JJRyan0/BNP Paribas Cardif Claims Management Problem - Accelarating Claims Management Process.ipynb

## BNP Paribas Cardif Claims Management Problem - Accelarating Claims Management Process.ipynb
{
  "cells": [
    {
      "metadata": {},
      "cell_type": "markdown",
      "source": "## Accelerating Insurance Claim Process with Machine Learning\n\n### Random Forests, Support Vector Machines, MLP Neural Networks and K- Nearest Neighbour Learning\n\nKaggle competition: BNP Paribas cardif claims management problem\n\nCreated by John Ryan 22th April 2017\n\nData source: https://www.kaggle.com/c/bnp-paribas-cardif-claims-management"
    },
    {
      "metadata": {
        "collapsed": false,
        "trusted": true
      },
      "cell_type": "code",
      "source": "from IPython.display import Image\nImage(\"C:\\\\data\\\\image.png\",  width=900, height=600)",
      "execution_count": 1,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "image/png": "iVBORw0KGgoAAAANSUhEUgAABTkAAAGVCAYAAAA15vXmAAAAAXNSR0IArs4c6QAAAARnQU1BAACx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\n4f8HdHeU+iWzczEAAAAASUVORK5CYII=\n",
            "text/plain": "<IPython.core.display.Image object>"
          },
          "metadata": {
            "image/png": {
              "width": 900,
              "height": 600
            }
          },
          "execution_count": 1
        }
      ]
    },
    {
      "metadata": {
        "collapsed": false,
        "trusted": true
      },
      "cell_type": "code",
      "source": "Image(\"C:\\\\data\\\\bnp.png\",  width=900, height=600)",
      "execution_count": 2,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "image/png": "iVBORw0KGgoAAAANSUhEUgAABHQAAAM5CAYAAABmbWaKAAAAAXNSR0IArs4c6QAAAARnQU1BAACx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\nZ6dw4QAAAABJRU5ErkJggg==\n",
            "text/plain": "<IPython.core.display.Image object>"
          },
          "metadata": {
            "image/png": {
              "width": 900,
              "height": 600
            }
          },
          "execution_count": 2
        }
      ]
    },
    {
      "metadata": {
        "collapsed": false,
        "trusted": true
      },
      "cell_type": "code",
      "source": "from IPython.display import Image\nImage(\"C:\\\\data\\\\Image2.png\",  width=900, height=600)",
      "execution_count": 3,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "image/png": "iVBORw0KGgoAAAANSUhEUgAABpYAAAMVCAYAAAB9eMdKAAAAAXNSR0IArs4c6QAAAARnQU1BAACx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\n",
            "text/plain": "<IPython.core.display.Image object>"
          },
          "metadata": {
            "image/png": {
              "width": 900,
              "height": 600
            }
          },
          "execution_count": 3
        }
      ]
    },
    {
      "metadata": {
        "collapsed": false,
        "trusted": true
      },
      "cell_type": "code",
      "source": "Image(\"C:\\\\data\\\\image1.png\",  width=500, height=200)",
      "execution_count": 4,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "image/png": "iVBORw0KGgoAAAANSUhEUgAABGcAAAH9CAYAAAC3EhHqAAAAAXNSR0IArs4c6QAAAARnQU1BAACx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\nAAAAAABciMEZAAAAAACAy7y9/X97g6+vKWRvDgAAAABJRU5ErkJggg==\n",
            "text/plain": "<IPython.core.display.Image object>"
          },
          "metadata": {
            "image/png": {
              "width": 500,
              "height": 200
            }
          },
          "execution_count": 4
        }
      ]
    },
    {
      "metadata": {
        "collapsed": false,
        "trusted": true
      },
      "cell_type": "code",
      "source": "#import dependencies\nimport os\nimport warnings\nimport pandas as pd\nimport numpy as np\nwarnings.filterwarnings(\"ignore\", category=DeprecationWarning,\n                       module=\"pandas, lineno=570\")\nfrom __future__ import print_function\nimport os\nimport pandas as pd\nimport numpy as np\nimport io\nimport requests\nimport seaborn as sns\nimport matplotlib.pyplot as plt\nsns.set_style('whitegrid')\n%matplotlib inline\nfrom sklearn import preprocessing\nfrom sklearn.metrics import log_loss, auc, roc_auc_score\nfrom sklearn.preprocessing import LabelEncoder\nfrom sklearn import metrics",
