Notebooks/Pima-Prediction-with-reload.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "UFUOuEFUdKC-"
   },
   "source": [
    "# Pima Indian Diabetes Prediction"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "attachments": {},
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    " ### Update History\n",
    "    \n",
    "2023-01-26 Corrected calculation error in display of Training and Test true/false counts and percentages\n",
    "\n",
    "2021-04-15 Added bypass of imputation of Num of Pregnancies field, switched to using only transform for test data, and added code to load data from client system when running in Colab.\n",
    "\n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "FaLa-9oJdKDC"
   },
   "source": [
    "Import some basic libraries.\n",
    "* Pandas - provided data frames\n",
    "* matplotlib.pyplot - plotting support\n",
    "\n",
    "Use Magic %matplotlib to display graphics inline instead of in a popup window.\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 96,
   "metadata": {
    "id": "1h4d-iKzdKDC"
   },
   "outputs": [],
   "source": [
    "import pandas as pd                 # pandas is a dataframe library\n",
    "import matplotlib.pyplot as plt      # matplotlib.pyplot plots data\n",
    "\n",
    "%matplotlib inline"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "jzSrj5ohdKDD"
   },
   "source": [
    "## Loading and Reviewing the Data"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 97,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 72,
     "resources": {
      "http://localhost:8080/nbextensions/google.colab/files.js": {
       "data": "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",
       "headers": [
        [
         "content-type",
         "application/javascript"
        ]
       ],
       "ok": true,
       "status": 200,
       "status_text": ""
      }
     }
    },
    "executionInfo": {
     "elapsed": 6143,
     "status": "ok",
     "timestamp": 1618406188834,
     "user": {
      "displayName": "jerry kurata",
      "photoUrl": "https://lh3.googleusercontent.com/a-/AOh14GgDrlccxI84_FsH18rCGaMpIHdbLPfi4DgdhCbSxQ=s64",
      "userId": "08438564134228659223"
     },
     "user_tz": 420
    },
    "id": "P191RQNqdoJ4",
    "outputId": "4d7fd0fc-a384-4f84-bad7-e7603627ccfc"
   },
   "outputs": [],
   "source": [
    "# COLAB VERSION ONLY - load file from user's computer\n",
    "#from google.colab import files\n",
    "#uploaded = files.upload() \n",
    "# once uploaded, read the files contents into the dataframe\n",
    "#import io\n",
    "#df = pd.read_csv(io.BytesIO(uploaded['pima-data.csv']))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 98,
   "metadata": {
    "id": "-KPXDsCjdKDD"
   },
   "outputs": [],
   "source": [
    "# regular version pointing to file on users system\n",
    "df = pd.read_csv(\"./data/pima-data.csv\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 99,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/"
    },
    "executionInfo": {
     "elapsed": 6138,
     "status": "ok",
     "timestamp": 1618406188836,
     "user": {
      "displayName": "jerry kurata",
      "photoUrl": "https://lh3.googleusercontent.com/a-/AOh14GgDrlccxI84_FsH18rCGaMpIHdbLPfi4DgdhCbSxQ=s64",
      "userId": "08438564134228659223"
     },
     "user_tz": 420
    },
    "id": "PzBbo6R8dKDD",
    "outputId": "04068303-6bb6-4e69-c99b-d4d91b163274"
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(768, 10)"
      ]
     },
     "execution_count": 99,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.shape"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 100,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 204
    },
    "executionInfo": {
     "elapsed": 6133,
     "status": "ok",
     "timestamp": 1618406188836,
     "user": {
      "displayName": "jerry kurata",
      "photoUrl": "https://lh3.googleusercontent.com/a-/AOh14GgDrlccxI84_FsH18rCGaMpIHdbLPfi4DgdhCbSxQ=s64",
      "userId": "08438564134228659223"
     },
     "user_tz": 420
    },
    "id": "_PSUjQBPdKDE",
    "outputId": "e80d7268-0e93-4005-bb78-aaf2c6cc7a77"
   },
   "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>num_preg</th>\n",
       "      <th>glucose_conc</th>\n",
       "      <th>diastolic_bp</th>\n",
       "      <th>thickness</th>\n",
       "      <th>insulin</th>\n",
       "      <th>bmi</th>\n",
       "      <th>diab_pred</th>\n",
       "      <th>age</th>\n",
       "      <th>skin</th>\n",
       "      <th>diabetes</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>6</td>\n",
       "      <td>148</td>\n",
       "      <td>72</td>\n",
       "      <td>35</td>\n",
       "      <td>0</td>\n",
       "      <td>33.6</td>\n",
       "      <td>0.627</td>\n",
       "      <td>50</td>\n",
       "      <td>1.3790</td>\n",
       "      <td>True</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>1</td>\n",
       "      <td>85</td>\n",
       "      <td>66</td>\n",
       "      <td>29</td>\n",
       "      <td>0</td>\n",
       "      <td>26.6</td>\n",
       "      <td>0.351</td>\n",
       "      <td>31</td>\n",
       "      <td>1.1426</td>\n",
       "      <td>False</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>8</td>\n",
       "      <td>183</td>\n",
       "      <td>64</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>23.3</td>\n",
       "      <td>0.672</td>\n",
       "      <td>32</td>\n",
       "      <td>0.0000</td>\n",
       "      <td>True</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>1</td>\n",
       "      <td>89</td>\n",
       "      <td>66</td>\n",
       "      <td>23</td>\n",
       "      <td>94</td>\n",
       "      <td>28.1</td>\n",
       "      <td>0.167</td>\n",
       "      <td>21</td>\n",
       "      <td>0.9062</td>\n",
       "      <td>False</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>0</td>\n",
       "      <td>137</td>\n",
       "      <td>40</td>\n",
       "      <td>35</td>\n",
       "      <td>168</td>\n",
       "      <td>43.1</td>\n",
       "      <td>2.288</td>\n",
       "      <td>33</td>\n",
       "      <td>1.3790</td>\n",
       "      <td>True</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   num_preg  glucose_conc  diastolic_bp  thickness  insulin   bmi  diab_pred  \\\n",
       "0         6           148            72         35        0  33.6      0.627   \n",
       "1         1            85            66         29        0  26.6      0.351   \n",
       "2         8           183            64          0        0  23.3      0.672   \n",
       "3         1            89            66         23       94  28.1      0.167   \n",
       "4         0           137            40         35      168  43.1      2.288   \n",
       "\n",
       "   age    skin  diabetes  \n",
       "0   50  1.3790      True  \n",
       "1   31  1.1426     False  \n",
       "2   32  0.0000      True  \n",
       "3   21  0.9062     False  \n",
       "4   33  1.3790      True  "
      ]
     },
     "execution_count": 100,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.head(5)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 101,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 204
    },
    "executionInfo": {
     "elapsed": 6397,
     "status": "ok",
     "timestamp": 1618406189106,
     "user": {
      "displayName": "jerry kurata",
      "photoUrl": "https://lh3.googleusercontent.com/a-/AOh14GgDrlccxI84_FsH18rCGaMpIHdbLPfi4DgdhCbSxQ=s64",
      "userId": "08438564134228659223"
     },
     "user_tz": 420
    },
    "id": "NLTl326SdKDE",
    "outputId": "53638616-5385-499e-bdd6-a2e91cd81f2c"
   },
   "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>num_preg</th>\n",
       "      <th>glucose_conc</th>\n",
       "      <th>diastolic_bp</th>\n",
       "      <th>thickness</th>\n",
       "      <th>insulin</th>\n",
       "      <th>bmi</th>\n",
       "      <th>diab_pred</th>\n",
       "      <th>age</th>\n",
       "      <th>skin</th>\n",
       "      <th>diabetes</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>763</th>\n",
       "      <td>10</td>\n",
       "      <td>101</td>\n",
       "      <td>76</td>\n",
       "      <td>48</td>\n",
       "      <td>180</td>\n",
       "      <td>32.9</td>\n",
       "      <td>0.171</td>\n",
       "      <td>63</td>\n",
       "      <td>1.8912</td>\n",
       "      <td>False</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>764</th>\n",
       "      <td>2</td>\n",
       "      <td>122</td>\n",
       "      <td>70</td>\n",
       "      <td>27</td>\n",
       "      <td>0</td>\n",
       "      <td>36.8</td>\n",
       "      <td>0.340</td>\n",
       "      <td>27</td>\n",
       "      <td>1.0638</td>\n",
       "      <td>False</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>765</th>\n",
       "      <td>5</td>\n",
       "      <td>121</td>\n",
       "      <td>72</td>\n",
       "      <td>23</td>\n",
       "      <td>112</td>\n",
       "      <td>26.2</td>\n",
       "      <td>0.245</td>\n",
       "      <td>30</td>\n",
       "      <td>0.9062</td>\n",
       "      <td>False</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>766</th>\n",
       "      <td>1</td>\n",
       "      <td>126</td>\n",
       "      <td>60</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>30.1</td>\n",
       "      <td>0.349</td>\n",
       "      <td>47</td>\n",
       "      <td>0.0000</td>\n",
       "      <td>True</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>767</th>\n",
       "      <td>1</td>\n",
       "      <td>93</td>\n",
       "      <td>70</td>\n",
       "      <td>31</td>\n",
       "      <td>0</td>\n",
       "      <td>30.4</td>\n",
       "      <td>0.315</td>\n",
       "      <td>23</td>\n",
       "      <td>1.2214</td>\n",
       "      <td>False</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "     num_preg  glucose_conc  diastolic_bp  thickness  insulin   bmi  \\\n",
       "763        10           101            76         48      180  32.9   \n",
       "764         2           122            70         27        0  36.8   \n",
       "765         5           121            72         23      112  26.2   \n",
       "766         1           126            60          0        0  30.1   \n",
       "767         1            93            70         31        0  30.4   \n",
       "\n",
       "     diab_pred  age    skin  diabetes  \n",
       "763      0.171   63  1.8912     False  \n",
       "764      0.340   27  1.0638     False  \n",
       "765      0.245   30  0.9062     False  \n",
       "766      0.349   47  0.0000      True  \n",
       "767      0.315   23  1.2214     False  "
      ]
     },
     "execution_count": 101,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.tail(5)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "UP5qWGjodKDE"
   },
   "source": [
    "### Definition of features\n",
    "From the metadata on the data source we have the following definition of the features.\n",
    "\n",
    "| Feature  | Description | Comments |\n",
    "|--------------|-------------|--------|\n",
    "| num_preg     | number of pregnancies         | 0 is valid\n",
    "| glucose_conc | Plasma glucose concentration a 2 hours in an oral glucose tolerance test         |\n",
    "| diastolic_bp | Diastolic blood pressure (mm Hg) |\n",
    "| thickness | Triceps skin fold thickness (mm) |\n",
    "|insulin | 2-Hour serum insulin (mu U/ml) |\n",
    "| bmi |  Body mass index (weight in kg/(height in m)^2) |\n",
    "| diab_pred |  Diabetes pedigree function |\n",
    "| Age (years) | Age (years)|\n",
    "| skin | ???? | What is this? |\n",
    "| diabetes | Class variable (1=True, 0=False) |  Why is our data boolean (True/False)? |\n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "LIDgIf5_dKDF"
   },
   "source": [
    "## Check for null values"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 102,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/"
    },
    "executionInfo": {
     "elapsed": 6395,
     "status": "ok",
     "timestamp": 1618406189109,
     "user": {
      "displayName": "jerry kurata",
      "photoUrl": "https://lh3.googleusercontent.com/a-/AOh14GgDrlccxI84_FsH18rCGaMpIHdbLPfi4DgdhCbSxQ=s64",
      "userId": "08438564134228659223"
