkzeug>=0.11.15 in /usr/local/lib/python3.6/dist-packages (from tensorboard<2.3.0,>=2.2.0->tensorflow) (1.0.1)\n",
      "Requirement already satisfied: google-auth<2,>=1.6.3 in /usr/local/lib/python3.6/dist-packages (from tensorboard<2.3.0,>=2.2.0->tensorflow) (1.7.2)\n",
      "Requirement already satisfied: tensorboard-plugin-wit>=1.6.0 in /usr/local/lib/python3.6/dist-packages (from tensorboard<2.3.0,>=2.2.0->tensorflow) (1.6.0.post3)\n",
      "Requirement already satisfied: markdown>=2.6.8 in /usr/local/lib/python3.6/dist-packages (from tensorboard<2.3.0,>=2.2.0->tensorflow) (3.2.2)\n",
      "Requirement already satisfied: requests<3,>=2.21.0 in /usr/local/lib/python3.6/dist-packages (from tensorboard<2.3.0,>=2.2.0->tensorflow) (2.23.0)\n",
      "Requirement already satisfied: google-auth-oauthlib<0.5,>=0.4.1 in /usr/local/lib/python3.6/dist-packages (from tensorboard<2.3.0,>=2.2.0->tensorflow) (0.4.1)\n",
      "Requirement already satisfied: rsa<4.1,>=3.1.4 in /usr/local/lib/python3.6/dist-packages (from google-auth<2,>=1.6.3->tensorboard<2.3.0,>=2.2.0->tensorflow) (4.0)\n",
      "Requirement already satisfied: cachetools<3.2,>=2.0.0 in /usr/local/lib/python3.6/dist-packages (from google-auth<2,>=1.6.3->tensorboard<2.3.0,>=2.2.0->tensorflow) (3.1.1)\n",
      "Requirement already satisfied: pyasn1-modules>=0.2.1 in /usr/local/lib/python3.6/dist-packages (from google-auth<2,>=1.6.3->tensorboard<2.3.0,>=2.2.0->tensorflow) (0.2.8)\n",
      "Requirement already satisfied: importlib-metadata; python_version < \"3.8\" in /usr/local/lib/python3.6/dist-packages (from markdown>=2.6.8->tensorboard<2.3.0,>=2.2.0->tensorflow) (1.6.0)\n",
      "Requirement already satisfied: urllib3!=1.25.0,!=1.25.1,<1.26,>=1.21.1 in /usr/local/lib/python3.6/dist-packages (from requests<3,>=2.21.0->tensorboard<2.3.0,>=2.2.0->tensorflow) (1.24.3)\n",
      "Requirement already satisfied: chardet<4,>=3.0.2 in /usr/local/lib/python3.6/dist-packages (from requests<3,>=2.21.0->tensorboard<2.3.0,>=2.2.0->tensorflow) (3.0.4)\n",
      "Requirement already satisfied: certifi>=2017.4.17 in /usr/local/lib/python3.6/dist-packages (from requests<3,>=2.21.0->tensorboard<2.3.0,>=2.2.0->tensorflow) (2020.4.5.1)\n",
      "Requirement already satisfied: idna<3,>=2.5 in /usr/local/lib/python3.6/dist-packages (from requests<3,>=2.21.0->tensorboard<2.3.0,>=2.2.0->tensorflow) (2.9)\n",
      "Requirement already satisfied: requests-oauthlib>=0.7.0 in /usr/local/lib/python3.6/dist-packages (from google-auth-oauthlib<0.5,>=0.4.1->tensorboard<2.3.0,>=2.2.0->tensorflow) (1.3.0)\n",
      "Requirement already satisfied: pyasn1>=0.1.3 in /usr/local/lib/python3.6/dist-packages (from rsa<4.1,>=3.1.4->google-auth<2,>=1.6.3->tensorboard<2.3.0,>=2.2.0->tensorflow) (0.4.8)\n",
      "Requirement already satisfied: zipp>=0.5 in /usr/local/lib/python3.6/dist-packages (from importlib-metadata; python_version < \"3.8\"->markdown>=2.6.8->tensorboard<2.3.0,>=2.2.0->tensorflow) (3.1.0)\n",
      "Requirement already satisfied: oauthlib>=3.0.0 in /usr/local/lib/python3.6/dist-packages (from requests-oauthlib>=0.7.0->google-auth-oauthlib<0.5,>=0.4.1->tensorboard<2.3.0,>=2.2.0->tensorflow) (3.1.0)\n"
     ]
    }
   ],
   "source": [
    "!pip install tensorflow #! used because pip is a command line tool, not a code command"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 34
    },
    "colab_type": "code",
    "id": "Kv9l2qjlVJFO",
    "outputId": "517362a4-0684-4725-924f-058ee3d85fb1"
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "2.2.0\n"
     ]
    }
   ],
   "source": [
    "import tensorflow as tf\n",
    "print(tf.__version__)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 0,
   "metadata": {
    "colab": {},
    "colab_type": "code",
    "id": "2XYYP6_KVdSX"
   },
   "outputs": [],
   "source": [
    "import pandas as pd\n",
    "import matplotlib.pyplot as plt\n",
    "import numpy as np\n",
    "from sklearn.model_selection import train_test_split\n",
    "from sklearn.metrics import confusion_matrix\n",
    "import itertools\n",
    "from keras.utils import to_categorical\n",
    "from keras.models import Sequential\n",
    "from keras.layers import Dense, Flatten, Conv2D, MaxPool2D\n",
    "from keras.preprocessing.image import ImageDataGenerator\n",
    "from keras.optimizers import SGD\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 0,
   "metadata": {
    "colab": {},
    "colab_type": "code",
    "id": "0V95e0Dh7hMZ"
   },
   "outputs": [],
   "source": [
    "%matplotlib inline"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 415,
     "resources": {
      "http://localhost:8080/nbextensions/google.colab/files.js": {