      "execution_count": 2,
      "outputs": []
    },
    {
      "metadata": {},
      "cell_type": "markdown",
      "source": "##   1.0 - Data Cleaning & Preperation\n\n1. Read in the csv file.\n2. Describe and analysis the data\n3. Randomization of the data, separate out all variables to make sure they have the correct     data type i.e. numeric, nominal and categorical.\n3. Missing value treatment.\n4. Encode labels in the data set with \"one hot encoder\".\n5. Use cross Validation to create a test, training and validation data set.\n6. Remove columns from the training data set and select important features.\n7. Randomization of the data, separate out all variables to make sure they have the correct data type i.e. numeric, nominal and categorical.\n8. Build machine Learning algorithms using pythons sci-kit learn from on the training, test data set constructed and preprocessed.\n9. Evaluate the results.\n10.Improve Performance.\n"
    },
    {
      "metadata": {
        "collapsed": false,
        "trusted": true
      },
      "cell_type": "code",
      "source": "#Load the data and make dataset a Pandas DataFrame\ndf = pd.read_csv(\"C:\\\\data\\\\claims.csv\")\ndf.head()",
      "execution_count": 3,
      "outputs": [
        {
          "execution_count": 3,
          "output_type": "execute_result",
          "data": {
            "text/plain": "   ID  target        v1        v2 v3        v4         v5        v6        v7  \\\n0   3       1  1.335739  8.727474  C  3.921026   7.915266  2.599278  3.176895   \n1   4       1       NaN       NaN  C       NaN   9.191265       NaN       NaN   \n2   5       1  0.943877  5.310079  C  4.410969   5.326159  3.979592  3.928571   \n3   6       1  0.797415  8.304757  C  4.225930  11.627438  2.097700  1.987549   \n4   8       1       NaN       NaN  C       NaN        NaN       NaN       NaN   \n\n         v8    ...         v122      v123      v124  v125      v126      v127  \\\n0  0.012941    ...     8.000000  1.989780  0.035754    AU  1.804126  3.113719   \n1  2.301630    ...          NaN       NaN  0.598896    AF       NaN       NaN   \n2  0.019645    ...     9.333333  2.477596  0.013452    AE  1.773709  3.922193   \n3  0.171947    ...     7.018256  1.812795  0.002267    CJ  1.415230  2.954381   \n4       NaN    ...          NaN       NaN       NaN     Z       NaN       NaN   \n\n       v128  v129      v130      v131  \n0  2.024285     0  0.636365  2.857144  \n1  1.957825     0       NaN       NaN  \n2  1.120468     2  0.883118  1.176472  \n3  1.990847     1  1.677108  1.034483  \n4       NaN     0       NaN       NaN  \n\n[5 rows x 133 columns]",
            "text/html": "<div>\n<style>\n    .dataframe thead tr:only-child th {\n        text-align: right;\n    }\n\n    .dataframe thead th {\n        text-align: left;\n    }\n\n    .dataframe tbody tr th {\n        vertical-align: top;\n    }\n</style>\n<table border=\"1\" class=\"dataframe\">\n  <thead>\n    <tr style=\"text-align: right;\">\n      <th></th>\n      <th>ID</th>\n      <th>target</th>\n      <th>v1</th>\n      <th>v2</th>\n      <th>v3</th>\n      <th>v4</th>\n      <th>v5</th>\n      <th>v6</th>\n      <th>v7</th>\n      <th>v8</th>\n      <th>...</th>\n      <th>v122</th>\n      <th>v123</th>\n      <th>v124</th>\n      <th>v125</th>\n      <th>v126</th>\n      <th>v127</th>\n      <th>v128</th>\n      <th>v129</th>\n      <th>v130</th>\n      <th>v131</th>\n    </tr>\n  </thead>\n  <tbody>\n    <tr>\n      <th>0</th>\n      <td>3</td>\n      <td>1</td>\n      <td>1.335739</td>\n      <td>8.727474</td>\n      <td>C</td>\n      <td>3.921026</td>\n      <td>7.915266</td>\n      <td>2.599278</td>\n      <td>3.176895</td>\n      <td>0.012941</td>\n      <td>...