     },
     "user_tz": 420
    },
    "id": "sJWqvdI5dKDF",
    "outputId": "404ac3d8-a7f9-4ffd-d5f1-56fd7aa6b96e"
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "False"
      ]
     },
     "execution_count": 102,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.isnull().values.any()\n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "XAoXhMe-dKDF"
   },
   "source": [
    "### Correlated Feature Check"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "DQz3N0SadKDF"
   },
   "source": [
    "Helper function that displays correlation by color.  Red is most correlated, Blue least."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 103,
   "metadata": {
    "id": "POeoJJJpdKDF"
   },
   "outputs": [],
   "source": [
    "def plot_corr(df, size=11):\n",
    "    \"\"\"\n",
    "    Function plots a graphical correlation matrix for each pair of columns in the dataframe.\n",
    "\n",
    "    Input:\n",
    "        df: pandas DataFrame\n",
    "        size: vertical and horizontal size of the plot\n",
    "\n",
    "    Displays:\n",
    "        matrix of correlation between columns.  Blue-cyan-yellow-red-darkred => less to more correlated\n",
    "                                                0 ------------------>  1\n",
    "                                                Expect a darkred line running from top left to bottom right\n",
    "    \"\"\"\n",
    "\n",
    "    corr = df.corr()    # data frame correlation function\n",
    "    fig, ax = plt.subplots(figsize=(size, size))\n",
    "    ax.matshow(corr)   # color code the rectangles by correlation value\n",
    "    plt.xticks(range(len(corr.columns)), corr.columns)  # draw x tick marks\n",
    "    plt.yticks(range(len(corr.columns)), corr.columns)  # draw y tick marks\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 104,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 650
    },
    "executionInfo": {
     "elapsed": 7192,
     "status": "ok",
     "timestamp": 1618406189912,
     "user": {
      "displayName": "jerry kurata",
      "photoUrl": "https://lh3.googleusercontent.com/a-/AOh14GgDrlccxI84_FsH18rCGaMpIHdbLPfi4DgdhCbSxQ=s64",
      "userId": "08438564134228659223"
     },
     "user_tz": 420
    },
    "id": "DJ3uzdgRdKDG",
    "outputId": "1c879424-b13b-4f11-847a-9d0965454331"
   },
   "outputs": [
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 792x792 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "plot_corr(df)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 105,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 359
    },
    "executionInfo": {
     "elapsed": 7188,
     "status": "ok",
     "timestamp": 1618406189913,
     "user": {
      "displayName": "jerry kurata",
      "photoUrl": "https://lh3.googleusercontent.com/a-/AOh14GgDrlccxI84_FsH18rCGaMpIHdbLPfi4DgdhCbSxQ=s64",
      "userId": "08438564134228659223"
     },
     "user_tz": 420
    },
    "id": "ptJgWTuGdKDG",
    "outputId": "1093218b-3a5a-4ccf-ed5a-a08cc4d67fae"
   },
   "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>num_preg</th>\n",
       "      <th>glucose_conc</th>\n",
       "      <th>diastolic_bp</th>\n",
       "      <th>thickness</th>\n",
       "      <th>insulin</th>\n",
       "      <th>bmi</th>\n",
       "      <th>diab_pred</th>\n",
       "      <th>age</th>\n",
       "      <th>skin</th>\n",
       "      <th>diabetes</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>num_preg</th>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.129459</td>\n",
       "      <td>0.141282</td>\n",
       "      <td>-0.081672</td>\n",
       "      <td>-0.073535</td>\n",
       "      <td>0.017683</td>\n",
       "      <td>-0.033523</td>\n",
       "      <td>0.544341</td>\n",
       "      <td>-0.081672</td>\n",
       "      <td>0.221898</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>glucose_conc</th>\n",
       "      <td>0.129459</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.152590</td>\n",
       "      <td>0.057328</td>\n",
       "      <td>0.331357</td>\n",
       "      <td>0.221071</td>\n",
       "      <td>0.137337</td>\n",
       "      <td>0.263514</td>\n",
       "      <td>0.057328</td>\n",
       "      <td>0.466581</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>diastolic_bp</th>\n",
       "      <td>0.141282</td>\n",
       "      <td>0.152590</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.207371</td>\n",
       "      <td>0.088933</td>\n",
       "      <td>0.281805</td>\n",
       "      <td>0.041265</td>\n",
       "      <td>0.239528</td>\n",
       "      <td>0.207371</td>\n",
       "      <td>0.065068</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>thickness</th>\n",
       "      <td>-0.081672</td>\n",
       "      <td>0.057328</td>\n",
       "      <td>0.207371</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.436783</td>\n",
       "      <td>0.392573</td>\n",
       "      <td>0.183928</td>\n",
       "      <td>-0.113970</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.074752</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>insulin</th>\n",
       "      <td>-0.073535</td>\n",
       "      <td>0.331357</td>\n",
       "      <td>0.088933</td>\n",
       "      <td>0.436783</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.197859</td>\n",
       "      <td>0.185071</td>\n",
       "      <td>-0.042163</td>\n",
       "      <td>0.436783</td>\n",
       "      <td>0.130548</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>bmi</th>\n",
       "      <td>0.017683</td>\n",
       "      <td>0.221071</td>\n",
       "      <td>0.281805</td>\n",
       "      <td>0.392573</td>\n",
       "      <td>0.197859</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.140647</td>\n",
       "      <td>0.036242</td>\n",
       "      <td>0.392573</td>\n",
       "      <td>0.292695</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>diab_pred</th>\n",
       "      <td>-0.033523</td>\n",
       "      <td>0.137337</td>\n",
       "      <td>0.041265</td>\n",
       "      <td>0.183928</td>\n",
       "      <td>0.185071</td>\n",
       "      <td>0.140647</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.033561</td>\n",
       "      <td>0.183928</td>\n",
       "      <td>0.173844</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>age</th>\n",
       "      <td>0.544341</td>\n",
       "      <td>0.263514</td>\n",
       "      <td>0.239528</td>\n",
       "      <td>-0.113970</td>\n",
       "      <td>-0.042163</td>\n",
       "      <td>0.036242</td>\n",
       "      <td>0.033561</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>-0.113970</td>\n",
       "      <td>0.238356</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>skin</th>\n",
       "      <td>-0.081672</td>\n",
       "      <td>0.057328</td>\n",
       "      <td>0.207371</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.436783</td>\n",
       "      <td>0.392573</td>\n",
       "      <td>0.183928</td>\n",
       "      <td>-0.113970</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.074752</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>diabetes</th>\n",
       "      <td>0.221898</td>\n",
       "      <td>0.466581</td>\n",
       "      <td>0.065068</td>\n",
       "      <td>0.074752</td>\n",
       "      <td>0.130548</td>\n",
       "      <td>0.292695</td>\n",
       "      <td>0.173844</td>\n",
       "      <td>0.238356</td>\n",
       "      <td>0.074752</td>\n",
       "      <td>1.000000</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "              num_preg  glucose_conc  diastolic_bp  thickness   insulin  \\\n",
       "num_preg      1.000000      0.129459      0.141282  -0.081672 -0.073535   \n",
       "glucose_conc  0.129459      1.000000      0.152590   0.057328  0.331357   \n",
       "diastolic_bp  0.141282      0.152590      1.000000   0.207371  0.088933   \n",
       "thickness    -0.081672      0.057328      0.207371   1.000000  0.436783   \n",
       "insulin      -0.073535      0.331357      0.088933   0.436783  1.000000   \n",
       "bmi           0.017683      0.221071      0.281805   0.392573  0.197859   \n",
       "diab_pred    -0.033523      0.137337      0.041265   0.183928  0.185071   \n",
       "age           0.544341      0.263514      0.239528  -0.113970 -0.042163   \n",
       "skin         -0.081672      0.057328      0.207371   1.000000  0.436783   \n",
       "diabetes      0.221898      0.466581      0.065068   0.074752  0.130548   \n",
       "\n",
       "                   bmi  diab_pred       age      skin  diabetes  \n",
       "num_preg      0.017683  -0.033523  0.544341 -0.081672  0.221898  \n",
       "glucose_conc  0.221071   0.137337  0.263514  0.057328  0.466581  \n",
       "diastolic_bp  0.281805   0.041265  0.239528  0.207371  0.065068  \n",
       "thickness     0.392573   0.183928 -0.113970  1.000000  0.074752  \n",
       "insulin       0.197859   0.185071 -0.042163  0.436783  0.130548  \n",
       "bmi           1.000000   0.140647  0.036242  0.392573  0.292695  \n",
       "diab_pred     0.140647   1.000000  0.033561  0.183928  0.173844  \n",
       "age           0.036242   0.033561  1.000000 -0.113970  0.238356  \n",
       "skin          0.392573   0.183928 -0.113970  1.000000  0.074752  \n",
       "diabetes      0.292695   0.173844  0.238356  0.074752  1.000000  "
      ]
     },
     "execution_count": 105,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.corr()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 106,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 204
    },
    "executionInfo": {
     "elapsed": 7182,
     "status": "ok",
     "timestamp": 1618406189913,
     "user": {
      "displayName": "jerry kurata",
      "photoUrl": "https://lh3.googleusercontent.com/a-/AOh14GgDrlccxI84_FsH18rCGaMpIHdbLPfi4DgdhCbSxQ=s64",
      "userId": "08438564134228659223"
     },
     "user_tz": 420
    },
    "id": "DTbYP9_LdKDG",
    "outputId": "ac44d6e6-e7c6-4846-e3b4-2bb6e6ae803b"
   },
   "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>num_preg</th>\n",
       "      <th>glucose_conc</th>\n",
       "      <th>diastolic_bp</th>\n",
       "      <th>thickness</th>\n",
       "      <th>insulin</th>\n",
       "      <th>bmi</th>\n",
       "      <th>diab_pred</th>\n",
       "      <th>age</th>\n",
       "      <th>skin</th>\n",
       "      <th>diabetes</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>6</td>\n",
       "      <td>148</td>\n",
       "      <td>72</td>\n",
       "      <td>35</td>\n",
       "      <td>0</td>\n",
       "      <td>33.6</td>\n",
       "      <td>0.627</td>\n",
       "      <td>50</td>\n",
       "      <td>1.3790</td>\n",
       "      <td>True</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>1</td>\n",
       "      <td>85</td>\n",
       "      <td>66</td>\n",
       "      <td>29</td>\n",
       "      <td>0</td>\n",
       "      <td>26.6</td>\n",
       "      <td>0.351</td>\n",
       "      <td>31</td>\n",
       "      <td>1.1426</td>\n",
       "      <td>False</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>8</td>\n",
       "      <td>183</td>\n",
       "      <td>64</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>23.3</td>\n",
       "      <td>0.672</td>\n",
       "      <td>32</td>\n",
       "      <td>0.0000</td>\n",
       "      <td>True</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>1</td>\n",
       "      <td>89</td>\n",
       "      <td>66</td>\n",
       "      <td>23</td>\n",
       "      <td>94</td>\n",
       "      <td>28.1</td>\n",
       "      <td>0.167</td>\n",
       "      <td>21</td>\n",
       "      <td>0.9062</td>\n",
       "      <td>False</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>0</td>\n",
       "      <td>137</td>\n",
       "      <td>40</td>\n",
       "      <td>35</td>\n",
       "      <td>168</td>\n",
       "      <td>43.1</td>\n",
       "      <td>2.288</td>\n",
       "      <td>33</td>\n",
       "      <td>1.3790</td>\n",
       "      <td>True</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   num_preg  glucose_conc  diastolic_bp  thickness  insulin   bmi  diab_pred  \\\n",
       "0         6           148            72         35        0  33.6      0.627   \n",