       "data": "Ly8gQ29weXJpZ2h0IDIwMTcgR29vZ2xlIExMQwovLwovLyBMaWNlbnNlZCB1bmRlciB0aGUgQXBhY2hlIExpY2Vuc2UsIFZlcnNpb24gMi4wICh0aGUgIkxpY2Vuc2UiKTsKLy8geW91IG1heSBub3QgdXNlIHRoaXMgZmlsZSBleGNlcHQgaW4gY29tcGxpYW5jZSB3aXRoIHRoZSBMaWNlbnNlLgovLyBZb3UgbWF5IG9idGFpbiBhIGNvcHkgb2YgdGhlIExpY2Vuc2UgYXQKLy8KLy8gICAgICBodHRwOi8vd3d3LmFwYWNoZS5vcmcvbGljZW5zZXMvTElDRU5TRS0yLjAKLy8KLy8gVW5sZXNzIHJlcXVpcmVkIGJ5IGFwcGxpY2FibGUgbGF3IG9yIGFncmVlZCB0byBpbiB3cml0aW5nLCBzb2Z0d2FyZQovLyBkaXN0cmlidXRlZCB1bmRlciB0aGUgTGljZW5zZSBpcyBkaXN0cmlidXRlZCBvbiBhbiAiQVMgSVMiIEJBU0lTLAovLyBXSVRIT1VUIFdBUlJBTlRJRVMgT1IgQ09ORElUSU9OUyBPRiBBTlkgS0lORCwgZWl0aGVyIGV4cHJlc3Mgb3IgaW1wbGllZC4KLy8gU2VlIHRoZSBMaWNlbnNlIGZvciB0aGUgc3BlY2lmaWMgbGFuZ3VhZ2UgZ292ZXJuaW5nIHBlcm1pc3Npb25zIGFuZAovLyBsaW1pdGF0aW9ucyB1bmRlciB0aGUgTGljZW5zZS4KCi8qKgogKiBAZmlsZW92ZXJ2aWV3IEhlbHBlcnMgZm9yIGdvb2dsZS5jb2xhYiBQeXRob24gbW9kdWxlLgogKi8KKGZ1bmN0aW9uKHNjb3BlKSB7CmZ1bmN0aW9uIHNwYW4odGV4dCwgc3R5bGVBdHRyaWJ1dGVzID0ge30pIHsKICBjb25zdCBlbGVtZW50ID0gZG9jdW1lbnQuY3JlYXRlRWxlbWVudCgnc3BhbicpOwogIGVsZW1lbnQudGV4dENvbnRlbnQgPSB0ZXh0OwogIGZvciAoY29uc3Qga2V5IG9mIE9iamVjdC5rZXlzKHN0eWxlQXR0cmlidXRlcykpIHsKICAgIGVsZW1lbnQuc3R5bGVba2V5XSA9IHN0eWxlQXR0cmlidXRlc1trZXldOwogIH0KICByZXR1cm4gZWxlbWVudDsKfQoKLy8gTWF4IG51bWJlciBvZiBieXRlcyB3aGljaCB3aWxsIGJlIHVwbG9hZGVkIGF0IGEgdGltZS4KY29uc3QgTUFYX1BBWUxPQURfU0laRSA9IDEwMCAqIDEwMjQ7Ci8vIE1heCBhbW91bnQgb2YgdGltZSB0byBibG9jayB3YWl0aW5nIGZvciB0aGUgdXNlci4KY29uc3QgRklMRV9DSEFOR0VfVElNRU9VVF9NUyA9IDMwICogMTAwMDsKCmZ1bmN0aW9uIF91cGxvYWRGaWxlcyhpbnB1dElkLCBvdXRwdXRJZCkgewogIGNvbnN0IHN0ZXBzID0gdXBsb2FkRmlsZXNTdGVwKGlucHV0SWQsIG91dHB1dElkKTsKICBjb25zdCBvdXRwdXRFbGVtZW50ID0gZG9jdW1lbnQuZ2V0RWxlbWVudEJ5SWQob3V0cHV0SWQpOwogIC8vIENhY2hlIHN0ZXBzIG9uIHRoZSBvdXRwdXRFbGVtZW50IHRvIG1ha2UgaXQgYXZhaWxhYmxlIGZvciB0aGUgbmV4dCBjYWxsCiAgLy8gdG8gdXBsb2FkRmlsZXNDb250aW51ZSBmcm9tIFB5dGhvbi4KICBvdXRwdXRFbGVtZW50LnN0ZXBzID0gc3RlcHM7CgogIHJldHVybiBfdXBsb2FkRmlsZXNDb250aW51ZShvdXRwdXRJZCk7Cn0KCi8vIFRoaXMgaXMgcm91Z2hseSBhbiBhc3luYyBnZW5lcmF0b3IgKG5vdCBzdXBwb3J0ZWQgaW4gdGhlIGJyb3dzZXIgeWV0KSwKLy8gd2hlcmUgdGhlcmUgYXJlIG11bHRpcGxlIGFzeW5jaHJvbm91cyBzdGVwcyBhbmQgdGhlIFB5dGhvbiBzaWRlIGlzIGdvaW5nCi8vIHRvIHBvbGwgZm9yIGNvbXBsZXRpb24gb2YgZWFjaCBzdGVwLgovLyBUaGlzIHVzZXMgYSBQcm9taXNlIHRvIGJsb2NrIHRoZSBweXRob24gc2lkZSBvbiBjb21wbGV0aW9uIG9mIGVhY2ggc3RlcCwKLy8gdGhlbiBwYXNzZXMgdGhlIHJlc3VsdCBvZiB0aGUgcHJldmlvdXMgc3RlcCBhcyB0aGUgaW5wdXQgdG8gdGhlIG5leHQgc3RlcC4KZnVuY3Rpb24gX3VwbG9hZEZpbGVzQ29udGludWUob3V0cHV0SWQpIHsKICBjb25zdCBvdXRwdXRFbGVtZW50ID0gZG9jdW1lbnQuZ2V0RWxlbWVudEJ5SWQob3V0cHV0SWQpOwogIGNvbnN0IHN0ZXBzID0gb3V0cHV0RWxlbWVudC5zdGVwczsKCiAgY29uc3QgbmV4dCA9IHN0ZXBzLm5leHQob3V0cHV0RWxlbWVudC5sYXN0UHJvbWlzZVZhbHVlKTsKICByZXR1cm4gUHJvbWlzZS5yZXNvbHZlKG5leHQudmFsdWUucHJvbWlzZSkudGhlbigodmFsdWUpID0+IHsKICAgIC8vIENhY2hlIHRoZSBsYXN0IHByb21pc2UgdmFsdWUgdG8gbWFrZSBpdCBhdmFpbGFibGUgdG8gdGhlIG5leHQKICAgIC8vIHN0ZXAgb2YgdGhlIGdlbmVyYXRvci4KICAgIG91dHB1dEVsZW1lbnQubGFzdFByb21pc2VWYWx1ZSA9IHZhbHVlOwogICAgcmV0dXJuIG5leHQudmFsdWUucmVzcG9uc2U7CiAgfSk7Cn0KCi8qKgogKiBHZW5lcmF0b3IgZnVuY3Rpb24gd2hpY2ggaXMgY2FsbGVkIGJldHdlZW4gZWFjaCBhc3luYyBzdGVwIG9mIHRoZSB1cGxvYWQKICogcHJvY2Vzcy4KICogQHBhcmFtIHtzdHJpbmd9IGlucHV0SWQgRWxlbWVudCBJRCBvZiB0aGUgaW5wdXQgZmlsZSBwaWNrZXIgZWxlbWVudC4KICogQHBhcmFtIHtzdHJpbmd9IG91dHB1dElkIEVsZW1lbnQgSUQgb2YgdGhlIG91dHB1dCBkaXNwbGF5LgogKiBAcmV0dXJuIHshSXRlcmFibGU8IU9iamVjdD59IEl0ZXJhYmxlIG9mIG5leHQgc3RlcHMuCiAqLwpmdW5jdGlvbiogdXBsb2FkRmlsZXNTdGVwKGlucHV0SWQsIG91dHB1dElkKSB7CiAgY29uc3QgaW5wdXRFbGVtZW50ID0gZG9jdW1lbnQuZ2V0RWxlbWVudEJ5SWQoaW5wdXRJZCk7CiAgaW5wdXRFbGVtZW50LmRpc2FibGVkID0gZmFsc2U7CgogIGNvbnN0IG91dHB1dEVsZW1lbnQgPSBkb2N1bWVudC5nZXRFbGVtZW50QnlJZChvdXRwdXRJZCk7CiAgb3V0cHV0RWxlbWVudC5pbm5lckhUTUwgPSAnJzsKCiAgY29uc3QgcGlja2VkUHJvbWlzZSA9IG5ldyBQcm9taXNlKChyZXNvbHZlKSA9PiB7CiAgICBpbnB1dEVsZW1lbnQuYWRkRXZlbnRMaXN0ZW5lcignY2hhbmdlJywgKGUpID0+IHsKICAgICAgcmVzb2x2ZShlLnRhcmdldC5maWxlcyk7CiAgICB9KTsKICB9KTsKCiAgY29uc3QgY2FuY2VsID0gZG9jdW1lbnQuY3JlYXRlRWxlbWVudCgnYnV0dG9uJyk7CiAgaW5wdXRFbGVtZW50LnBhcmVudEVsZW1lbnQuYXBwZW5kQ2hpbGQoY2FuY2VsKTsKICBjYW5jZWwudGV4dENvbnRlbnQgPSAnQ2FuY2VsIHVwbG9hZCc7CiAgY29uc3QgY2FuY2VsUHJvbWlzZSA9IG5ldyBQcm9taXNlKChyZXNvbHZlKSA9PiB7CiAgICBjYW5jZWwub25jbGljayA9ICgpID0+IHsKICAgICAgcmVzb2x2ZShudWxsKTsKICAgIH07CiAgfSk7CgogIC8vIENhbmNlbCB1cGxvYWQgaWYgdXNlciBoYXNuJ3QgcGlja2VkIGFueXRoaW5nIGluIHRpbWVvdXQuCiAgY29uc3QgdGltZW91dFByb21pc2UgPSBuZXcgUHJvbWlzZSgocmVzb2x2ZSkgPT4gewogICAgc2V0VGltZW91dCgoKSA9PiB7CiAgICAgIHJlc29sdmUobnVsbCk7CiAgICB9LCBGSUxFX0NIQU5HRV9USU1FT1VUX01TKTsKICB9KTsKCiAgLy8gV2FpdCBmb3IgdGhlIHVzZXIgdG8gcGljayB0aGUgZmlsZXMuCiAgY29uc3QgZmlsZXMgPSB5aWVsZCB7CiAgICBwcm9taXNlOiBQcm9taXNlLnJhY2UoW3BpY2tlZFByb21pc2UsIHRpbWVvdXRQcm9taXNlLCBjYW5jZWxQcm9taXNlXSksCiAgICByZXNwb25zZTogewogICAgICBhY3Rpb246ICdzdGFydGluZycsCiAgICB9CiAgfTsKCiAgaWYgKCFmaWxlcykgewogICAgcmV0dXJuIHsKICAgICAgcmVzcG9uc2U6IHsKICAgICAgICBhY3Rpb246ICdjb21wbGV0ZScsCiAgICAgIH0KICAgIH07CiAgfQoKICBjYW5jZWwucmVtb3ZlKCk7CgogIC8vIERpc2FibGUgdGhlIGlucHV0IGVsZW1lbnQgc2luY2UgZnVydGhlciBwaWNrcyBhcmUgbm90IGFsbG93ZWQuCiAgaW5wdXRFbGVtZW50LmRpc2FibGVkID0gdHJ1ZTsKCiAgZm9yIChjb25zdCBmaWxlIG9mIGZpbGVzKSB7CiAgICBjb25zdCBsaSA9IGRvY3VtZW50LmNyZWF0ZUVsZW1lbnQoJ2xpJyk7CiAgICBsaS5hcHBlbmQoc3BhbihmaWxlLm5hbWUsIHtmb250V2VpZ2h0OiAnYm9sZCd9KSk7CiAgICBsaS5hcHBlbmQoc3BhbigKICAgICAgICBgKCR7ZmlsZS50eXBlIHx8ICduL2EnfSkgLSAke2ZpbGUuc2l6ZX0gYnl0ZXMsIGAgKwogICAgICAgIGBsYXN0IG1vZGlmaWVkOiAkewogICAgICAgICAgICBmaWxlLmxhc3RNb2RpZmllZERhdGUgPyBmaWxlLmxhc3RNb2RpZmllZERhdGUudG9Mb2NhbGVEYXRlU3RyaW5nKCkgOgogICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAgICAnbi9hJ30gLSBgKSk7CiAgICBjb25zdCBwZXJjZW50ID0gc3BhbignMCUgZG9uZScpOwogICAgbGkuYXBwZW5kQ2hpbGQocGVyY2VudCk7CgogICAgb3V0cHV0RWxlbWVudC5hcHBlbmRDaGlsZChsaSk7CgogICAgY29uc3QgZmlsZURhdGFQcm9taXNlID0gbmV3IFByb21pc2UoKHJlc29sdmUpID0+IHsKICAgICAgY29uc3QgcmVhZGVyID0gbmV3IEZpbGVSZWFkZXIoKTsKICAgICAgcmVhZGVyLm9ubG9hZCA9IChlKSA9PiB7CiAgICAgICAgcmVzb2x2ZShlLnRhcmdldC5yZXN1bHQpOwogICAgICB9OwogICAgICByZWFkZXIucmVhZEFzQXJyYXlCdWZmZXIoZmlsZSk7CiAgICB9KTsKICAgIC8vIFdhaXQgZm9yIHRoZSBkYXRhIHRvIGJlIHJlYWR5LgogICAgbGV0IGZpbGVEYXRhID0geWllbGQgewogICAgICBwcm9taXNlOiBmaWxlRGF0YVByb21pc2UsCiAgICAgIHJlc3BvbnNlOiB7CiAgICAgICAgYWN0aW9uOiAnY29udGludWUnLAogICAgICB9CiAgICB9OwoKICAgIC8vIFVzZSBhIGNodW5rZWQgc2VuZGluZyB0byBhdm9pZCBtZXNzYWdlIHNpemUgbGltaXRzLiBTZWUgYi82MjExNTY2MC4KICAgIGxldCBwb3NpdGlvbiA9IDA7CiAgICB3aGlsZSAocG9zaXRpb24gPCBmaWxlRGF0YS5ieXRlTGVuZ3RoKSB7CiAgICAgIGNvbnN0IGxlbmd0aCA9IE1hdGgubWluKGZpbGVEYXRhLmJ5dGVMZW5ndGggLSBwb3NpdGlvbiwgTUFYX1BBWUxPQURfU0laRSk7CiAgICAgIGNvbnN0IGNodW5rID0gbmV3IFVpbnQ4QXJyYXkoZmlsZURhdGEsIHBvc2l0aW9uLCBsZW5ndGgpOwogICAgICBwb3NpdGlvbiArPSBsZW5ndGg7CgogICAgICBjb25zdCBiYXNlNjQgPSBidG9hKFN0cmluZy5mcm9tQ2hhckNvZGUuYXBwbHkobnVsbCwgY2h1bmspKTsKICAgICAgeWllbGQgewogICAgICAgIHJlc3BvbnNlOiB7CiAgICAgICAgICBhY3Rpb246ICdhcHBlbmQnLAogICAgICAgICAgZmlsZTogZmlsZS5uYW1lLAogICAgICAgICAgZGF0YTogYmFzZTY0LAogICAgICAgIH0sCiAgICAgIH07CiAgICAgIHBlcmNlbnQudGV4dENvbnRlbnQgPQogICAgICAgICAgYCR7TWF0aC5yb3VuZCgocG9zaXRpb24gLyBmaWxlRGF0YS5ieXRlTGVuZ3RoKSAqIDEwMCl9JSBkb25lYDsKICAgIH0KICB9CgogIC8vIEFsbCBkb25lLgogIHlpZWxkIHsKICAgIHJlc3BvbnNlOiB7CiAgICAgIGFjdGlvbjogJ2NvbXBsZXRlJywKICAgIH0KICB9Owp9CgpzY29wZS5nb29nbGUgPSBzY29wZS5nb29nbGUgfHwge307CnNjb3BlLmdvb2dsZS5jb2xhYiA9IHNjb3BlLmdvb2dsZS5jb2xhYiB8fCB7fTsKc2NvcGUuZ29vZ2xlLmNvbGFiLl9maWxlcyA9IHsKICBfdXBsb2FkRmlsZXMsCiAgX3VwbG9hZEZpbGVzQ29udGludWUsCn07Cn0pKHNlbGYpOwo=",
       "headers": [
        [
         "content-type",
         "application/javascript"
        ]
       ],
       "ok": true,
       "status": 200,
       "status_text": "OK"
      }
     }
    },
    "colab_type": "code",
    "id": "140Bpokw8OYe",
    "outputId": "ddbffa2f-5eaa-4b45-ad53-6614a1b9ea14"
   },
   "outputs": [
    {
     "data": {
      "text/html": [
       "\n",
       "     <input type=\"file\" id=\"files-2db6e4c2-89ae-46d7-99a9-ef3da7ff9046\" name=\"files[]\" multiple disabled />\n",
       "     <output id=\"result-2db6e4c2-89ae-46d7-99a9-ef3da7ff9046\">\n",
       "      Upload widget is only available when the cell has been executed in the\n",
       "      current browser session. Please rerun this cell to enable.\n",
       "      </output>\n",
       "      <script src=\"/nbextensions/google.colab/files.js\"></script> "
      ],
      "text/plain": [
       "<IPython.core.display.HTML object>"
      ]
     },
     "metadata": {
      "tags": []
     },
     "output_type": "display_data"
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Saving test.csv to test (2).csv\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>label</th>\n",
       "      <th>pixel0</th>\n",
       "      <th>pixel1</th>\n",
       "      <th>pixel2</th>\n",
       "      <th>pixel3</th>\n",
       "      <th>pixel4</th>\n",
       "      <th>pixel5</th>\n",
       "      <th>pixel6</th>\n",
       "      <th>pixel7</th>\n",
       "      <th>pixel8</th>\n",
       "      <th>pixel9</th>\n",
       "      <th>pixel10</th>\n",
       "      <th>pixel11</th>\n",
       "      <th>pixel12</th>\n",
       "      <th>pixel13</th>\n",
       "      <th>pixel14</th>\n",
       "      <th>pixel15</th>\n",
       "      <th>pixel16</th>\n",
       "      <th>pixel17</th>\n",
       "      <th>pixel18</th>\n",
       "      <th>pixel19</th>\n",
       "      <th>pixel20</th>\n",
       "      <th>pixel21</th>\n",
       "      <th>pixel22</th>\n",
       "      <th>pixel23</th>\n",
       "      <th>pixel24</th>\n",
       "      <th>pixel25</th>\n",
       "      <th>pixel26</th>\n",
       "      <th>pixel27</th>\n",
       "      <th>pixel28</th>\n",
       "      <th>pixel29</th>\n",
       "      <th>pixel30</th>\n",
       "      <th>pixel31</th>\n",
       "      <th>pixel32</th>\n",
       "      <th>pixel33</th>\n",
       "      <th>pixel34</th>\n",
       "      <th>pixel35</th>\n",
       "      <th>pixel36</th>\n",
       "      <th>pixel37</th>\n",
       "      <th>pixel38</th>\n",
       "      <th>...</th>\n",
       "      <th>pixel744</th>\n",
       "      <th>pixel745</th>\n",
       "      <th>pixel746</th>\n",
       "      <th>pixel747</th>\n",
       "      <th>pixel748</th>\n",
       "      <th>pixel749</th>\n",
       "      <th>pixel750</th>\n",
       "      <th>pixel751</th>\n",
       "      <th>pixel752</th>\n",
       "      <th>pixel753</th>\n",
       "      <th>pixel754</th>\n",
       "      <th>pixel755</th>\n",
       "      <th>pixel756</th>\n",
       "      <th>pixel757</th>\n",
       "      <th>pixel758</th>\n",