</td>\n      <td>8.000000</td>\n      <td>1.989780</td>\n      <td>0.035754</td>\n      <td>AU</td>\n      <td>1.804126</td>\n      <td>3.113719</td>\n      <td>2.024285</td>\n      <td>0</td>\n      <td>0.636365</td>\n      <td>2.857144</td>\n    </tr>\n    <tr>\n      <th>1</th>\n      <td>4</td>\n      <td>1</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>C</td>\n      <td>NaN</td>\n      <td>9.191265</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>2.301630</td>\n      <td>...</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>0.598896</td>\n      <td>AF</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>1.957825</td>\n      <td>0</td>\n      <td>NaN</td>\n      <td>NaN</td>\n    </tr>\n    <tr>\n      <th>2</th>\n      <td>5</td>\n      <td>1</td>\n      <td>0.943877</td>\n      <td>5.310079</td>\n      <td>C</td>\n      <td>4.410969</td>\n      <td>5.326159</td>\n      <td>3.979592</td>\n      <td>3.928571</td>\n      <td>0.019645</td>\n      <td>...</td>\n      <td>9.333333</td>\n      <td>2.477596</td>\n      <td>0.013452</td>\n      <td>AE</td>\n      <td>1.773709</td>\n      <td>3.922193</td>\n      <td>1.120468</td>\n      <td>2</td>\n      <td>0.883118</td>\n      <td>1.176472</td>\n    </tr>\n    <tr>\n      <th>3</th>\n      <td>6</td>\n      <td>1</td>\n      <td>0.797415</td>\n      <td>8.304757</td>\n      <td>C</td>\n      <td>4.225930</td>\n      <td>11.627438</td>\n      <td>2.097700</td>\n      <td>1.987549</td>\n      <td>0.171947</td>\n      <td>...</td>\n      <td>7.018256</td>\n      <td>1.812795</td>\n      <td>0.002267</td>\n      <td>CJ</td>\n      <td>1.415230</td>\n      <td>2.954381</td>\n      <td>1.990847</td>\n      <td>1</td>\n      <td>1.677108</td>\n      <td>1.034483</td>\n    </tr>\n    <tr>\n      <th>4</th>\n      <td>8</td>\n      <td>1</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>C</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>...</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>Z</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>NaN</td>\n      <td>0</td>\n      <td>NaN</td>\n      <td>NaN</td>\n    </tr>\n  </tbody>\n</table>\n<p>5 rows × 133 columns</p>\n</div>"
          },
          "metadata": {}
        }
      ]
    },
    {
      "metadata": {
        "collapsed": false,
        "trusted": true
      },
      "cell_type": "code",
      "source": "#summerize the data to make some initle assessments\ndf.describe()",
      "execution_count": 4,
      "outputs": [
        {
          "execution_count": 4,
          "output_type": "execute_result",
          "data": {
            "text/plain": "                  ID         target            v1            v2            v4  \\\ncount  114321.000000  114321.000000  6.448900e+04  6.452500e+04  6.452500e+04   \nmean   114228.928228       0.761199  1.630686e+00  7.464411e+00  4.145098e+00   \nstd     65934.487362       0.426353  1.082813e+00  2.961676e+00  1.148263e+00   \nmin         3.000000       0.000000 -9.996497e-07 -9.817614e-07 -6.475929e-07   \n25%     57280.000000       1.000000  9.135798e-01  5.316428e+00  3.487398e+00   \n50%    114189.000000       1.000000  1.469550e+00  7.023803e+00  4.205991e+00   \n75%    171206.000000       1.000000  2.136128e+00  9.465497e+00  4.833250e+00   \nmax    228713.000000       1.000000  2.000000e+01  2.000000e+01  2.000000e+01   \n\n                 v5            v6            v7            v8            v9  \\\ncount  6.569700e+04  6.448900e+04  6.448900e+04  6.570200e+04  6.447000e+04   \nmean   8.742359e+00  2.436402e+00  2.483921e+00  1.496569e+00  9.031859e+00   \nstd    2.036018e+00  5.999653e-01  5.894485e-01  2.783003e+00  1.930262e+00   \nmin   -5.287068e-07 -9.055091e-07 -9.468765e-07 -7.783778e-07 -9.828757e-07   \n25%    7.605918e+00  2.065064e+00  2.101477e+00  8.658986e-02  7.853659e+00   \n50%    8.670867e+00  2.412790e+00  2.452166e+00  3.860317e-01  9.059582e+00   \n75%    9.771353e+00  2.775285e+00  2.834285e+00  1.625246e+00  1.023256e+01   \nmax    2.000000e+01  2.000000e+01  2.000000e+01  2.000000e+01  2.000000e+01   \n\n           ...               v121          v122          v123          v124  \\\ncount      ...       6.448100e+04  6.447000e+04  63643.000000  6.570200e+04   \nmean       ...       2.737596e+00  6.822439e+00      3.549938  9.198120e-01   \nstd        ...       