       "1         1            85            66         29        0  26.6      0.351   \n",
       "2         8           183            64          0        0  23.3      0.672   \n",
       "3         1            89            66         23       94  28.1      0.167   \n",
       "4         0           137            40         35      168  43.1      2.288   \n",
       "\n",
       "   age    skin  diabetes  \n",
       "0   50  1.3790      True  \n",
       "1   31  1.1426     False  \n",
       "2   32  0.0000      True  \n",
       "3   21  0.9062     False  \n",
       "4   33  1.3790      True  "
      ]
     },
     "execution_count": 106,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.head(5)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "BmTnDByddKDG"
   },
   "source": [
    "The skin and thickness columns are correlated 1 to 1.  Dropping the skin column"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 107,
   "metadata": {
    "id": "hN8nPyFrdKDG"
   },
   "outputs": [],
   "source": [
    "del df['skin']"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 108,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 204
    },
    "executionInfo": {
     "elapsed": 7176,
     "status": "ok",
     "timestamp": 1618406189914,
     "user": {
      "displayName": "jerry kurata",
      "photoUrl": "https://lh3.googleusercontent.com/a-/AOh14GgDrlccxI84_FsH18rCGaMpIHdbLPfi4DgdhCbSxQ=s64",
      "userId": "08438564134228659223"
     },
     "user_tz": 420
    },
    "id": "F0nx-XJDdKDH",
    "outputId": "d18c4269-c5cf-4018-9f4d-86e65fb903fe"
   },
   "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>num_preg</th>\n",
       "      <th>glucose_conc</th>\n",
       "      <th>diastolic_bp</th>\n",
       "      <th>thickness</th>\n",
       "      <th>insulin</th>\n",
       "      <th>bmi</th>\n",
       "      <th>diab_pred</th>\n",
       "      <th>age</th>\n",
       "      <th>diabetes</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>6</td>\n",
       "      <td>148</td>\n",
       "      <td>72</td>\n",
       "      <td>35</td>\n",
       "      <td>0</td>\n",
       "      <td>33.6</td>\n",
       "      <td>0.627</td>\n",
       "      <td>50</td>\n",
       "      <td>True</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>1</td>\n",
       "      <td>85</td>\n",
       "      <td>66</td>\n",
       "      <td>29</td>\n",
       "      <td>0</td>\n",
       "      <td>26.6</td>\n",
       "      <td>0.351</td>\n",
       "      <td>31</td>\n",
       "      <td>False</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>8</td>\n",
       "      <td>183</td>\n",
       "      <td>64</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>23.3</td>\n",
       "      <td>0.672</td>\n",
       "      <td>32</td>\n",
       "      <td>True</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>1</td>\n",
       "      <td>89</td>\n",
       "      <td>66</td>\n",
       "      <td>23</td>\n",
       "      <td>94</td>\n",
       "      <td>28.1</td>\n",
       "      <td>0.167</td>\n",
       "      <td>21</td>\n",
       "      <td>False</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>0</td>\n",
       "      <td>137</td>\n",
       "      <td>40</td>\n",
       "      <td>35</td>\n",
       "      <td>168</td>\n",
       "      <td>43.1</td>\n",
       "      <td>2.288</td>\n",
       "      <td>33</td>\n",
       "      <td>True</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   num_preg  glucose_conc  diastolic_bp  thickness  insulin   bmi  diab_pred  \\\n",
       "0         6           148            72         35        0  33.6      0.627   \n",
       "1         1            85            66         29        0  26.6      0.351   \n",
       "2         8           183            64          0        0  23.3      0.672   \n",
       "3         1            89            66         23       94  28.1      0.167   \n",
       "4         0           137            40         35      168  43.1      2.288   \n",
       "\n",
       "   age  diabetes  \n",
       "0   50      True  \n",
       "1   31     False  \n",
       "2   32      True  \n",
       "3   21     False  \n",
       "4   33      True  "
      ]
     },
     "execution_count": 108,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.head(5)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "FzzvMfd_dKDH"
   },
   "source": [
    "Check for additional correlations"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 109,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 650
    },
    "executionInfo": {
     "elapsed": 7460,
     "status": "ok",
     "timestamp": 1618406190203,
     "user": {
      "displayName": "jerry kurata",
      "photoUrl": "https://lh3.googleusercontent.com/a-/AOh14GgDrlccxI84_FsH18rCGaMpIHdbLPfi4DgdhCbSxQ=s64",
      "userId": "08438564134228659223"
     },
     "user_tz": 420
    },
    "id": "v51Xcj-sdKDH",
    "outputId": "5f08a6ee-4389-48d6-f99c-2863cff02cb1"
   },
   "outputs": [
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 792x792 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "plot_corr(df)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "HrdfZzcZdKDH"
   },
   "source": [
    "The correlations look good.  There appear to be no coorelated columns."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "Az0ZoaaKdKDH"
   },
   "source": [
    "## Mold Data"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "HxcA0JEGdKDH"
   },
   "source": [
    "### Data Types\n",
    "\n",
    "Inspect data types to see if there are any issues.  Data should be numeric."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 110,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 204
    },
    "executionInfo": {
     "elapsed": 7455,
     "status": "ok",
     "timestamp": 1618406190203,
     "user": {
      "displayName": "jerry kurata",
      "photoUrl": "https://lh3.googleusercontent.com/a-/AOh14GgDrlccxI84_FsH18rCGaMpIHdbLPfi4DgdhCbSxQ=s64",
      "userId": "08438564134228659223"
     },
     "user_tz": 420
    },
    "id": "RcJaW62ydKDI",
    "outputId": "246e584e-f426-4d72-e48d-8f699f1f3b71"
   },
   "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>num_preg</th>\n",
       "      <th>glucose_conc</th>\n",
       "      <th>diastolic_bp</th>\n",
       "      <th>thickness</th>\n",
       "      <th>insulin</th>\n",
       "      <th>bmi</th>\n",
       "      <th>diab_pred</th>\n",
       "      <th>age</th>\n",
       "      <th>diabetes</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>6</td>\n",
       "      <td>148</td>\n",
       "      <td>72</td>\n",
       "      <td>35</td>\n",
       "      <td>0</td>\n",
       "      <td>33.6</td>\n",
       "      <td>0.627</td>\n",
       "      <td>50</td>\n",
       "      <td>True</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>1</td>\n",
       "      <td>85</td>\n",
       "      <td>66</td>\n",
       "      <td>29</td>\n",
       "      <td>0</td>\n",
       "      <td>26.6</td>\n",
       "      <td>0.351</td>\n",
       "      <td>31</td>\n",
       "      <td>False</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>8</td>\n",
       "      <td>183</td>\n",
       "      <td>64</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>23.3</td>\n",
       "      <td>0.672</td>\n",
       "      <td>32</td>\n",
       "      <td>True</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>1</td>\n",
       "      <td>89</td>\n",
       "      <td>66</td>\n",
       "      <td>23</td>\n",
       "      <td>94</td>\n",
       "      <td>28.1</td>\n",
       "      <td>0.167</td>\n",
       "      <td>21</td>\n",
       "      <td>False</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>0</td>\n",
       "      <td>137</td>\n",
       "      <td>40</td>\n",
       "      <td>35</td>\n",
       "      <td>168</td>\n",
       "      <td>43.1</td>\n",
       "      <td>2.288</td>\n",
       "      <td>33</td>\n",
       "      <td>True</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   num_preg  glucose_conc  diastolic_bp  thickness  insulin   bmi  diab_pred  \\\n",
       "0         6           148            72         35        0  33.6      0.627   \n",
       "1         1            85            66         29        0  26.6      0.351   \n",
       "2         8           183            64          0        0  23.3      0.672   \n",
       "3         1            89            66         23       94  28.1      0.167   \n",
       "4         0           137            40         35      168  43.1      2.288   \n",
       "\n",
       "   age  diabetes  \n",
       "0   50      True  \n",
       "1   31     False  \n",
       "2   32      True  \n",
       "3   21     False  \n",
       "4   33      True  "
      ]
     },
     "execution_count": 110,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.head(5)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "dy1h7_3VdKDI"
   },
   "source": [
    "Change diabetes from boolean to integer, True=1, False=0"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 111,
   "metadata": {
    "id": "deosWnRRdKDI"
   },
   "outputs": [],
   "source": [
    "diabetes_map = {True : 1, False : 0}\n",
    "df['diabetes'] = df['diabetes'].map(diabetes_map)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "R3IziSz9dKDI"
   },
   "source": [
    "Verify that the diabetes data type has been changed."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "2j1yua3CdKDI"
   },
   "source": [
    "     \n",
    "     \n",
    "     \n",
    "     \n",
    "     \n",
    "     \n",
    "     \n",
    "     \n",
    "     \n",
    "     \n",
    "     \n",
    "     \n",
    "     \n",
    "     \n",
    "     \n",
    "     "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 112,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 204
    },
    "executionInfo": {
     "elapsed": 7449,
     "status": "ok",
     "timestamp": 1618406190204,
     "user": {
      "displayName": "jerry kurata",
      "photoUrl": "https://lh3.googleusercontent.com/a-/AOh14GgDrlccxI84_FsH18rCGaMpIHdbLPfi4DgdhCbSxQ=s64",
      "userId": "08438564134228659223"
     },
     "user_tz": 420
    },
    "id": "s-jZNWVzdKDI",
    "outputId": "191828dd-083c-4480-fdd6-e2087bc02c0f"
   },
   "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>num_preg</th>\n",
       "      <th>glucose_conc</th>\n",
       "      <th>diastolic_bp</th>\n",
       "      <th>thickness</th>\n",
       "      <th>insulin</th>\n",
       "      <th>bmi</th>\n",
       "      <th>diab_pred</th>\n",
       "      <th>age</th>\n",
       "      <th>diabetes</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>6</td>\n",
       "      <td>148</td>\n",
       "      <td>72</td>\n",
       "      <td>35</td>\n",
       "      <td>0</td>\n",
       "      <td>33.6</td>\n",
       "      <td>0.627</td>\n",
       "      <td>50</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>1</td>\n",
       "      <td>85</td>\n",
       "      <td>66</td>\n",
       "      <td>29</td>\n",
       "      <td>0</td>\n",
       "      <td>26.6</td>\n",
       "      <td>0.351</td>\n",
       "      <td>31</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>8</td>\n",
       "      <td>183</td>\n",
       "      <td>64</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>23.3</td>\n",
       "      <td>0.672</td>\n",
       "      <td>32</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>1</td>\n",
       "      <td>89</td>\n",
       "      <td>66</td>\n",
       "      <td>23</td>\n",
       "      <td>94</td>\n",
       "      <td>28.1</td>\n",
       "      <td>0.167</td>\n",
       "      <td>21</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>0</td>\n",
       "      <td>137</td>\n",
       "      <td>40</td>\n",
       "      <td>35</td>\n",
       "      <td>168</td>\n",
       "      <td>43.1</td>\n",
       "      <td>2.288</td>\n",
       "      <td>33</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   num_preg  glucose_conc  diastolic_bp  thickness  insulin   bmi  diab_pred  \\\n",
       "0         6           148            72         35        0  33.6      0.627   \n",
       "1         1            85            66         29        0  26.6      0.351   \n",
       "2         8           183            64          0        0  23.3      0.672   \n",