       "      <th>pixel759</th>\n",
       "      <th>pixel760</th>\n",
       "      <th>pixel761</th>\n",
       "      <th>pixel762</th>\n",
       "      <th>pixel763</th>\n",
       "      <th>pixel764</th>\n",
       "      <th>pixel765</th>\n",
       "      <th>pixel766</th>\n",
       "      <th>pixel767</th>\n",
       "      <th>pixel768</th>\n",
       "      <th>pixel769</th>\n",
       "      <th>pixel770</th>\n",
       "      <th>pixel771</th>\n",
       "      <th>pixel772</th>\n",
       "      <th>pixel773</th>\n",
       "      <th>pixel774</th>\n",
       "      <th>pixel775</th>\n",
       "      <th>pixel776</th>\n",
       "      <th>pixel777</th>\n",
       "      <th>pixel778</th>\n",
       "      <th>pixel779</th>\n",
       "      <th>pixel780</th>\n",
       "      <th>pixel781</th>\n",
       "      <th>pixel782</th>\n",
       "      <th>pixel783</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>count</th>\n",
       "      <td>42000.000000</td>\n",
       "      <td>42000.0</td>\n",
       "      <td>42000.0</td>\n",
       "      <td>42000.0</td>\n",
       "      <td>42000.0</td>\n",
       "      <td>42000.0</td>\n",
       "      <td>42000.0</td>\n",
       "      <td>42000.0</td>\n",
       "      <td>42000.0</td>\n",
       "      <td>42000.0</td>\n",
       "      <td>42000.0</td>\n",
       "      <td>42000.0</td>\n",
       "      <td>42000.0</td>\n",
       "      <td>42000.00000</td>\n",
       "      <td>42000.000000</td>\n",
       "      <td>42000.000000</td>\n",
       "      <td>42000.000000</td>\n",
       "      <td>42000.0</td>\n",
       "      <td>42000.0</td>\n",
       "      <td>42000.0</td>\n",
       "      <td>42000.0</td>\n",
       "      <td>42000.0</td>\n",
       "      <td>42000.0</td>\n",
       "      <td>42000.0</td>\n",
       "      <td>42000.0</td>\n",
       "      <td>42000.0</td>\n",
       "      <td>42000.0</td>\n",
       "      <td>42000.0</td>\n",
       "      <td>42000.0</td>\n",
       "      <td>42000.0</td>\n",
       "      <td>42000.0</td>\n",
       "      <td>42000.0</td>\n",
       "      <td>42000.0</td>\n",
       "      <td>42000.000000</td>\n",
       "      <td>42000.000000</td>\n",
       "      <td>42000.000000</td>\n",
       "      <td>42000.000000</td>\n",
       "      <td>42000.000000</td>\n",
       "      <td>42000.000000</td>\n",
       "      <td>42000.000000</td>\n",
       "      <td>...</td>\n",
       "      <td>42000.000000</td>\n",
       "      <td>42000.000000</td>\n",
       "      <td>42000.000000</td>\n",
       "      <td>42000.000000</td>\n",
       "      <td>42000.000000</td>\n",
       "      <td>42000.000000</td>\n",
       "      <td>42000.000000</td>\n",
       "      <td>42000.000000</td>\n",
       "      <td>42000.000000</td>\n",
       "      <td>42000.000000</td>\n",
       "      <td>42000.0</td>\n",
       "      <td>42000.0</td>\n",
       "      <td>42000.0</td>\n",
       "      <td>42000.0</td>\n",
       "      <td>42000.0</td>\n",
       "      <td>42000.0</td>\n",
       "      <td>42000.0</td>\n",
       "      <td>42000.000000</td>\n",
       "      <td>42000.000000</td>\n",
       "      <td>42000.000000</td>\n",
       "      <td>42000.000000</td>\n",
       "      <td>42000.000000</td>\n",
       "      <td>42000.000000</td>\n",
       "      <td>42000.000000</td>\n",
       "      <td>42000.000000</td>\n",
       "      <td>42000.000000</td>\n",
       "      <td>42000.000000</td>\n",
       "      <td>42000.00000</td>\n",
       "      <td>42000.000000</td>\n",
       "      <td>42000.000000</td>\n",
       "      <td>42000.000000</td>\n",
       "      <td>42000.000000</td>\n",
       "      <td>42000.000000</td>\n",
       "      <td>42000.00000</td>\n",
       "      <td>42000.000000</td>\n",
       "      <td>42000.000000</td>\n",
       "      <td>42000.0</td>\n",
       "      <td>42000.0</td>\n",
       "      <td>42000.0</td>\n",
       "      <td>42000.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>mean</th>\n",
       "      <td>4.456643</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>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>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.00300</td>\n",
       "      <td>0.011190</td>\n",
       "      <td>0.005143</td>\n",
       "      <td>0.000214</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>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>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>0.0</td>\n",
       "      <td>0.000381</td>\n",
       "      <td>0.001310</td>\n",
       "      <td>0.010548</td>\n",
       "      <td>0.027262</td>\n",
       "      <td>0.050905</td>\n",
       "      <td>0.066405</td>\n",
       "      <td>0.129571</td>\n",
       "      <td>...</td>\n",
       "      <td>3.772524</td>\n",
       "      <td>2.748905</td>\n",
       "      <td>1.796452</td>\n",
       "      <td>1.089905</td>\n",
       "      <td>0.563190</td>\n",
       "      <td>0.239571</td>\n",
       "      <td>0.093524</td>\n",