1.356294e+00  1.795978e+00      2.604704  2.099407e+00   \nmin        ...      -9.820642e-07 -9.978497e-07      0.019139 -9.994953e-07   \n25%        ...       1.786965e+00  5.647712e+00      1.963315  2.053777e-02   \n50%        ...       2.436195e+00  6.749117e+00      2.739239  1.398639e-01   \n75%        ...       3.379175e+00  7.911392e+00      4.075361  8.718333e-01   \nmax        ...       2.000000e+01  2.000000e+01     19.686069  2.000000e+01   \n\n               v126          v127          v128           v129          v130  \\\ncount  6.448900e+04  6.448900e+04  6.569700e+04  114321.000000  6.447800e+04   \nmean   1.672658e+00  3.239542e+00  2.030373e+00       0.310144  1.925763e+00   \nstd    5.031683e-01  1.625988e+00  1.074232e+00       0.693262  1.264497e+00   \nmin   -9.564174e-07 -9.223798e-07  8.197812e-07       0.000000 -9.901257e-07   \n25%    1.417600e+00  2.101900e+00  1.393830e+00       0.000000  1.106172e+00   \n50%    1.614802e+00  2.963620e+00  1.798436e+00       0.000000  1.560138e+00   \n75%    1.843886e+00  4.108146e+00  2.390158e+00       0.000000  2.332425e+00   \nmax    1.563161e+01  2.000000e+01  2.000000e+01      11.000000  2.000000e+01   \n\n               v131  \ncount  6.442600e+04  \nmean   1.739389e+00  \nstd    1.134702e+00  \nmin   -9.999134e-07  \n25%    1.012658e+00  \n50%    1.589403e+00  \n75%    2.261905e+00  \nmax    2.000000e+01  \n\n[8 rows x 114 columns]",
            "text/html": "<div>\n<style>\n    .dataframe thead tr:only-child th {\n        text-align: right;\n    }\n\n    .dataframe thead th {\n        text-align: left;\n    }\n\n    .dataframe tbody tr th {\n        vertical-align: top;\n    }\n</style>\n<table border=\"1\" class=\"dataframe\">\n  <thead>\n    <tr style=\"text-align: right;\">\n      <th></th>\n      <th>ID</th>\n      <th>target</th>\n      <th>v1</th>\n      <th>v2</th>\n      <th>v4</th>\n      <th>v5</th>\n      <th>v6</th>\n      <th>v7</th>\n      <th>v8</th>\n      <th>v9</th>\n      <th>...</th>\n      <th>v121</th>\n      <th>v122</th>\n      <th>v123</th>\n      <th>v124</th>\n      <th>v126</th>\n      <th>v127</th>\n      <th>v128</th>\n      <th>v129</th>\n      <th>v130</th>\n      <th>v131</th>\n    </tr>\n  </thead>\n  <tbody>\n    <tr>\n      <th>count</th>\n      <td>114321.000000</td>\n      <td>114321.000000</td>\n      <td>6.448900e+04</td>\n      <td>6.452500e+04</td>\n      <td>6.452500e+04</td>\n      <td>6.569700e+04</td>\n      <td>6.448900e+04</td>\n      <td>6.448900e+04</td>\n      <td>6.570200e+04</td>\n      <td>6.447000e+04</td>\n      <td>...</td>\n      <td>6.448100e+04</td>\n      <td>6.447000e+04</td>\n      <td>63643.000000</td>\n      <td>6.570200e+04</td>\n      <td>6.448900e+04</td>\n      <td>6.448900e+04</td>\n      <td>6.569700e+04</td>\n      <td>114321.000000</td>\n      <td>6.447800e+04</td>\n      <td>6.442600e+04</td>\n    </tr>\n    <tr>\n      <th>mean</th>\n      <td>114228.928228</td>\n      <td>0.761199</td>\n      <td>1.630686e+00</td>\n      <td>7.464411e+00</td>\n      <td>4.145098e+00</td>\n      <td>8.742359e+00</td>\n      <td>2.436402e+00</td>\n      <td>2.483921e+00</td>\n      <td>1.496569e+00</td>\n      <td>9.031859e+00</td>\n      <td>...</td>\n      <td>2.737596e+00</td>\n      <td>6.822439e+00</td>\n      <td>3.549938</td>\n      <td>9.198120e-01</td>\n      <td>1.672658e+00</td>\n      <td>3.239542e+00</td>\n      <td>2.030373e+00</td>\n      <td>0.310144</td>\n      <td>1.925763e+00</td>\n      <td>1.739389e+00</td>\n    </tr>\n    <tr>\n      <th>std</th>\n      <td>65934.487362</td>\n      <td>0.426353</td>\n      <td>1.082813e+00</td>\n      <td>2.961676e+00</td>\n      <td>1.148263e+00</td>\n      <td>2.036018e+00</td>\n      <td>5.999653e-01</td>\n      <td>5.894485e-01</td>\n      <td>2.783003e+00</td>\n      <td>1.930262e+00</td>\n      <td>...