       "3         1            89            66         23       94  28.1      0.167   \n",
       "4         0           137            40         35      168  43.1      2.288   \n",
       "\n",
       "   age  diabetes  \n",
       "0   50         1  \n",
       "1   31         0  \n",
       "2   32         1  \n",
       "3   21         0  \n",
       "4   33         1  "
      ]
     },
     "execution_count": 112,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.head(5)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "VIFb2nOkdKDI"
   },
   "source": [
    "### Check for null values"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 113,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/"
    },
    "executionInfo": {
     "elapsed": 7445,
     "status": "ok",
     "timestamp": 1618406190205,
     "user": {
      "displayName": "jerry kurata",
      "photoUrl": "https://lh3.googleusercontent.com/a-/AOh14GgDrlccxI84_FsH18rCGaMpIHdbLPfi4DgdhCbSxQ=s64",
      "userId": "08438564134228659223"
     },
     "user_tz": 420
    },
    "id": "PfpLX2hqdKDJ",
    "outputId": "1f92fec6-2b99-406c-f10d-792692adfc56"
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "False"
      ]
     },
     "execution_count": 113,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.isnull().values.any()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "UVC7G7addKDJ"
   },
   "source": [
    "No obvious null values."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "Xyz9hoVEdKDJ"
   },
   "source": [
    "### Check class distribution \n",
    "\n",
    "Rare events are hard to predict"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 114,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/"
    },
    "executionInfo": {
     "elapsed": 7442,
     "status": "ok",
     "timestamp": 1618406190206,
     "user": {
      "displayName": "jerry kurata",
      "photoUrl": "https://lh3.googleusercontent.com/a-/AOh14GgDrlccxI84_FsH18rCGaMpIHdbLPfi4DgdhCbSxQ=s64",
      "userId": "08438564134228659223"
     },
     "user_tz": 420
    },
    "id": "Bvy7mFPWdKDJ",
    "outputId": "4bb2dd16-6aab-42a0-ec7e-2ec7e8bce0ca"
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Number of True cases:  268 (34.90%)\n",
      "Number of False cases: 500 (65.10%)\n"
     ]
    }
   ],
   "source": [
    "num_obs = len(df)\n",
    "num_true = len(df.loc[df['diabetes'] == 1])\n",
    "num_false = len(df.loc[df['diabetes'] == 0])\n",
    "print(\"Number of True cases:  {0} ({1:2.2f}%)\".format(num_true, (num_true/num_obs) * 100))\n",
    "print(\"Number of False cases: {0} ({1:2.2f}%)\".format(num_false, (num_false/num_obs) * 100))"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "SiJlduHmdKDJ"
   },
   "source": [
    "Good distribution of true and false cases.  No special work needed."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "URJI1Q3BdKDJ"
   },
   "source": [
    "### Spliting the data \n",
    "\n",
    "70% for training, 30% for testing"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 115,
   "metadata": {
    "id": "aEaPT4oYdKDJ"
   },
   "outputs": [],
   "source": [
    "#from sklearn.cross_validation import train_test_split\n",
    "from sklearn.model_selection import train_test_split\n",
    "feature_col_names = ['num_preg', 'glucose_conc', 'diastolic_bp', 'thickness', 'insulin', 'bmi', 'diab_pred', 'age']\n",
    "predicted_class_names = ['diabetes']\n",
    "\n",
    "X =  df[feature_col_names]   # predictor feature columns (8 X m)\n",
    "y = df[predicted_class_names] # predicted class (1=true, 0=false) column (1 X m)\n",
    "\n",
    "split_test_size = 0.30\n",
    "\n",
    "X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=split_test_size, random_state=42) \n",
    "                            # test_size = 0.3 is 30%, 42 is the answer to everything"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "2nuJW70JdKDK"
   },
   "source": [
    "We check to ensure we have the the desired 70% train, 30% test split of the data"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 116,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/"
    },
    "executionInfo": {
     "elapsed": 8782,
     "status": "ok",
     "timestamp": 1618406191551,
     "user": {
      "displayName": "jerry kurata",
      "photoUrl": "https://lh3.googleusercontent.com/a-/AOh14GgDrlccxI84_FsH18rCGaMpIHdbLPfi4DgdhCbSxQ=s64",
      "userId": "08438564134228659223"
     },
     "user_tz": 420
    },
    "id": "YZmkSOc9dKDK",
    "outputId": "bc0fc09e-9885-4ddf-e507-c6e8e77d22a8"
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "69.92% in training set\n",
      "30.08% in test set\n"
     ]
    }
   ],
   "source": [
    "print(\"{0:0.2f}% in training set\".format((len(X_train)/len(df.index)) * 100))\n",
    "print(\"{0:0.2f}% in test set\".format((len(X_test)/len(df.index)) * 100))"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "XKExDh62dKDK"
   },
   "source": [
    "#### Verifying predicted value was split correctly"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 117,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/"
    },
    "executionInfo": {
     "elapsed": 8779,
     "status": "ok",
     "timestamp": 1618406191552,
     "user": {
      "displayName": "jerry kurata",
      "photoUrl": "https://lh3.googleusercontent.com/a-/AOh14GgDrlccxI84_FsH18rCGaMpIHdbLPfi4DgdhCbSxQ=s64",
      "userId": "08438564134228659223"
     },
     "user_tz": 420
    },
    "id": "yjIqnGIAdKDK",
    "outputId": "1b72b675-9de3-4ccd-d604-33b5ca9b552b"
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Original True  : 268 (34.90%)\n",
      "Original False : 500 (65.10%)\n",
      "\n",
      "Training True  : 188 (35.01%)\n",
      "Training False : 349 (64.99%)\n",
      "\n",
      "Test True      : 80 (34.63%)\n",
      "Test False     : 151 (65.37%)\n"
     ]
    }
   ],
   "source": [
    "print(\"Original True  : {0} ({1:0.2f}%)\".format(len(df.loc[df['diabetes'] == 1]), (len(df.loc[df['diabetes'] == 1])/len(df.index)) * 100.0))\n",
    "print(\"Original False : {0} ({1:0.2f}%)\".format(len(df.loc[df['diabetes'] == 0]), (len(df.loc[df['diabetes'] == 0])/len(df.index)) * 100.0))\n",
    "print(\"\")\n",
    "print(\"Training True  : {0} ({1:0.2f}%)\".format(len(y_train[y_train['diabetes'] == 1]), (len(y_train[y_train['diabetes'] == 1])/len(y_train) * 100.0)))\n",
    "print(\"Training False : {0} ({1:0.2f}%)\".format(len(y_train[y_train['diabetes'] == 0]), (len(y_train[y_train['diabetes'] == 0])/len(y_train) * 100.0)))\n",
    "print(\"\")\n",
    "print(\"Test True      : {0} ({1:0.2f}%)\".format(len(y_test[y_test['diabetes'] == 1]), (len(y_test[y_test['diabetes'] == 1])/len(y_test) * 100.0)))\n",
    "print(\"Test False     : {0} ({1:0.2f}%)\".format(len(y_test[y_test['diabetes'] == 0]), (len(y_test[y_test['diabetes'] == 0])/len(y_test) * 100.0)))"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "-xPescVhdKDK"
   },
   "source": [
    "### Post-split Data Preparation"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "1BJIPhqzdKDL"
   },
   "source": [
    "#### Hidden Missing Values"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 118,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 204
    },
    "executionInfo": {
     "elapsed": 8773,
     "status": "ok",
     "timestamp": 1618406191552,
     "user": {
      "displayName": "jerry kurata",
      "photoUrl": "https://lh3.googleusercontent.com/a-/AOh14GgDrlccxI84_FsH18rCGaMpIHdbLPfi4DgdhCbSxQ=s64",
      "userId": "08438564134228659223"
     },
     "user_tz": 420
    },
    "id": "ByuQETn2dKDL",
    "outputId": "c94a8a5f-f4c4-4522-e2c8-b4172f0f1373"
   },
   "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>num_preg</th>\n",
       "      <th>glucose_conc</th>\n",
       "      <th>diastolic_bp</th>\n",
       "      <th>thickness</th>\n",
       "      <th>insulin</th>\n",
       "      <th>bmi</th>\n",
       "      <th>diab_pred</th>\n",
       "      <th>age</th>\n",
       "      <th>diabetes</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>6</td>\n",
       "      <td>148</td>\n",
       "      <td>72</td>\n",
       "      <td>35</td>\n",
       "      <td>0</td>\n",
       "      <td>33.6</td>\n",
       "      <td>0.627</td>\n",
       "      <td>50</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>1</td>\n",
       "      <td>85</td>\n",
       "      <td>66</td>\n",
       "      <td>29</td>\n",
       "      <td>0</td>\n",
       "      <td>26.6</td>\n",
       "      <td>0.351</td>\n",
       "      <td>31</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>8</td>\n",
       "      <td>183</td>\n",
       "      <td>64</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>23.3</td>\n",
       "      <td>0.672</td>\n",
       "      <td>32</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>1</td>\n",
       "      <td>89</td>\n",
       "      <td>66</td>\n",
       "      <td>23</td>\n",
       "      <td>94</td>\n",
       "      <td>28.1</td>\n",
       "      <td>0.167</td>\n",
       "      <td>21</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>0</td>\n",
       "      <td>137</td>\n",
       "      <td>40</td>\n",
       "      <td>35</td>\n",
       "      <td>168</td>\n",
       "      <td>43.1</td>\n",
       "      <td>2.288</td>\n",
       "      <td>33</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   num_preg  glucose_conc  diastolic_bp  thickness  insulin   bmi  diab_pred  \\\n",
       "0         6           148            72         35        0  33.6      0.627   \n",
       "1         1            85            66         29        0  26.6      0.351   \n",
       "2         8           183            64          0        0  23.3      0.672   \n",
       "3         1            89            66         23       94  28.1      0.167   \n",
       "4         0           137            40         35      168  43.1      2.288   \n",
       "\n",
       "   age  diabetes  \n",
       "0   50         1  \n",
       "1   31         0  \n",
       "2   32         1  \n",
       "3   21         0  \n",
       "4   33         1  "
      ]
     },
     "execution_count": 118,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.head()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "q8XvhTCMdKDL"
   },
   "source": [
    "Are these 0 values possible?\n",
    "\n",
    "How many rows have have unexpected 0 values?"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 119,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/"
    },
    "executionInfo": {
     "elapsed": 8769,
     "status": "ok",
     "timestamp": 1618406191553,
     "user": {
      "displayName": "jerry kurata",
      "photoUrl": "https://lh3.googleusercontent.com/a-/AOh14GgDrlccxI84_FsH18rCGaMpIHdbLPfi4DgdhCbSxQ=s64",
      "userId": "08438564134228659223"
     },
     "user_tz": 420
    },
    "id": "AHPhLI0EdKDL",
    "outputId": "317768d6-7629-4cd2-a317-fe541079fc26"
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "# rows in dataframe 768\n",
      "# rows missing glucose_conc: 5\n",
      "# rows missing diastolic_bp: 35\n",
      "# rows missing thickness: 227\n",
      "# rows missing insulin: 374\n",
      "# rows missing bmi: 11\n",
      "# rows missing diab_pred: 0\n",
      "# rows missing age: 0\n"
     ]
    }
   ],
   "source": [
    "print(\"# rows in dataframe {0}\".format(len(df)))\n",
    "print(\"# rows missing glucose_conc: {0}\".format(len(df.loc[df['glucose_conc'] == 0])))\n",
    "print(\"# rows missing diastolic_bp: {0}\".format(len(df.loc[df['diastolic_bp'] == 0])))\n",
    "print(\"# rows missing thickness: {0}\".format(len(df.loc[df['thickness'] == 0])))\n",
    "print(\"# rows missing insulin: {0}\".format(len(df.loc[df['insulin'] == 0])))\n",
    "print(\"# rows missing bmi: {0}\".format(len(df.loc[df['bmi'] == 0])))\n",
    "print(\"# rows missing diab_pred: {0}\".format(len(df.loc[df['diab_pred'] == 0])))\n",
    "print(\"# rows missing age: {0}\".format(len(df.loc[df['age'] == 0])))"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "WExfoDqBdKDL"
   },
   "source": [
    "#### Impute with the mean"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 120,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/"
    },
    "executionInfo": {