       "      <td>0.024833</td>\n",
       "      <td>0.000857</td>\n",
       "      <td>0.001405</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>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.006143</td>\n",
       "      <td>0.035833</td>\n",
       "      <td>0.082357</td>\n",
       "      <td>0.114905</td>\n",
       "      <td>0.178714</td>\n",
       "      <td>0.301452</td>\n",
       "      <td>0.413643</td>\n",
       "      <td>0.513667</td>\n",
       "      <td>0.558833</td>\n",
       "      <td>0.677857</td>\n",
       "      <td>0.60281</td>\n",
       "      <td>0.489238</td>\n",
       "      <td>0.340214</td>\n",
       "      <td>0.219286</td>\n",
       "      <td>0.117095</td>\n",
       "      <td>0.059024</td>\n",
       "      <td>0.02019</td>\n",
       "      <td>0.017238</td>\n",
       "      <td>0.002857</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>std</th>\n",
       "      <td>2.887730</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>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>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.56812</td>\n",
       "      <td>1.626927</td>\n",
       "      <td>1.053972</td>\n",
       "      <td>0.043916</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>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>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>0.0</td>\n",
       "      <td>0.078072</td>\n",
       "      <td>0.232634</td>\n",
       "      <td>1.131661</td>\n",
       "      <td>2.310396</td>\n",
       "      <td>3.121847</td>\n",
       "      <td>3.259128</td>\n",
       "      <td>4.992894</td>\n",
       "      <td>...</td>\n",
       "      <td>26.957829</td>\n",
       "      <td>22.879248</td>\n",
       "      <td>18.595109</td>\n",
       "      <td>14.434439</td>\n",
       "      <td>10.517823</td>\n",
       "      <td>6.469315</td>\n",
       "      <td>3.976306</td>\n",
       "      <td>1.846016</td>\n",
       "      <td>0.139556</td>\n",
       "      <td>0.287891</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>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.949803</td>\n",
       "      <td>2.350859</td>\n",
       "      <td>3.934280</td>\n",
       "      <td>4.543583</td>\n",
       "      <td>5.856772</td>\n",
       "      <td>7.219742</td>\n",
       "      <td>8.928286</td>\n",
       "      <td>10.004069</td>\n",
       "      <td>10.129595</td>\n",
       "      <td>11.254931</td>\n",
       "      <td>10.69603</td>\n",
       "      <td>9.480066</td>\n",
       "      <td>7.950251</td>\n",
       "      <td>6.312890</td>\n",
       "      <td>4.633819</td>\n",
       "      <td>3.274488</td>\n",
       "      <td>1.75987</td>\n",
       "      <td>1.894498</td>\n",
       "      <td>0.414264</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>min</th>\n",
       "      <td>0.000000</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>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>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.00000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</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>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>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>0.0</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>...</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</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>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.00000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.00000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>25%</th>\n",
       "      <td>2.000000</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>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>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.00000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</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>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>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>0.0</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>...</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</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>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.00000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.00000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>50%</th>\n",
       "      <td>4.000000</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>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>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.00000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</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>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>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>0.0</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>...</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</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>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.00000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.00000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>75%</th>\n",