</td>\n      <td>1.356294e+00</td>\n      <td>1.795978e+00</td>\n      <td>2.604704</td>\n      <td>2.099407e+00</td>\n      <td>5.031683e-01</td>\n      <td>1.625988e+00</td>\n      <td>1.074232e+00</td>\n      <td>0.693262</td>\n      <td>1.264497e+00</td>\n      <td>1.134702e+00</td>\n    </tr>\n    <tr>\n      <th>min</th>\n      <td>3.000000</td>\n      <td>0.000000</td>\n      <td>-9.996497e-07</td>\n      <td>-9.817614e-07</td>\n      <td>-6.475929e-07</td>\n      <td>-5.287068e-07</td>\n      <td>-9.055091e-07</td>\n      <td>-9.468765e-07</td>\n      <td>-7.783778e-07</td>\n      <td>-9.828757e-07</td>\n      <td>...</td>\n      <td>-9.820642e-07</td>\n      <td>-9.978497e-07</td>\n      <td>0.019139</td>\n      <td>-9.994953e-07</td>\n      <td>-9.564174e-07</td>\n      <td>-9.223798e-07</td>\n      <td>8.197812e-07</td>\n      <td>0.000000</td>\n      <td>-9.901257e-07</td>\n      <td>-9.999134e-07</td>\n    </tr>\n    <tr>\n      <th>25%</th>\n      <td>57280.000000</td>\n      <td>1.000000</td>\n      <td>9.135798e-01</td>\n      <td>5.316428e+00</td>\n      <td>3.487398e+00</td>\n      <td>7.605918e+00</td>\n      <td>2.065064e+00</td>\n      <td>2.101477e+00</td>\n      <td>8.658986e-02</td>\n      <td>7.853659e+00</td>\n      <td>...</td>\n      <td>1.786965e+00</td>\n      <td>5.647712e+00</td>\n      <td>1.963315</td>\n      <td>2.053777e-02</td>\n      <td>1.417600e+00</td>\n      <td>2.101900e+00</td>\n      <td>1.393830e+00</td>\n      <td>0.000000</td>\n      <td>1.106172e+00</td>\n      <td>1.012658e+00</td>\n    </tr>\n    <tr>\n      <th>50%</th>\n      <td>114189.000000</td>\n      <td>1.000000</td>\n      <td>1.469550e+00</td>\n      <td>7.023803e+00</td>\n      <td>4.205991e+00</td>\n      <td>8.670867e+00</td>\n      <td>2.412790e+00</td>\n      <td>2.452166e+00</td>\n      <td>3.860317e-01</td>\n      <td>9.059582e+00</td>\n      <td>...</td>\n      <td>2.436195e+00</td>\n      <td>6.749117e+00</td>\n      <td>2.739239</td>\n      <td>1.398639e-01</td>\n      <td>1.614802e+00</td>\n      <td>2.963620e+00</td>\n      <td>1.798436e+00</td>\n      <td>0.000000</td>\n      <td>1.560138e+00</td>\n      <td>1.589403e+00</td>\n    </tr>\n    <tr>\n      <th>75%</th>\n      <td>171206.000000</td>\n      <td>1.000000</td>\n      <td>2.136128e+00</td>\n      <td>9.465497e+00</td>\n      <td>4.833250e+00</td>\n      <td>9.771353e+00</td>\n      <td>2.775285e+00</td>\n      <td>2.834285e+00</td>\n      <td>1.625246e+00</td>\n      <td>1.023256e+01</td>\n      <td>...</td>\n      <td>3.379175e+00</td>\n      <td>7.911392e+00</td>\n      <td>4.075361</td>\n      <td>8.718333e-01</td>\n      <td>1.843886e+00</td>\n      <td>4.108146e+00</td>\n      <td>2.390158e+00</td>\n      <td>0.000000</td>\n      <td>2.332425e+00</td>\n      <td>2.261905e+00</td>\n    </tr>\n    <tr>\n      <th>max</th>\n      <td>228713.000000</td>\n      <td>1.000000</td>\n      <td>2.000000e+01</td>\n      <td>2.000000e+01</td>\n      <td>2.000000e+01</td>\n      <td>2.000000e+01</td>\n      <td>2.000000e+01</td>\n      <td>2.000000e+01</td>\n      <td>2.000000e+01</td>\n      <td>2.000000e+01</td>\n      <td>...</td>\n      <td>2.000000e+01</td>\n      <td>2.000000e+01</td>\n      <td>19.686069</td>\n      <td>2.000000e+01</td>\n      <td>1.563161e+01</td>\n      <td>2.000000e+01</td>\n      <td>2.000000e+01</td>\n      <td>11.000000</td>\n      <td>2.000000e+01</td>\n      <td>2.000000e+01</td>\n    </tr>\n  </tbody>\n</table>\n<p>8 rows × 114 columns</p>\n</div>"
          },
          "metadata": {}
        }
      ]
    },
    {
      "metadata": {
        "collapsed": false,
        "trusted": true
      },
      "cell_type": "code",
      "source": "#A glimpse at the target variable using a bar plot\nsns.countplot(x=\"target\", data=df)",
      "execution_count": 5,
      "outputs": [
        {
          "execution_count": 5,
          "output_type": "execute_result",
          "data": {
            "text/plain": "<matplotlib.axes._subplots.AxesSubplot at 0x127aee80>"
          },
          "metadata": {}
        },
        {
          "output_type": "display_data",
          "data": {
            "image/png": "iVBORw0KGgoAAAANSUhEUgAAAY8AAAERCAYAAACD9ivUAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\n",
            "text/plain": "<matplotlib.figure.Figure at 0x40d0160>"
          },
          "metadata": {}
        }
      ]
    },
    {
      "metadata": {