     "elapsed": 8765,
     "status": "ok",
     "timestamp": 1618406191553,
     "user": {
      "displayName": "jerry kurata",
      "photoUrl": "https://lh3.googleusercontent.com/a-/AOh14GgDrlccxI84_FsH18rCGaMpIHdbLPfi4DgdhCbSxQ=s64",
      "userId": "08438564134228659223"
     },
     "user_tz": 420
    },
    "id": "oO5vMgq4dKDM",
    "outputId": "38e5e43b-2e29-49e8-c320-7bdf3a100de4"
   },
   "outputs": [],
   "source": [
    "# NEED CALLOUT MENTION CHANGE TO SIMPLEIMPUTER\n",
    "from sklearn.impute import SimpleImputer\n",
    "\n",
    "#Impute with mean all 0 readings\n",
    "fill_0 = SimpleImputer(missing_values=0, strategy=\"mean\")\n",
    "\n",
    "# Notice the missing_values=0 will be replaced by mean.  However, the num_preg can have a value of 0.\n",
    "# To prevent replacing the 0 num_preg with the mean we need to skip imputing the 'num_preg' column\n",
    "cols_not_num_preg = X_train.columns.difference(['num_preg']) # all columns but the num_preg column\n",
    "pd.options.mode.chained_assignment = None  # Supress warning message on transformed assignment\n",
    "\n",
    "# impute the training data\n",
    "X_train[cols_not_num_preg] = fill_0.fit_transform(X_train[cols_not_num_preg])\n",
    "\n",
    "# impute the test data\n",
    "X_test[cols_not_num_preg] = fill_0.transform(X_test[cols_not_num_preg])"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "bSVf8ZPadKDM"
   },
   "source": [
    "## Training Initial Algorithm - Naive Bayes"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 121,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/"
    },
    "executionInfo": {
     "elapsed": 9018,
     "status": "ok",
     "timestamp": 1618406191815,
     "user": {
      "displayName": "jerry kurata",
      "photoUrl": "https://lh3.googleusercontent.com/a-/AOh14GgDrlccxI84_FsH18rCGaMpIHdbLPfi4DgdhCbSxQ=s64",
      "userId": "08438564134228659223"
     },
     "user_tz": 420
    },
    "id": "zPqW8uXrdKDM",
    "outputId": "52b2d782-1bb7-49df-d2c4-7cba8600ca4e"
   },
   "outputs": [
    {
     "data": {
      "text/html": [
       "<style>#sk-container-id-7 {color: black;background-color: white;}#sk-container-id-7 pre{padding: 0;}#sk-container-id-7 div.sk-toggleable {background-color: white;}#sk-container-id-7 label.sk-toggleable__label {cursor: pointer;display: block;width: 100%;margin-bottom: 0;padding: 0.3em;box-sizing: border-box;text-align: center;}#sk-container-id-7 label.sk-toggleable__label-arrow:before {content: \"▸\";float: left;margin-right: 0.25em;color: #696969;}#sk-container-id-7 label.sk-toggleable__label-arrow:hover:before {color: black;}#sk-container-id-7 div.sk-estimator:hover label.sk-toggleable__label-arrow:before {color: black;}#sk-container-id-7 div.sk-toggleable__content {max-height: 0;max-width: 0;overflow: hidden;text-align: left;background-color: #f0f8ff;}#sk-container-id-7 div.sk-toggleable__content pre {margin: 0.2em;color: black;border-radius: 0.25em;background-color: #f0f8ff;}#sk-container-id-7 input.sk-toggleable__control:checked~div.sk-toggleable__content {max-height: 200px;max-width: 100%;overflow: auto;}#sk-container-id-7 input.sk-toggleable__control:checked~label.sk-toggleable__label-arrow:before {content: \"▾\";}#sk-container-id-7 div.sk-estimator input.sk-toggleable__control:checked~label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-7 div.sk-label input.sk-toggleable__control:checked~label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-7 input.sk-hidden--visually {border: 0;clip: rect(1px 1px 1px 1px);clip: rect(1px, 1px, 1px, 1px);height: 1px;margin: -1px;overflow: hidden;padding: 0;position: absolute;width: 1px;}#sk-container-id-7 div.sk-estimator {font-family: monospace;background-color: #f0f8ff;border: 1px dotted black;border-radius: 0.25em;box-sizing: border-box;margin-bottom: 0.5em;}#sk-container-id-7 div.sk-estimator:hover {background-color: #d4ebff;}#sk-container-id-7 div.sk-parallel-item::after {content: \"\";width: 100%;border-bottom: 1px solid gray;flex-grow: 1;}#sk-container-id-7 div.sk-label:hover label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-7 div.sk-serial::before {content: \"\";position: absolute;border-left: 1px solid gray;box-sizing: border-box;top: 0;bottom: 0;left: 50%;z-index: 0;}#sk-container-id-7 div.sk-serial {display: flex;flex-direction: column;align-items: center;background-color: white;padding-right: 0.2em;padding-left: 0.2em;position: relative;}#sk-container-id-7 div.sk-item {position: relative;z-index: 1;}#sk-container-id-7 div.sk-parallel {display: flex;align-items: stretch;justify-content: center;background-color: white;position: relative;}#sk-container-id-7 div.sk-item::before, #sk-container-id-7 div.sk-parallel-item::before {content: \"\";position: absolute;border-left: 1px solid gray;box-sizing: border-box;top: 0;bottom: 0;left: 50%;z-index: -1;}#sk-container-id-7 div.sk-parallel-item {display: flex;flex-direction: column;z-index: 1;position: relative;background-color: white;}#sk-container-id-7 div.sk-parallel-item:first-child::after {align-self: flex-end;width: 50%;}#sk-container-id-7 div.sk-parallel-item:last-child::after {align-self: flex-start;width: 50%;}#sk-container-id-7 div.sk-parallel-item:only-child::after {width: 0;}#sk-container-id-7 div.sk-dashed-wrapped {border: 1px dashed gray;margin: 0 0.4em 0.5em 0.4em;box-sizing: border-box;padding-bottom: 0.4em;background-color: white;}#sk-container-id-7 div.sk-label label {font-family: monospace;font-weight: bold;display: inline-block;line-height: 1.2em;}#sk-container-id-7 div.sk-label-container {text-align: center;}#sk-container-id-7 div.sk-container {/* jupyter's `normalize.less` sets `[hidden] { display: none; }` but bootstrap.min.css set `[hidden] { display: none !important; }` so we also need the `!important` here to be able to override the default hidden behavior on the sphinx rendered scikit-learn.org. See: https://github.com/scikit-learn/scikit-learn/issues/21755 */display: inline-block !important;position: relative;}#sk-container-id-7 div.sk-text-repr-fallback {display: none;}</style><div id=\"sk-container-id-7\" class=\"sk-top-container\"><div class=\"sk-text-repr-fallback\"><pre>GaussianNB()</pre><b>In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook. <br />On GitHub, the HTML representation is unable to render, please try loading this page with nbviewer.org.</b></div><div class=\"sk-container\" hidden><div class=\"sk-item\"><div class=\"sk-estimator sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-7\" type=\"checkbox\" checked><label for=\"sk-estimator-id-7\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">GaussianNB</label><div class=\"sk-toggleable__content\"><pre>GaussianNB()</pre></div></div></div></div></div>"
      ],
      "text/plain": [
       "GaussianNB()"
      ]
     },
     "execution_count": 121,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "from sklearn.naive_bayes import GaussianNB\n",
    "\n",
    "# create Gaussian Naive Bayes model object and train it with the data\n",
    "nb_model = GaussianNB()\n",
    "\n",
    "nb_model.fit(X_train, y_train.values.flatten())"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "collapsed": true,
    "id": "mW_sUIecdKDM"
   },
   "source": [
    "### Performance on Training Data"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 122,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/"
    },
    "executionInfo": {
     "elapsed": 9015,
     "status": "ok",
     "timestamp": 1618406191816,
     "user": {
      "displayName": "jerry kurata",
      "photoUrl": "https://lh3.googleusercontent.com/a-/AOh14GgDrlccxI84_FsH18rCGaMpIHdbLPfi4DgdhCbSxQ=s64",
      "userId": "08438564134228659223"
     },
     "user_tz": 420
    },
    "id": "P3lv47OFdKDM",
    "outputId": "f2fa7c66-2c88-472c-a17b-7d21bb6edc41"
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Accuracy: 0.7523\n",
      "\n"
     ]
    }
   ],
   "source": [
    "# predict values using the training data\n",
    "nb_predict_train = nb_model.predict(X_train)\n",
    "\n",
    "# import the performance metrics library\n",
    "from sklearn import metrics\n",
    "\n",
    "# Accuracy\n",
    "print(\"Accuracy: {0:.4f}\".format(metrics.accuracy_score(y_train, nb_predict_train)))\n",
    "print()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "3r_u5z1BdKDN"
   },
   "source": [
    "### Performance on Testing Data"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 123,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/"
    },
    "executionInfo": {
     "elapsed": 9011,
     "status": "ok",
     "timestamp": 1618406191816,
     "user": {
      "displayName": "jerry kurata",
      "photoUrl": "https://lh3.googleusercontent.com/a-/AOh14GgDrlccxI84_FsH18rCGaMpIHdbLPfi4DgdhCbSxQ=s64",
      "userId": "08438564134228659223"
     },
     "user_tz": 420
    },
    "id": "cOlVXpowdKDN",
    "outputId": "05cbf139-cff1-4eb4-a7ef-2a630f39842a"
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "nb_predict_test [0 0 0 0 1 0 0 0 0 1 0 1 1 0 0 0 0 0 1 0 0 0 1 0 1 1 0 0 0 0 1 1 1 1 1 1 1\n",
      " 0 1 0 0 0 0 1 0 1 1 0 0 1 0 1 1 0 0 0 1 0 0 1 1 0 0 0 0 1 0 1 0 1 1 0 0 0\n",
      " 0 1 0 0 0 0 1 0 0 1 0 1 1 0 0 0 0 0 0 0 0 1 0 0 1 0 1 0 1 1 1 0 0 1 0 1 0\n",
      " 1 0 1 0 0 1 0 0 0 0 0 0 0 0 1 0 1 1 1 1 1 0 1 1 0 0 1 1 0 0 0 0 1 0 0 0 0\n",
      " 0 1 0 0 1 0 0 1 0 0 1 0 0 1 0 0 0 1 0 0 1 1 1 0 0 1 1 0 0 1 0 0 1 1 0 1 1\n",
      " 0 0 0 1 1 0 0 1 0 0 0 0 0 0 1 0 0 0 1 1 0 0 0 1 1 0 0 0 0 1 0 1 0 0 1 1 0\n",
      " 0 0 0 0 0 0 0 0 0]\n",
      "y_test      diabetes\n",
      "668         0\n",
      "324         0\n",
      "624         0\n",
      "690         0\n",
      "473         0\n",
      "..        ...\n",
      "619         1\n",
      "198         1\n",
      "538         0\n",
      "329         0\n",
      "302         0\n",
      "\n",
      "[231 rows x 1 columns]\n",
      "Accuracy: 0.7403\n"
     ]
    }
   ],
   "source": [
    "# predict values using the testing data\n",
    "nb_predict_test = nb_model.predict(X_test)\n",
    "\n",
    "from sklearn import metrics\n",
    "\n",
    "# training metrics\n",
    "print(\"nb_predict_test\", nb_predict_test)\n",
    "print (\"y_test\", y_test)\n",
    "print(\"Accuracy: {0:.4f}\".format(metrics.accuracy_score(y_test, nb_predict_test)))\n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "KB12IyQddKDN"
   },
   "source": [
    "#### Metrics"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 124,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/"
    },
    "executionInfo": {
     "elapsed": 9006,
     "status": "ok",
     "timestamp": 1618406191816,
     "user": {
      "displayName": "jerry kurata",
      "photoUrl": "https://lh3.googleusercontent.com/a-/AOh14GgDrlccxI84_FsH18rCGaMpIHdbLPfi4DgdhCbSxQ=s64",
      "userId": "08438564134228659223"
     },
     "user_tz": 420
    },
    "id": "J7A1VTTmdKDN",
    "outputId": "cfcddd27-81f7-4d56-a4fb-a0aab50380ab"
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Confusion Matrix\n",
      "[[119  32]\n",
      " [ 28  52]]\n",
      "\n",
      "Classification Report\n",
      "              precision    recall  f1-score   support\n",
      "\n",
      "           0       0.81      0.79      0.80       151\n",
      "           1       0.62      0.65      0.63        80\n",
      "\n",
      "    accuracy                           0.74       231\n",
      "   macro avg       0.71      0.72      0.72       231\n",
      "weighted avg       0.74      0.74      0.74       231\n",
      "\n"
     ]
    }
   ],
   "source": [
    "print(\"Confusion Matrix\")\n",
    "print(\"{0}\".format(metrics.confusion_matrix(y_test, nb_predict_test)))\n",
    "print(\"\")\n",
    "\n",
    "print(\"Classification Report\")\n",
    "print(metrics.classification_report(y_test, nb_predict_test))\n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "ZFjBaN7YdKDN"
   },
   "source": [
    "## Random Forest"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 125,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/"
    },
    "executionInfo": {
     "elapsed": 9003,
     "status": "ok",
     "timestamp": 1618406191817,
     "user": {
      "displayName": "jerry kurata",
      "photoUrl": "https://lh3.googleusercontent.com/a-/AOh14GgDrlccxI84_FsH18rCGaMpIHdbLPfi4DgdhCbSxQ=s64",