       "      <td>7.000000</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>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>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.00000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</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>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>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>0.0</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>...</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</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>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.00000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.00000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>max</th>\n",
       "      <td>9.000000</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>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>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>116.00000</td>\n",
       "      <td>254.000000</td>\n",
       "      <td>216.000000</td>\n",
       "      <td>9.000000</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>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>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>0.0</td>\n",
       "      <td>16.000000</td>\n",
       "      <td>47.000000</td>\n",
       "      <td>157.000000</td>\n",
       "      <td>254.000000</td>\n",
       "      <td>255.000000</td>\n",
       "      <td>243.000000</td>\n",
       "      <td>255.000000</td>\n",
       "      <td>...</td>\n",
       "      <td>255.000000</td>\n",
       "      <td>255.000000</td>\n",
       "      <td>255.000000</td>\n",
       "      <td>255.000000</td>\n",
       "      <td>255.000000</td>\n",
       "      <td>255.000000</td>\n",
       "      <td>255.000000</td>\n",
       "      <td>253.000000</td>\n",
       "      <td>28.000000</td>\n",
       "      <td>59.000000</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>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>177.000000</td>\n",
       "      <td>231.000000</td>\n",
       "      <td>253.000000</td>\n",
       "      <td>254.000000</td>\n",
       "      <td>254.000000</td>\n",
       "      <td>255.000000</td>\n",
       "      <td>255.000000</td>\n",
       "      <td>255.000000</td>\n",
       "      <td>255.000000</td>\n",
       "      <td>255.000000</td>\n",
       "      <td>255.00000</td>\n",
       "      <td>255.000000</td>\n",
       "      <td>255.000000</td>\n",
       "      <td>254.000000</td>\n",
       "      <td>254.000000</td>\n",
       "      <td>253.000000</td>\n",
       "      <td>253.00000</td>\n",
       "      <td>254.000000</td>\n",
       "      <td>62.000000</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>8 rows × 785 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "              label   pixel0   pixel1  ...  pixel781  pixel782  pixel783\n",
       "count  42000.000000  42000.0  42000.0  ...   42000.0   42000.0   42000.0\n",
       "mean       4.456643      0.0      0.0  ...       0.0       0.0       0.0\n",
       "std        2.887730      0.0      0.0  ...       0.0       0.0       0.0\n",
       "min        0.000000      0.0      0.0  ...       0.0       0.0       0.0\n",
       "25%        2.000000      0.0      0.0  ...       0.0       0.0       0.0\n",
       "50%        4.000000      0.0      0.0  ...       0.0       0.0       0.0\n",
       "75%        7.000000      0.0      0.0  ...       0.0       0.0       0.0\n",
       "max        9.000000      0.0      0.0  ...       0.0       0.0       0.0\n",
       "\n",
       "[8 rows x 785 columns]"
      ]
     },
     "execution_count": 7,
     "metadata": {
      "tags": []
     },
     "output_type": "execute_result"
    }
   ],
   "source": [
    "from google.colab import files\n",
    "file = files.upload()\n",
    "train_data = pd.read_csv(\"train.csv\")\n",
    "test_data = pd.read_csv(\"test.csv\")\n",
    "train_data.describe()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 44,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 34
    },
    "colab_type": "code",
    "id": "0ce5Y-07AT1I",
    "outputId": "3d35decb-1860-4b01-f9b4-c2b57c41fb2a"
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(42000, 28, 28, 1)"
      ]
     },
     "execution_count": 44,
     "metadata": {
      "tags": []
     },
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Prep data\n",
    "X_train = train_data.iloc[:,1:].values  # Pixel values\n",
    "Y_train = train_data.iloc[:,0].values # Image label (digit that's being represented by the pixel values)\n",
    "X_test = test_data.values\n",
    "X_train = X_train.reshape(X_train.shape[0], 28, 28, 1) #reshaping training data in 28x28x1 squares, for all images in training dataset. Format: (nb_images, rows, cols, nb_color_channels(grayscale here))\n",
    "X_test = X_test.reshape(X_test.shape[0], 28, 28, 1)\n",