        "collapsed": false,
        "trusted": true
      },
      "cell_type": "code",
      "source": "#View of target varable by labels 0 = not eligible for acceleration,  \n#1 = claims suitable for an accelerated approval\nd = sns.countplot(x =\"target\", data=df)\nd.set(xticklabels=['not eligible for acceleration', 'claims suitable for an accelerated approval'])\nplt.xlabel(' ')\nd;",
      "execution_count": 6,
      "outputs": [
        {
          "output_type": "display_data",
          "data": {
            "image/png": "iVBORw0KGgoAAAANSUhEUgAAAZoAAAECCAYAAADHMxFNAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\ngg==\n",
            "text/plain": "<matplotlib.figure.Figure at 0x67053c8>"
          },
          "metadata": {}
        }
      ]
    },
    {
      "metadata": {},
      "cell_type": "markdown",
      "source": "### 1.1 - Missing Value Treatment\n\nFor this example we will use the PVI technique meaning Predictive Value Imputation. Before the model is created we will use this method when detecting missing values to estimate values that to replace NaN's with the attribute’s mean, median or mode value.\n\nsteps taken:\n\n- Print out the number of missing values in the entire data set\n- Fill in missing value using mean value of the attributes\n- Summerize the data after cleaning or transforming activities"
    },
    {
      "metadata": {
        "collapsed": false,
        "trusted": true
      },
      "cell_type": "code",
      "source": "#Print out the number of missing values\nprint(\"Number of NA values : {0}\".format((df.shape[0] * df.shape[1]) - df.count().sum()))",
      "execution_count": 8,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": "Number of NA values : 4967293\n"
        }
      ]
    },
    {
      "metadata": {
        "collapsed": false,
        "trusted": true
      },
      "cell_type": "code",
      "source": "#Missing Value PVI using mean value of attributes;\nx = df.fillna(df.mean())\nx.head(7)",
      "execution_count": 9,
      "outputs": [
        {
          "execution_count": 9,
          "output_type": "execute_result",
          "data": {
            "text/plain": "   ID  target        v1        v2  v3        v4         v5        v6  \\\n0   3       1  1.335739  8.727474   3  3.921026   7.915266  2.599278   \n1   4       1  1.630686  7.464411   3  4.145098   9.191265  2.436402   \n2   5       1  0.943877  5.310079   3  4.410969   5.326159  3.979592   \n3   6       1  0.797415  8.304757   3  4.225930  11.627438  2.097700   \n4   8       1  1.630686  7.464411   3  4.145098   8.742359  2.436402   \n5   9       0  1.630686  7.464411   3  4.145098   8.856791  2.436402   \n6  12       0  0.899806  7.312995   3  3.494148   9.946200  1.926070   \n\n         v7        v8    ...         v122      v123      v124  v125      v126  \\\n0  3.176895  0.012941    ...     8.000000  1.989780  0.035754    22  1.804126   \n1  2.483921  2.301630    ...     6.822439  3.549938  0.598896     7  1.672658   \n2  3.928571  0.019645    ...     9.333333  2.477596  0.013452     6  1.773709   \n3  1.987549  0.171947    ...     7.018256  1.812795  0.002267    65  1.415230   \n4  2.483921  1.496569    ...     6.822439  3.549938  0.919812    90  1.672658   \n5  2.483921  0.359993    ...     6.822439  3.549938  0.049861    88  1.672658   \n6  1.770427  0.066251    ...     3.476299  1.992594  0.083758    38  3.276100   \n\n       v127      v128  v129      v130      v131  \n0  3.113719  2.024285     0  0.636365  2.857144  \n1  3.239542  1.957825     0  1.925763  1.739389  \n2  3.922193  1.120468     2  0.883118  1.176472  \n3  2.954381  1.990847     1  1.677108  1.034483  \n4  3.239542  2.030373     0  1.925763  1.739389  \n5  3.239542  1.536222     0  1.925763  1.739389  \n6  1.623298  2.266575     0  2.263736  0.970873  \n\n[7 rows x 133 columns]",