      "userId": "08438564134228659223"
     },
     "user_tz": 420
    },
    "id": "H7IcJPwVdKDN",
    "outputId": "84b72225-cd91-4498-851b-4b29d6a3b1bf"
   },
   "outputs": [
    {
     "data": {
      "text/html": [
       "<style>#sk-container-id-8 {color: black;background-color: white;}#sk-container-id-8 pre{padding: 0;}#sk-container-id-8 div.sk-toggleable {background-color: white;}#sk-container-id-8 label.sk-toggleable__label {cursor: pointer;display: block;width: 100%;margin-bottom: 0;padding: 0.3em;box-sizing: border-box;text-align: center;}#sk-container-id-8 label.sk-toggleable__label-arrow:before {content: \"▸\";float: left;margin-right: 0.25em;color: #696969;}#sk-container-id-8 label.sk-toggleable__label-arrow:hover:before {color: black;}#sk-container-id-8 div.sk-estimator:hover label.sk-toggleable__label-arrow:before {color: black;}#sk-container-id-8 div.sk-toggleable__content {max-height: 0;max-width: 0;overflow: hidden;text-align: left;background-color: #f0f8ff;}#sk-container-id-8 div.sk-toggleable__content pre {margin: 0.2em;color: black;border-radius: 0.25em;background-color: #f0f8ff;}#sk-container-id-8 input.sk-toggleable__control:checked~div.sk-toggleable__content {max-height: 200px;max-width: 100%;overflow: auto;}#sk-container-id-8 input.sk-toggleable__control:checked~label.sk-toggleable__label-arrow:before {content: \"▾\";}#sk-container-id-8 div.sk-estimator input.sk-toggleable__control:checked~label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-8 div.sk-label input.sk-toggleable__control:checked~label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-8 input.sk-hidden--visually {border: 0;clip: rect(1px 1px 1px 1px);clip: rect(1px, 1px, 1px, 1px);height: 1px;margin: -1px;overflow: hidden;padding: 0;position: absolute;width: 1px;}#sk-container-id-8 div.sk-estimator {font-family: monospace;background-color: #f0f8ff;border: 1px dotted black;border-radius: 0.25em;box-sizing: border-box;margin-bottom: 0.5em;}#sk-container-id-8 div.sk-estimator:hover {background-color: #d4ebff;}#sk-container-id-8 div.sk-parallel-item::after {content: \"\";width: 100%;border-bottom: 1px solid gray;flex-grow: 1;}#sk-container-id-8 div.sk-label:hover label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-8 div.sk-serial::before {content: \"\";position: absolute;border-left: 1px solid gray;box-sizing: border-box;top: 0;bottom: 0;left: 50%;z-index: 0;}#sk-container-id-8 div.sk-serial {display: flex;flex-direction: column;align-items: center;background-color: white;padding-right: 0.2em;padding-left: 0.2em;position: relative;}#sk-container-id-8 div.sk-item {position: relative;z-index: 1;}#sk-container-id-8 div.sk-parallel {display: flex;align-items: stretch;justify-content: center;background-color: white;position: relative;}#sk-container-id-8 div.sk-item::before, #sk-container-id-8 div.sk-parallel-item::before {content: \"\";position: absolute;border-left: 1px solid gray;box-sizing: border-box;top: 0;bottom: 0;left: 50%;z-index: -1;}#sk-container-id-8 div.sk-parallel-item {display: flex;flex-direction: column;z-index: 1;position: relative;background-color: white;}#sk-container-id-8 div.sk-parallel-item:first-child::after {align-self: flex-end;width: 50%;}#sk-container-id-8 div.sk-parallel-item:last-child::after {align-self: flex-start;width: 50%;}#sk-container-id-8 div.sk-parallel-item:only-child::after {width: 0;}#sk-container-id-8 div.sk-dashed-wrapped {border: 1px dashed gray;margin: 0 0.4em 0.5em 0.4em;box-sizing: border-box;padding-bottom: 0.4em;background-color: white;}#sk-container-id-8 div.sk-label label {font-family: monospace;font-weight: bold;display: inline-block;line-height: 1.2em;}#sk-container-id-8 div.sk-label-container {text-align: center;}#sk-container-id-8 div.sk-container {/* jupyter's `normalize.less` sets `[hidden] { display: none; }` but bootstrap.min.css set `[hidden] { display: none !important; }` so we also need the `!important` here to be able to override the default hidden behavior on the sphinx rendered scikit-learn.org. See: https://github.com/scikit-learn/scikit-learn/issues/21755 */display: inline-block !important;position: relative;}#sk-container-id-8 div.sk-text-repr-fallback {display: none;}</style><div id=\"sk-container-id-8\" class=\"sk-top-container\"><div class=\"sk-text-repr-fallback\"><pre>RandomForestClassifier(n_estimators=10, random_state=42)</pre><b>In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook. <br />On GitHub, the HTML representation is unable to render, please try loading this page with nbviewer.org.</b></div><div class=\"sk-container\" hidden><div class=\"sk-item\"><div class=\"sk-estimator sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-8\" type=\"checkbox\" checked><label for=\"sk-estimator-id-8\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">RandomForestClassifier</label><div class=\"sk-toggleable__content\"><pre>RandomForestClassifier(n_estimators=10, random_state=42)</pre></div></div></div></div></div>"
      ],
      "text/plain": [
       "RandomForestClassifier(n_estimators=10, random_state=42)"
      ]
     },
     "execution_count": 125,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "from sklearn.ensemble import RandomForestClassifier\n",
    "rf_model = RandomForestClassifier(random_state=42, n_estimators=10)      # Create random forest object\n",
    "rf_model.fit(X_train, y_train.values.flatten()) "
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "m8EtmdOsdKDO"
   },
   "source": [
    "### Predict Training Data"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 126,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/"
    },
    "executionInfo": {
     "elapsed": 8999,
     "status": "ok",
     "timestamp": 1618406191817,
     "user": {
      "displayName": "jerry kurata",
      "photoUrl": "https://lh3.googleusercontent.com/a-/AOh14GgDrlccxI84_FsH18rCGaMpIHdbLPfi4DgdhCbSxQ=s64",
      "userId": "08438564134228659223"
     },
     "user_tz": 420
    },
    "id": "iQioMSHQdKDO",
    "outputId": "d35e9063-cfcf-4757-8f87-55a882bd9108"
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Accuracy: 0.9851\n"
     ]
    }
   ],
   "source": [
    "rf_predict_train = rf_model.predict(X_train)\n",
    "# training metrics\n",
    "print(\"Accuracy: {0:.4f}\".format(metrics.accuracy_score(y_train, rf_predict_train)))"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "D-3wPsP4dKDO"
   },
   "source": [
    "### Predict Test Data"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 127,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/"
    },
    "executionInfo": {
     "elapsed": 8995,
     "status": "ok",
     "timestamp": 1618406191817,
     "user": {
      "displayName": "jerry kurata",
      "photoUrl": "https://lh3.googleusercontent.com/a-/AOh14GgDrlccxI84_FsH18rCGaMpIHdbLPfi4DgdhCbSxQ=s64",
      "userId": "08438564134228659223"
     },
     "user_tz": 420
    },
    "id": "cZEjcPTadKDO",
    "outputId": "96cf74af-82f3-42f6-fdf3-7d243a2e3a43"
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Accuracy: 0.7446\n"
     ]
    }
   ],
   "source": [
    "rf_predict_test = rf_model.predict(X_test)\n",
    "\n",
    "# training metrics\n",
    "print(\"Accuracy: {0:.4f}\".format(metrics.accuracy_score(y_test, rf_predict_test)))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 128,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/"
    },
    "executionInfo": {
     "elapsed": 8991,
     "status": "ok",
     "timestamp": 1618406191818,
     "user": {
      "displayName": "jerry kurata",
      "photoUrl": "https://lh3.googleusercontent.com/a-/AOh14GgDrlccxI84_FsH18rCGaMpIHdbLPfi4DgdhCbSxQ=s64",
      "userId": "08438564134228659223"
     },
     "user_tz": 420
    },
    "id": "5qkzbLI6dKDO",
    "outputId": "057728a2-148d-49b4-cb99-f0eac0583ded"
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "[[125  26]\n",
      " [ 33  47]]\n",
      "\n",
      "Classification Report\n",
      "              precision    recall  f1-score   support\n",
      "\n",
      "           0       0.79      0.83      0.81       151\n",
      "           1       0.64      0.59      0.61        80\n",
      "\n",
      "    accuracy                           0.74       231\n",
      "   macro avg       0.72      0.71      0.71       231\n",
      "weighted avg       0.74      0.74      0.74       231\n",
      "\n"
     ]
    }
   ],
   "source": [
    "print(metrics.confusion_matrix(y_test, rf_predict_test) )\n",
    "print(\"\")\n",
    "print(\"Classification Report\")\n",
    "print(metrics.classification_report(y_test, rf_predict_test))"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "BRmrU8NbdKDO"
   },
   "source": [
    "## Logistic Regression"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 129,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/"
    },
    "executionInfo": {
     "elapsed": 8987,
     "status": "ok",
     "timestamp": 1618406191818,
     "user": {
      "displayName": "jerry kurata",
      "photoUrl": "https://lh3.googleusercontent.com/a-/AOh14GgDrlccxI84_FsH18rCGaMpIHdbLPfi4DgdhCbSxQ=s64",
      "userId": "08438564134228659223"
     },
     "user_tz": 420
    },
    "id": "kTz_y-M6dKDO",
    "outputId": "86e7866a-7a73-4bae-ba53-f3624ce035ed"
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Accuracy: 0.7576\n",
      "[[130  21]\n",
      " [ 35  45]]\n",
      "\n",
      "Classification Report\n",
      "              precision    recall  f1-score   support\n",
      "\n",
      "           0       0.79      0.86      0.82       151\n",
      "           1       0.68      0.56      0.62        80\n",
      "\n",
      "    accuracy                           0.76       231\n",
      "   macro avg       0.73      0.71      0.72       231\n",
      "weighted avg       0.75      0.76      0.75       231\n",
      "\n"
     ]
    }
   ],
   "source": [
    "from sklearn.linear_model import LogisticRegression\n",
    "\n",
    "lr_model =LogisticRegression(C=0.7, random_state=42, solver='liblinear', max_iter=10000)\n",
    "lr_model.fit(X_train, y_train.values.flatten()) #.ravel())\n",
    "lr_predict_test = lr_model.predict(X_test)\n",
    "\n",
    "# training metrics\n",
    "print(\"Accuracy: {0:.4f}\".format(metrics.accuracy_score(y_test, lr_predict_test)))\n",
    "print(metrics.confusion_matrix(y_test, lr_predict_test) )\n",
    "print(\"\")\n",
    "print(\"Classification Report\")\n",
    "print(metrics.classification_report(y_test, lr_predict_test))"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "zA11-w0cdKDP"
   },
   "source": [
    "Setting regularization parameter"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 130,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 313
    },
    "executionInfo": {
     "elapsed": 9643,
     "status": "ok",
     "timestamp": 1618406192478,
     "user": {
      "displayName": "jerry kurata",
      "photoUrl": "https://lh3.googleusercontent.com/a-/AOh14GgDrlccxI84_FsH18rCGaMpIHdbLPfi4DgdhCbSxQ=s64",
      "userId": "08438564134228659223"
     },
     "user_tz": 420
    },
    "id": "YVyEerBgdKDP",
    "outputId": "ff322c72-a9fd-4dec-a0ba-d38b8f14b485"
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "1st max value of 0.613 occured at C=2.900\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "Text(0, 0.5, 'recall score')"
      ]
     },
     "execution_count": 130,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "C_start = 0.1\n",
    "C_end = 5\n",
    "C_inc = 0.1\n",
    "\n",
    "C_values, recall_scores = [], []\n",
    "\n",
    "C_val = C_start\n",
    "best_recall_score = 0\n",
    "while (C_val < C_end):\n",
    "    C_values.append(C_val)\n",
    "    lr_model_loop = LogisticRegression(C=C_val, random_state=42, solver='liblinear')\n",
    "    lr_model_loop.fit(X_train, y_train.values.flatten()) #.ravel())\n",
    "    lr_predict_loop_test = lr_model_loop.predict(X_test)\n",
    "    recall_score = metrics.recall_score(y_test, lr_predict_loop_test)\n",
    "    recall_scores.append(recall_score)\n",
    "    if (recall_score > best_recall_score):\n",
    "        best_recall_score = recall_score\n",
    "        best_lr_predict_test = lr_predict_loop_test\n",
    "        \n",
    "    C_val = C_val + C_inc\n",
    "\n",
    "best_score_C_val = C_values[recall_scores.index(best_recall_score)]\n",