    "X_train.shape"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 45,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 104
    },
    "colab_type": "code",
    "id": "CBCKVlkVEChs",
    "outputId": "3338989d-0f6d-42a0-ba0f-c8b93f82e608"
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "count       784\n",
       "unique        2\n",
       "top       False\n",
       "freq        462\n",
       "dtype: object"
      ]
     },
     "execution_count": 45,
     "metadata": {
      "tags": []
     },
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Check for null and missing values\n",
    "train_data.isnull().any().describe()\n",
    "test_data.isnull().any().describe()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 0,
   "metadata": {
    "colab": {},
    "colab_type": "code",
    "id": "GfXPbAQGHPzs"
   },
   "outputs": [],
   "source": [
    "# Normalize images to reduce illumination effect\n",
    "X_train = X_train / 255.0\n",
    "X_test = X_test / 255.0"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 47,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 34
    },
    "colab_type": "code",
    "id": "ZzCwYg5kJVFD",
    "outputId": "4e1a8c9a-10fb-4097-ff11-f74beae36840"
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "(35700, 28, 28, 1) (35700, 10) (6300, 28, 28, 1) (6300, 10)\n"
     ]
    }
   ],
   "source": [
    "Y_train = to_categorical(Y_train, num_classes=10) # one_hot_encoding of labels\n",
    "# initialize a seed for reproducibility\n",
    "rand_seed = 4\n",
    "X_train, X_val, Y_train, Y_val = train_test_split(X_train, Y_train, test_size = 0.15, random_state=rand_seed)\n",
    "print(X_train.shape, Y_train.shape, X_val.shape, Y_val.shape)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 0,
   "metadata": {
    "colab": {},
    "colab_type": "code",
    "id": "g3q6bOM4LAfQ"
   },
   "outputs": [],
   "source": [
    "# Build CNN model\n",
    "model = Sequential()\n",
    "model.add(Conv2D(filters = 20, kernel_size = (7,7),padding = 'Same', \n",
    "                 activation ='relu', input_shape = (28,28,1)))\n",
    "model.add(Conv2D(filters = 20, kernel_size = (7,7),padding = 'Same', \n",
    "                 activation ='relu'))\n",
    "model.add(MaxPool2D(pool_size=(2,2)))\n",
    "\n",
    "model.add(Conv2D(filters = 50, kernel_size = (3,3),padding = 'Same', \n",
    "                 activation ='relu'))\n",
    "model.add(Conv2D(filters = 50, kernel_size = (3,3),padding = 'Same', \n",
    "                 activation ='relu'))\n",
    "model.add(MaxPool2D(pool_size=(2,2), strides=(2,2)))\n",
    "\n",
    "model.add(Flatten())\n",
    "model.add(Dense(256, activation = \"relu\"))\n",
    "model.add(Dense(10, activation = \"softmax\"))\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 0,
   "metadata": {
    "colab": {},
    "colab_type": "code",
    "id": "mR9RHpSKMTmk"
   },
   "outputs": [],
   "source": [
    "model.compile(optimizer=SGD(learning_rate=0.01,momentum=0.0),loss=\"categorical_crossentropy\", metrics=[\"accuracy\"])\n",
    "epochs = 20\n",
    "batch_size = 70"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 0,
   "metadata": {
    "colab": {},
    "colab_type": "code",
    "id": "qqglX__MNcQK"
   },
   "outputs": [],
   "source": [
    "# Augment Data to expand training set\n",
    "data_aug = ImageDataGenerator(rotation_range=10,zoom_range=0.2, width_shift_range=0.2)\n",
    "data_aug.fit(X_train)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 51,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 712
    },
    "colab_type": "code",
    "id": "_IAcsIi6N4tB",
    "outputId": "dc19f8ee-8404-4955-e184-764f8d77a93a"
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch 1/20\n",
      "510/510 [==============================] - 264s 517ms/step - loss: 1.5815 - accuracy: 0.4633 - val_loss: 0.3979 - val_accuracy: 0.8971\n",
      "Epoch 2/20\n",
      "510/510 [==============================] - 261s 511ms/step - loss: 0.3653 - accuracy: 0.8914 - val_loss: 0.1953 - val_accuracy: 0.9468\n",
      "Epoch 3/20\n",
      "510/510 [==============================] - 260s 510ms/step - loss: 0.2173 - accuracy: 0.9345 - val_loss: 0.1306 - val_accuracy: 0.9625\n",
      "Epoch 4/20\n",
      "510/510 [==============================] - 256s 501ms/step - loss: 0.1676 - accuracy: 0.9503 - val_loss: 0.1138 - val_accuracy: 0.9621\n",
      "Epoch 5/20\n",
      "510/510 [==============================] - 256s 501ms/step - loss: 0.1437 - accuracy: 0.9565 - val_loss: 0.1043 - val_accuracy: 0.9686\n",
      "Epoch 6/20\n",
      "510/510 [==============================] - 265s 519ms/step - loss: 0.1235 - accuracy: 0.9622 - val_loss: 0.0875 - val_accuracy: 0.9732\n",
      "Epoch 7/20\n",
      "510/510 [==============================] - 267s 523ms/step - loss: 0.1108 - accuracy: 0.9656 - val_loss: 0.0862 - val_accuracy: 0.9719\n",
      "Epoch 8/20\n",
      "510/510 [==============================] - 268s 526ms/step - loss: 0.1051 - accuracy: 0.9674 - val_loss: 0.0836 - val_accuracy: 0.9732\n",