            "text/html": "<div>\n<style>\n    .dataframe thead tr:only-child th {\n        text-align: right;\n    }\n\n    .dataframe thead th {\n        text-align: left;\n    }\n\n    .dataframe tbody tr th {\n        vertical-align: top;\n    }\n</style>\n<table border=\"1\" class=\"dataframe\">\n  <thead>\n    <tr style=\"text-align: right;\">\n      <th></th>\n      <th>ID</th>\n      <th>target</th>\n      <th>v1</th>\n      <th>v2</th>\n      <th>v3</th>\n      <th>v4</th>\n      <th>v5</th>\n      <th>v6</th>\n      <th>v7</th>\n      <th>v8</th>\n      <th>...</th>\n      <th>v122</th>\n      <th>v123</th>\n      <th>v124</th>\n      <th>v125</th>\n      <th>v126</th>\n      <th>v127</th>\n      <th>v128</th>\n      <th>v129</th>\n      <th>v130</th>\n      <th>v131</th>\n    </tr>\n  </thead>\n  <tbody>\n    <tr>\n      <th>0</th>\n      <td>3</td>\n      <td>1</td>\n      <td>1.335739</td>\n      <td>8.727474</td>\n      <td>3</td>\n      <td>3.921026</td>\n      <td>7.915266</td>\n      <td>2.599278</td>\n      <td>3.176895</td>\n      <td>0.012941</td>\n      <td>...</td>\n      <td>8.000000</td>\n      <td>1.989780</td>\n      <td>0.035754</td>\n      <td>22</td>\n      <td>1.804126</td>\n      <td>3.113719</td>\n      <td>2.024285</td>\n      <td>0</td>\n      <td>0.636365</td>\n      <td>2.857144</td>\n    </tr>\n    <tr>\n      <th>1</th>\n      <td>4</td>\n      <td>1</td>\n      <td>1.630686</td>\n      <td>7.464411</td>\n      <td>3</td>\n      <td>4.145098</td>\n      <td>9.191265</td>\n      <td>2.436402</td>\n      <td>2.483921</td>\n      <td>2.301630</td>\n      <td>...</td>\n      <td>6.822439</td>\n      <td>3.549938</td>\n      <td>0.598896</td>\n      <td>7</td>\n      <td>1.672658</td>\n      <td>3.239542</td>\n      <td>1.957825</td>\n      <td>0</td>\n      <td>1.925763</td>\n      <td>1.739389</td>\n    </tr>\n    <tr>\n      <th>2</th>\n      <td>5</td>\n      <td>1</td>\n      <td>0.943877</td>\n      <td>5.310079</td>\n      <td>3</td>\n      <td>4.410969</td>\n      <td>5.326159</td>\n      <td>3.979592</td>\n      <td>3.928571</td>\n      <td>0.019645</td>\n      <td>...</td>\n      <td>9.333333</td>\n      <td>2.477596</td>\n      <td>0.013452</td>\n      <td>6</td>\n      <td>1.773709</td>\n      <td>3.922193</td>\n      <td>1.120468</td>\n      <td>2</td>\n      <td>0.883118</td>\n      <td>1.176472</td>\n    </tr>\n    <tr>\n      <th>3</th>\n      <td>6</td>\n      <td>1</td>\n      <td>0.797415</td>\n      <td>8.304757</td>\n      <td>3</td>\n      <td>4.225930</td>\n      <td>11.627438</td>\n      <td>2.097700</td>\n      <td>1.987549</td>\n      <td>0.171947</td>\n      <td>...</td>\n      <td>7.018256</td>\n      <td>1.812795</td>\n      <td>0.002267</td>\n      <td>65</td>\n      <td>1.415230</td>\n      <td>2.954381</td>\n      <td>1.990847</td>\n      <td>1</td>\n      <td>1.677108</td>\n      <td>1.034483</td>\n    </tr>\n    <tr>\n      <th>4</th>\n      <td>8</td>\n      <td>1</td>\n      <td>1.630686</td>\n      <td>7.464411</td>\n      <td>3</td>\n      <td>4.145098</td>\n      <td>8.742359</td>\n      <td>2.436402</td>\n      <td>2.483921</td>\n      <td>1.496569</td>\n      <td>...</td>\n      <td>6.822439</td>\n      <td>3.549938</td>\n      <td>0.919812</td>\n      <td>90</td>\n      <td>1.672658</td>\n      <td>3.239542</td>\n      <td>2.030373</td>\n      <td>0</td>\n      <td>1.925763</td>\n      <td>1.739389</td>\n    </tr>\n    <tr>\n      <th>5</th>\n      <td>9</td>\n      <td>0</td>\n      <td>1.630686</td>\n      <td>7.464411</td>\n      <td>3</td>\n      <td>4.145098</td>\n      <td>8.856791</td>\n      <td>2.436402</td>\n      <td>2.483921</td>\n      <td>0.359993</td>\n      <td>...</td>\n      <td>6.822439</td>\n      <td>3.549938</td>\n      <td>0.049861</td>\n      <td>88</td>\n      <td>1.672658</td>\n      <td>3.239542</td>\n      <td>1.536222</td>\n      <td>0</td>\n      <td>1.925763</td>\n      <td>1.739389</td>\n    </tr>\n    <tr>\n      <th>6</th>\n      <td>12</td>\n      <td>0</td>\n      <td>0.899806</td>\n      <td>7.312995</td>\n      <td>3</td>\n      <td>3.494148</td>\n      <td>9.946200</td>\n      <td>1.926070</td>\n      <td>1.770427</td>\n      <td>0.066251</td>\n      <td>...</td>\n      <td>3.476299</td>\n      <td>1.992594</td>\n      <td>0.083758</td>\n      <td>38</td>\n      <td>3.276100</td>\n      <td>1.623298</td>\n      <td>2.266575</td>\n      <td>0</td>\n      <td>2.263736</td>\n      <td>0.970873</td>\n    </tr>\n  </tbody>\n</table>\n<p>7 rows × 133 columns</p>\n</div>"