    "print(\"1st max value of {0:.3f} occured at C={1:.3f}\".format(best_recall_score, best_score_C_val))\n",
    "\n",
    "%matplotlib inline \n",
    "plt.plot(C_values, recall_scores, \"-\")\n",
    "plt.xlabel(\"C value\")\n",
    "plt.ylabel(\"recall score\")\n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "Zu6tzIRBdKDP"
   },
   "source": [
    "### Logisitic regression with class_weight='balanced'"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 131,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 315
    },
    "executionInfo": {
     "elapsed": 10837,
     "status": "ok",
     "timestamp": 1618406193678,
     "user": {
      "displayName": "jerry kurata",
      "photoUrl": "https://lh3.googleusercontent.com/a-/AOh14GgDrlccxI84_FsH18rCGaMpIHdbLPfi4DgdhCbSxQ=s64",
      "userId": "08438564134228659223"
     },
     "user_tz": 420
    },
    "id": "vOiW3X4NdKDP",
    "outputId": "6423d552-8491-4e10-cc8a-85d62e05f104"
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "1st max value of 0.738 occured at C=0.200\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "Text(0, 0.5, 'recall score')"
      ]
     },
     "execution_count": 131,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "C_start = 0.1\n",
    "C_end = 5\n",
    "C_inc = 0.1\n",
    "\n",
    "C_values, recall_scores = [], []\n",
    "\n",
    "C_val = C_start\n",
    "best_recall_score = 0\n",
    "while (C_val < C_end):\n",
    "    C_values.append(C_val)\n",
    "    lr_model_loop = LogisticRegression(C=C_val, class_weight=\"balanced\", random_state=42, solver='liblinear', max_iter=10000)\n",
    "    lr_model_loop.fit(X_train, y_train.values.flatten()) \n",
    "    lr_predict_loop_test = lr_model_loop.predict(X_test)\n",
    "    recall_score = metrics.recall_score(y_test, lr_predict_loop_test)\n",
    "    recall_scores.append(recall_score)\n",
    "    if (recall_score > best_recall_score):\n",
    "        best_recall_score = recall_score\n",
    "        best_lr_predict_test = lr_predict_loop_test\n",
    "        \n",
    "    C_val = C_val + C_inc\n",
    "\n",
    "best_score_C_val = C_values[recall_scores.index(best_recall_score)]\n",
    "print(\"1st max value of {0:.3f} occured at C={1:.3f}\".format(best_recall_score, best_score_C_val))\n",
    "\n",
    "%matplotlib inline \n",
    "plt.plot(C_values, recall_scores, \"-\")\n",
    "plt.xlabel(\"C value\")\n",
    "plt.ylabel(\"recall score\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 132,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/"
    },
    "executionInfo": {
     "elapsed": 10833,
     "status": "ok",
     "timestamp": 1618406193679,
     "user": {
      "displayName": "jerry kurata",
      "photoUrl": "https://lh3.googleusercontent.com/a-/AOh14GgDrlccxI84_FsH18rCGaMpIHdbLPfi4DgdhCbSxQ=s64",
      "userId": "08438564134228659223"
     },
     "user_tz": 420
    },
    "id": "nccZCatydKDP",
    "outputId": "11d81fab-245d-433b-ce01-9cadd9a14e06"
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Accuracy: 0.7186\n",
      "[[107  44]\n",
      " [ 21  59]]\n",
      "\n",
      "Classification Report\n",
      "              precision    recall  f1-score   support\n",
      "\n",
      "           0       0.84      0.71      0.77       151\n",
      "           1       0.57      0.74      0.64        80\n",
      "\n",
      "    accuracy                           0.72       231\n",
      "   macro avg       0.70      0.72      0.71       231\n",
      "weighted avg       0.74      0.72      0.72       231\n",
      "\n",
      "0.7375\n"
     ]
    }
   ],
   "source": [
    "from sklearn.linear_model import LogisticRegression\n",
    "lr_model =LogisticRegression( class_weight=\"balanced\", C=best_score_C_val, random_state=42, solver='liblinear')\n",
    "lr_model.fit(X_train, y_train.values.flatten())\n",
    "lr_predict_test = lr_model.predict(X_test)\n",
    "\n",
    "# training metrics\n",
    "print(\"Accuracy: {0:.4f}\".format(metrics.accuracy_score(y_test, lr_predict_test)))\n",
    "print(metrics.confusion_matrix(y_test, lr_predict_test) )\n",
    "print(\"\")\n",
    "print(\"Classification Report\")\n",
    "print(metrics.classification_report(y_test, lr_predict_test))\n",
    "print(metrics.recall_score(y_test, lr_predict_test))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "id": "1Jbv5fM5dKDQ"
   },
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "6u7QlZvJdKDQ"
   },
   "source": [
    "### LogisticRegressionCV"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 133,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/"
    },
    "executionInfo": {
     "elapsed": 12540,
     "status": "ok",
     "timestamp": 1618406195392,
     "user": {
      "displayName": "jerry kurata",
      "photoUrl": "https://lh3.googleusercontent.com/a-/AOh14GgDrlccxI84_FsH18rCGaMpIHdbLPfi4DgdhCbSxQ=s64",
      "userId": "08438564134228659223"
     },
     "user_tz": 420
    },
    "id": "ivFz9k9idKDQ",
    "outputId": "f3217bee-0b10-492c-e0b8-e20d407a6600"
   },
   "outputs": [
    {
     "data": {
      "text/html": [
       "<style>#sk-container-id-9 {color: black;background-color: white;}#sk-container-id-9 pre{padding: 0;}#sk-container-id-9 div.sk-toggleable {background-color: white;}#sk-container-id-9 label.sk-toggleable__label {cursor: pointer;display: block;width: 100%;margin-bottom: 0;padding: 0.3em;box-sizing: border-box;text-align: center;}#sk-container-id-9 label.sk-toggleable__label-arrow:before {content: \"▸\";float: left;margin-right: 0.25em;color: #696969;}#sk-container-id-9 label.sk-toggleable__label-arrow:hover:before {color: black;}#sk-container-id-9 div.sk-estimator:hover label.sk-toggleable__label-arrow:before {color: black;}#sk-container-id-9 div.sk-toggleable__content {max-height: 0;max-width: 0;overflow: hidden;text-align: left;background-color: #f0f8ff;}#sk-container-id-9 div.sk-toggleable__content pre {margin: 0.2em;color: black;border-radius: 0.25em;background-color: #f0f8ff;}#sk-container-id-9 input.sk-toggleable__control:checked~div.sk-toggleable__content {max-height: 200px;max-width: 100%;overflow: auto;}#sk-container-id-9 input.sk-toggleable__control:checked~label.sk-toggleable__label-arrow:before {content: \"▾\";}#sk-container-id-9 div.sk-estimator input.sk-toggleable__control:checked~label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-9 div.sk-label input.sk-toggleable__control:checked~label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-9 input.sk-hidden--visually {border: 0;clip: rect(1px 1px 1px 1px);clip: rect(1px, 1px, 1px, 1px);height: 1px;margin: -1px;overflow: hidden;padding: 0;position: absolute;width: 1px;}#sk-container-id-9 div.sk-estimator {font-family: monospace;background-color: #f0f8ff;border: 1px dotted black;border-radius: 0.25em;box-sizing: border-box;margin-bottom: 0.5em;}#sk-container-id-9 div.sk-estimator:hover {background-color: #d4ebff;}#sk-container-id-9 div.sk-parallel-item::after {content: \"\";width: 100%;border-bottom: 1px solid gray;flex-grow: 1;}#sk-container-id-9 div.sk-label:hover label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-9 div.sk-serial::before {content: \"\";position: absolute;border-left: 1px solid gray;box-sizing: border-box;top: 0;bottom: 0;left: 50%;z-index: 0;}#sk-container-id-9 div.sk-serial {display: flex;flex-direction: column;align-items: center;background-color: white;padding-right: 0.2em;padding-left: 0.2em;position: relative;}#sk-container-id-9 div.sk-item {position: relative;z-index: 1;}#sk-container-id-9 div.sk-parallel {display: flex;align-items: stretch;justify-content: center;background-color: white;position: relative;}#sk-container-id-9 div.sk-item::before, #sk-container-id-9 div.sk-parallel-item::before {content: \"\";position: absolute;border-left: 1px solid gray;box-sizing: border-box;top: 0;bottom: 0;left: 50%;z-index: -1;}#sk-container-id-9 div.sk-parallel-item {display: flex;flex-direction: column;z-index: 1;position: relative;background-color: white;}#sk-container-id-9 div.sk-parallel-item:first-child::after {align-self: flex-end;width: 50%;}#sk-container-id-9 div.sk-parallel-item:last-child::after {align-self: flex-start;width: 50%;}#sk-container-id-9 div.sk-parallel-item:only-child::after {width: 0;}#sk-container-id-9 div.sk-dashed-wrapped {border: 1px dashed gray;margin: 0 0.4em 0.5em 0.4em;box-sizing: border-box;padding-bottom: 0.4em;background-color: white;}#sk-container-id-9 div.sk-label label {font-family: monospace;font-weight: bold;display: inline-block;line-height: 1.2em;}#sk-container-id-9 div.sk-label-container {text-align: center;}#sk-container-id-9 div.sk-container {/* jupyter's `normalize.less` sets `[hidden] { display: none; }` but bootstrap.min.css set `[hidden] { display: none !important; }` so we also need the `!important` here to be able to override the default hidden behavior on the sphinx rendered scikit-learn.org. See: https://github.com/scikit-learn/scikit-learn/issues/21755 */display: inline-block !important;position: relative;}#sk-container-id-9 div.sk-text-repr-fallback {display: none;}</style><div id=\"sk-container-id-9\" class=\"sk-top-container\"><div class=\"sk-text-repr-fallback\"><pre>LogisticRegressionCV(Cs=3, class_weight=&#x27;balanced&#x27;, cv=10, max_iter=500,\n",
       "                     n_jobs=-1, random_state=42, refit=False)</pre><b>In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook. <br />On GitHub, the HTML representation is unable to render, please try loading this page with nbviewer.org.</b></div><div class=\"sk-container\" hidden><div class=\"sk-item\"><div class=\"sk-estimator sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-9\" type=\"checkbox\" checked><label for=\"sk-estimator-id-9\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">LogisticRegressionCV</label><div class=\"sk-toggleable__content\"><pre>LogisticRegressionCV(Cs=3, class_weight=&#x27;balanced&#x27;, cv=10, max_iter=500,\n",
       "                     n_jobs=-1, random_state=42, refit=False)</pre></div></div></div></div></div>"
      ],
      "text/plain": [
       "LogisticRegressionCV(Cs=3, class_weight='balanced', cv=10, max_iter=500,\n",
       "                     n_jobs=-1, random_state=42, refit=False)"
      ]
     },
     "execution_count": 133,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "from sklearn.linear_model import LogisticRegressionCV\n",
    "lr_cv_model = LogisticRegressionCV(n_jobs=-1, random_state=42, Cs=3, cv=10, refit=False, class_weight=\"balanced\", max_iter=500)  # set number of jobs to -1 which uses all cores to parallelize\n",
    "lr_cv_model.fit(X_train, y_train.values.flatten())"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "oZs9VwW-dKDQ"
   },
   "source": [
    "### Predict on Test data"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 134,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/"
    },
    "executionInfo": {
     "elapsed": 12536,
     "status": "ok",
     "timestamp": 1618406195392,
     "user": {
      "displayName": "jerry kurata",
      "photoUrl": "https://lh3.googleusercontent.com/a-/AOh14GgDrlccxI84_FsH18rCGaMpIHdbLPfi4DgdhCbSxQ=s64",
      "userId": "08438564134228659223"
     },
     "user_tz": 420
    },
    "id": "ngFNHCw6dKDQ",
    "outputId": "99abd17c-db96-432f-8d63-d65d848bdfb5"
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Accuracy: 0.6970\n",
      "[[109  42]\n",
      " [ 28  52]]\n",
      "\n",
      "Classification Report\n",
      "              precision    recall  f1-score   support\n",
      "\n",
      "           0       0.80      0.72      0.76       151\n",
      "           1       0.55      0.65      0.60        80\n",
      "\n",
      "    accuracy                           0.70       231\n",
      "   macro avg       0.67      0.69      0.68       231\n",
      "weighted avg       0.71      0.70      0.70       231\n",
      "\n"
     ]
    }
   ],
   "source": [
    "lr_cv_predict_test = lr_cv_model.predict(X_test)\n",
    "\n",
    "# training metrics\n",
    "print(\"Accuracy: {0:.4f}\".format(metrics.accuracy_score(y_test, lr_cv_predict_test)))\n",
    "print(metrics.confusion_matrix(y_test, lr_cv_predict_test) )\n",
    "print(\"\")\n",
    "print(\"Classification Report\")\n",
    "print(metrics.classification_report(y_test, lr_cv_predict_test))"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "PXvOfWuDdKDQ"