      "Epoch 9/20\n",
      "510/510 [==============================] - 261s 512ms/step - loss: 0.0958 - accuracy: 0.9710 - val_loss: 0.0724 - val_accuracy: 0.9762\n",
      "Epoch 10/20\n",
      "510/510 [==============================] - 264s 518ms/step - loss: 0.0900 - accuracy: 0.9727 - val_loss: 0.0718 - val_accuracy: 0.9768\n",
      "Epoch 11/20\n",
      "510/510 [==============================] - 259s 508ms/step - loss: 0.0864 - accuracy: 0.9733 - val_loss: 0.0726 - val_accuracy: 0.9757\n",
      "Epoch 12/20\n",
      "510/510 [==============================] - 260s 510ms/step - loss: 0.0817 - accuracy: 0.9746 - val_loss: 0.0716 - val_accuracy: 0.9779\n",
      "Epoch 13/20\n",
      "510/510 [==============================] - 264s 518ms/step - loss: 0.0769 - accuracy: 0.9761 - val_loss: 0.0603 - val_accuracy: 0.9790\n",
      "Epoch 14/20\n",
      "510/510 [==============================] - 265s 520ms/step - loss: 0.0754 - accuracy: 0.9778 - val_loss: 0.0631 - val_accuracy: 0.9792\n",
      "Epoch 15/20\n",
      "510/510 [==============================] - 268s 525ms/step - loss: 0.0720 - accuracy: 0.9781 - val_loss: 0.0609 - val_accuracy: 0.9800\n",
      "Epoch 16/20\n",
      "510/510 [==============================] - 264s 517ms/step - loss: 0.0701 - accuracy: 0.9787 - val_loss: 0.0609 - val_accuracy: 0.9790\n",
      "Epoch 17/20\n",
      "510/510 [==============================] - 267s 524ms/step - loss: 0.0653 - accuracy: 0.9803 - val_loss: 0.0551 - val_accuracy: 0.9819\n",
      "Epoch 18/20\n",
      "510/510 [==============================] - 263s 515ms/step - loss: 0.0611 - accuracy: 0.9806 - val_loss: 0.0527 - val_accuracy: 0.9830\n",
      "Epoch 19/20\n",
      "510/510 [==============================] - 263s 516ms/step - loss: 0.0593 - accuracy: 0.9813 - val_loss: 0.0552 - val_accuracy: 0.9821\n",
      "Epoch 20/20\n",
      "510/510 [==============================] - 268s 525ms/step - loss: 0.0599 - accuracy: 0.9808 - val_loss: 0.0582 - val_accuracy: 0.9810\n"
     ]
    }
   ],
   "source": [
    "# Fit the model\n",
    "output = model.fit_generator(data_aug.flow(X_train, Y_train, batch_size=batch_size), epochs=epochs, validation_data=(X_val, Y_val), steps_per_epoch=X_train.shape[0] // batch_size)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 55,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 52
    },
    "colab_type": "code",
    "id": "oKScFYgSkeg6",
    "outputId": "835688b7-184a-48c0-b586-e4a83ae4ab9f"
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "R^2 score: 0.9686180128435817\n",
      "Accuracy: 0.9809523809523809\n"
     ]
    }
   ],
   "source": [
    "# Checking validation accuracy\n",
    "from sklearn import metrics\n",
    "Y_pred = model.predict(X_val)\n",
    "print('R^2 score:',metrics.r2_score(Y_val, Y_pred))\n",
    "Y_pred_class = np.argmax(Y_pred, axis=1)   # Converting predictions to one hot vectors\n",
    "Y_val_class = np.argmax(Y_val, axis=1)\n",
    "print('Accuracy:',metrics.accuracy_score(Y_val_class, Y_pred_class)) # accuracy needs a vector of labels"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 0,
   "metadata": {
    "colab": {},
    "colab_type": "code",
    "id": "Df6iSDdLoByg"
   },
   "outputs": [],
   "source": [
    "# Predict test dataset\n",
    "test_output = model.predict(X_test)\n",
    "test_output = np.argmax(test_output, axis=1)\n",
    "test_output = pd.Series(test_output, name=\"Label\")\n",
    "results = pd.concat([pd.Series(range(1,28001),name = \"ImageId\"),test_output],axis = 1)\n",
    "#results.to_csv(\"mnist_testoutput.csv\",index=False)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 69,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 34
    },
    "colab_type": "code",
    "id": "QayXt7Nm9Bup",
    "outputId": "88c27fdc-b9ff-4be7-8ec2-e019a0a125aa"
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Drive already mounted at drive; to attempt to forcibly remount, call drive.mount(\"drive\", force_remount=True).\n"
     ]
    }
   ],
   "source": [
    "# Save file to drive\n",
    "from google.colab import drive\n",
    "drive.mount('drive')\n",
    "results.to_csv('mnist_testoutput.csv', index=False)\n",
    "!cp mnist_testoutput.csv \"drive/My Drive/\""
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 70,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 34
    },
    "colab_type": "code",
    "id": "hJErQsbJ_Ezo",
    "outputId": "0fe341c6-f2f1-4330-86a5-a4fcf8f8be35"
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(28000, 2)"
      ]
     },
     "execution_count": 70,
     "metadata": {
      "tags": []
     },
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Sanity check\n",
    "df = pd.read_csv('mnist_testoutput.csv')\n",
    "df.shape"
   ]
  }
 ],
 "metadata": {
  "colab": {
   "name": "MNIST.ipynb",
   "provenance": []
  },
  "kernelspec": {
   "display_name": "Python 3",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.7.7"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 1
}