   },
   "source": [
    "# Using your trained Model"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "UnL1eEnrdKDQ"
   },
   "source": [
    "## Save trained model to file"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 135,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 353
    },
    "executionInfo": {
     "elapsed": 12862,
     "status": "error",
     "timestamp": 1618406195722,
     "user": {
      "displayName": "jerry kurata",
      "photoUrl": "https://lh3.googleusercontent.com/a-/AOh14GgDrlccxI84_FsH18rCGaMpIHdbLPfi4DgdhCbSxQ=s64",
      "userId": "08438564134228659223"
     },
     "user_tz": 420
    },
    "id": "n7BfOt89dKDR",
    "outputId": "04136931-8f63-45ed-b7d4-12c8f2c92a43"
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "['./data/pima-trained-model.pkl']"
      ]
     },
     "execution_count": 135,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "import joblib\n",
    "\n",
    "joblib.dump(lr_cv_model, \"./data/pima-trained-model.pkl\")\n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "ctySbPMadKDR"
   },
   "source": [
    "## Load trained model from file"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 136,
   "metadata": {
    "id": "jr90ZHNzdKDR"
   },
   "outputs": [],
   "source": [
    "lr_cv_model = joblib.load(\"./data/pima-trained-model.pkl\")"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "collapsed": true,
    "id": "lP9T-6cAdKDR"
   },
   "source": [
    "## Test Prediction on data\n",
    "\n",
    "Once the model is loaded we can use it to predict on some data.  In this case the data file contains a few rows from the original Pima CSV file.\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 137,
   "metadata": {
    "id": "n8Y6UzVHdKDR"
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "(4, 10)\n"
     ]
    }
   ],
   "source": [
    "# get data from truncated pima data file\n",
    "df_predict = pd.read_csv(\"./data/pima-data-trunc.csv\")\n",
    "print(df_predict.shape)\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 138,
   "metadata": {
    "id": "tLK8RG9AdKDR"
   },
   "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>num_preg</th>\n",
       "      <th>glucose_conc</th>\n",
       "      <th>diastolic_bp</th>\n",
       "      <th>thickness</th>\n",
       "      <th>insulin</th>\n",
       "      <th>bmi</th>\n",
       "      <th>diab_pred</th>\n",
       "      <th>age</th>\n",
       "      <th>skin</th>\n",
       "      <th>diabetes</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>1</td>\n",
       "      <td>89</td>\n",
       "      <td>66</td>\n",
       "      <td>23</td>\n",
       "      <td>94</td>\n",
       "      <td>28.1</td>\n",
       "      <td>0.167</td>\n",
       "      <td>21</td>\n",
       "      <td>0.9062</td>\n",
       "      <td>False</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>2</td>\n",
       "      <td>197</td>\n",
       "      <td>70</td>\n",
       "      <td>45</td>\n",
       "      <td>543</td>\n",
       "      <td>30.5</td>\n",
       "      <td>0.158</td>\n",
       "      <td>53</td>\n",
       "      <td>1.7730</td>\n",
       "      <td>True</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>7</td>\n",
       "      <td>100</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>30.0</td>\n",
       "      <td>0.484</td>\n",
       "      <td>32</td>\n",
       "      <td>0.0000</td>\n",
       "      <td>True</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>1</td>\n",
       "      <td>103</td>\n",
       "      <td>30</td>\n",
       "      <td>38</td>\n",
       "      <td>83</td>\n",
       "      <td>43.3</td>\n",
       "      <td>0.183</td>\n",
       "      <td>33</td>\n",
       "      <td>1.4972</td>\n",
       "      <td>False</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   num_preg  glucose_conc  diastolic_bp  thickness  insulin   bmi  diab_pred  \\\n",
       "0         1            89            66         23       94  28.1      0.167   \n",
       "1         2           197            70         45      543  30.5      0.158   \n",
       "2         7           100             0          0        0  30.0      0.484   \n",
       "3         1           103            30         38       83  43.3      0.183   \n",
       "\n",
       "   age    skin  diabetes  \n",
       "0   21  0.9062     False  \n",
       "1   53  1.7730      True  \n",
       "2   32  0.0000      True  \n",
       "3   33  1.4972     False  "
      ]
     },
     "execution_count": 138,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df_predict"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "HnIsv2T1dKDR"
   },
   "source": [
    "The truncated file contained 4 rows from the original CSV.\n",
    "\n",
    "Data is the same is in same format as the original CSV file's data.  Therefore, just like the original data, we need to transform it before we can make predictions on the data.  \n",
    "\n",
    "Note: If the data had been previously \"cleaned up\" this would not be necessary.\n",
    "\n",
    "We do this by executed the same transformations as we did to the original data\n",
    "\n",
    "Start by dropping the \"skin\" which is the same as thickness, with different units."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 139,
   "metadata": {
    "id": "remgBBUzdKDR"
   },
   "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>num_preg</th>\n",
       "      <th>glucose_conc</th>\n",
       "      <th>diastolic_bp</th>\n",
       "      <th>thickness</th>\n",
       "      <th>insulin</th>\n",
       "      <th>bmi</th>\n",
       "      <th>diab_pred</th>\n",
       "      <th>age</th>\n",
       "      <th>diabetes</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>1</td>\n",
       "      <td>89</td>\n",
       "      <td>66</td>\n",
       "      <td>23</td>\n",
       "      <td>94</td>\n",
       "      <td>28.1</td>\n",
       "      <td>0.167</td>\n",
       "      <td>21</td>\n",
       "      <td>False</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>2</td>\n",
       "      <td>197</td>\n",
       "      <td>70</td>\n",
       "      <td>45</td>\n",
       "      <td>543</td>\n",
       "      <td>30.5</td>\n",
       "      <td>0.158</td>\n",
       "      <td>53</td>\n",
       "      <td>True</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>7</td>\n",
       "      <td>100</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>30.0</td>\n",
       "      <td>0.484</td>\n",
       "      <td>32</td>\n",
       "      <td>True</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>1</td>\n",
       "      <td>103</td>\n",
       "      <td>30</td>\n",
       "      <td>38</td>\n",
       "      <td>83</td>\n",
       "      <td>43.3</td>\n",
       "      <td>0.183</td>\n",
       "      <td>33</td>\n",
       "      <td>False</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   num_preg  glucose_conc  diastolic_bp  thickness  insulin   bmi  diab_pred  \\\n",
       "0         1            89            66         23       94  28.1      0.167   \n",
       "1         2           197            70         45      543  30.5      0.158   \n",
       "2         7           100             0          0        0  30.0      0.484   \n",
       "3         1           103            30         38       83  43.3      0.183   \n",
       "\n",
       "   age  diabetes  \n",
       "0   21     False  \n",
       "1   53      True  \n",
       "2   32      True  \n",
       "3   33     False  "
      ]
     },
     "execution_count": 139,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "del df_predict['skin']\n",
    "df_predict"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "oUlu3aVUdKDS"
   },
   "source": [
    "We need to drop the diabetes column since that is what we are predicting.  \n",
    "Store data without the column with the prefix X as we did with the X_train and X_test to indicate that it contains only the columns we are prediction."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 140,
   "metadata": {
    "id": "5yoCJ5VkdKDS"
   },
   "outputs": [],
   "source": [
    "X_predict = df_predict\n",
    "del X_predict['diabetes']"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "kRrLT_bGdKDS"
   },
   "source": [
    "Data has 0 in places it should not.  \n",
    "\n",
    "Just like test or test datasets we will use imputation to fix this."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 141,
   "metadata": {
    "id": "M9OA64QIdKDS"
   },
   "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>num_preg</th>\n",
       "      <th>glucose_conc</th>\n",
       "      <th>diastolic_bp</th>\n",
       "      <th>thickness</th>\n",
       "      <th>insulin</th>\n",
       "      <th>bmi</th>\n",
       "      <th>diab_pred</th>\n",
       "      <th>age</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>1</td>\n",
       "      <td>89.0</td>\n",
       "      <td>66.000000</td>\n",
       "      <td>23.000000</td>\n",
       "      <td>94.0</td>\n",
       "      <td>28.1</td>\n",
       "      <td>0.167</td>\n",
       "      <td>21.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>2</td>\n",
       "      <td>197.0</td>\n",
       "      <td>70.000000</td>\n",
       "      <td>45.000000</td>\n",
       "      <td>543.0</td>\n",
       "      <td>30.5</td>\n",
       "      <td>0.158</td>\n",
       "      <td>53.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>7</td>\n",
       "      <td>100.0</td>\n",
       "      <td>55.333333</td>\n",
       "      <td>35.333333</td>\n",
       "      <td>240.0</td>\n",
       "      <td>30.0</td>\n",
       "      <td>0.484</td>\n",
       "      <td>32.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>1</td>\n",
       "      <td>103.0</td>\n",
       "      <td>30.000000</td>\n",
       "      <td>38.000000</td>\n",
       "      <td>83.0</td>\n",
       "      <td>43.3</td>\n",
       "      <td>0.183</td>\n",
       "      <td>33.0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   num_preg  glucose_conc  diastolic_bp  thickness  insulin   bmi  diab_pred  \\\n",
       "0         1          89.0     66.000000  23.000000     94.0  28.1      0.167   \n",
       "1         2         197.0     70.000000  45.000000    543.0  30.5      0.158   \n",
       "2         7         100.0     55.333333  35.333333    240.0  30.0      0.484   \n",
       "3         1         103.0     30.000000  38.000000     83.0  43.3      0.183   \n",
       "\n",
       "    age  \n",
       "0  21.0  \n",
       "1  53.0  \n",
       "2  32.0  \n",
       "3  33.0  "
      ]
     },
     "execution_count": 141,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "#Impute with mean all 0 readings\n",
    "from sklearn.impute import SimpleImputer\n",
    "fill_0 = SimpleImputer(missing_values=0, strategy=\"mean\")\n",
    "pd.options.mode.chained_assignment = None\n",
    "X_predict_cols_not_num_preg = X_predict.columns.difference(['num_preg']) # do not impute num_preg column\n",
    "X_predict[X_predict_cols_not_num_preg] = fill_0.fit_transform(X_predict[X_predict_cols_not_num_preg])\n",
    "X_predict"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "Hpo58g9WdKDS"
   },
   "source": [
    "At this point our data is ready to be used for prediction.  "
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "QN1_1tiSdKDS"
   },
   "source": [
    "## Predict diabetes with the prediction data.  Returns 1 if True, 0 if false"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 142,
   "metadata": {
    "id": "YIJo5Z8QdKDS"
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([0, 1, 0, 0], dtype=int64)"
      ]
     },
     "execution_count": 142,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "lr_cv_model.predict(X_predict)"
   ]
  }
 ],
 "metadata": {
  "colab": {
   "collapsed_sections": [],
   "name": "Pima-Prediction-with-reload-with-imputation-transform-fixes.ipynb",
   "provenance": [
    {
     "file_id": "1S3IUgFGkwVKgV0T2xArOV9HGvi9jv6F0",
     "timestamp": 1618406093346
    }
   ]
  },
  "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": "3.10.4"
  },
  "vscode": {
   "interpreter": {
    "hash": "086cb8ea0e00268231bc99a7e331b6f8c4b5c043b1aca225d3975cc839bbbb04"
   }
  }
 },
 "nbformat": 4,
 "nbformat_minor": 1
}