          },
          "metadata": {}
        }
      ]
    },
    {
      "metadata": {
        "collapsed": false,
        "trusted": true
      },
      "cell_type": "code",
      "source": "print(\"Number of NA values : {0}\".format((x.shape[0] * x.shape[1]) - x.count().sum()))",
      "execution_count": 11,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": "Number of NA values : 0\n"
        }
      ]
    },
    {
      "metadata": {
        "collapsed": false,
        "trusted": true
      },
      "cell_type": "code",
      "source": "#Always good preactise to summerize the data after cleaning or transforming activities\nx.describe()",
      "execution_count": 12,
      "outputs": [
        {
          "execution_count": 12,
          "output_type": "execute_result",
          "data": {
            "text/plain": "                  ID         target            v1            v2  \\\ncount  114321.000000  114321.000000  1.143210e+05  1.143210e+05   \nmean   114228.928228       0.761199  1.630686e+00  7.464411e+00   \nstd     65934.487362       0.426353  8.132649e-01  2.225036e+00   \nmin         3.000000       0.000000 -9.996497e-07 -9.817614e-07   \n25%     57280.000000       1.000000  1.346153e+00  6.575770e+00   \n50%    114189.000000       1.000000  1.630686e+00  7.464411e+00   \n75%    171206.000000       1.000000  1.630686e+00  7.551501e+00   \nmax    228713.000000       1.000000  2.000000e+01  2.000000e+01   \n\n                  v3            v4            v5            v6            v7  \\\ncount  114321.000000  1.143210e+05  1.143210e+05  1.143210e+05  1.143210e+05   \nmean        2.904847  4.145098e+00  8.742359e+00  2.436402e+00  2.483921e+00   \nstd         0.521065  8.626621e-01  1.543441e+00  4.506138e-01  4.427150e-01   \nmin         0.000000 -6.475929e-07 -5.287068e-07 -9.055091e-07 -9.468765e-07   \n25%         3.000000  4.068697e+00  8.394090e+00  2.340968e+00  2.376586e+00   \n50%         3.000000  4.145098e+00  8.742359e+00  2.436402e+00  2.483921e+00   \n75%         3.000000  4.340229e+00  8.924798e+00  2.484699e+00  2.528445e+00   \nmax         3.000000  2.000000e+01  2.000000e+01  2.000000e+01  2.000000e+01   \n\n                 v8      ...               v122           v123          v124  \\\ncount  1.143210e+05      ...       1.143210e+05  114321.000000  1.143210e+05   \nmean   1.496569e+00      ...       6.822439e+00       3.549938  9.198120e-01   \nstd    2.109786e+00      ...       1.348700e+00       1.943431  1.591555e+00   \nmin   -7.783778e-07      ...      -9.978497e-07       0.019139 -9.994953e-07   \n25%    2.653147e-01      ...       6.519607e+00       2.571053  8.471320e-02   \n50%    1.496569e+00      ...       6.822439e+00       3.549938  9.198120e-01   \n75%    1.496569e+00      ...       6.999999e+00       3.549938  9.198120e-01   \nmax    2.000000e+01      ...       2.000000e+01      19.686069  2.000000e+01   \n\n                v125          v126          v127          v128           v129  \\\ncount  114321.000000  1.143210e+05  1.143210e+05  1.143210e+05  114321.000000   \nmean       46.719964  1.672658e+00  3.239542e+00  2.030373e+00       0.310144   \nstd        25.405608  3.779128e-01  1.221225e+00  8.143413e-01       0.693262   \nmin         0.000000 -9.564174e-07 -9.223798e-07  8.197812e-07       0.000000   \n25%        26.000000  1.570974e+00  2.762497e+00  1.681261e+00       0.000000   \n50%        46.000000  1.672658e+00  3.239542e+00  2.030373e+00       0.000000   \n75%        69.000000  1.672658e+00  3.239542e+00  2.030373e+00       0.000000   \nmax        90.000000  1.563161e+01  2.000000e+01  2.000000e+01      11.000000   \n\n               v130          v131  \ncount  1.143210e+05  1.143210e+05  \nmean   1.925763e+00  1.739389e+00  \nstd    9.496402e-01  8.518204e-01  \nmin   -9.901257e-07 -9.999134e-07  \n25%    1.449477e+00  1.463414e+00  \n50%    1.925763e+00  1.739389e+00  \n75%    1.925763e+00  1.739389e+00  \nmax    2.000000e+01  2.000000e+01  \n\n[8 rows x 133 columns]",
            "text/html": "<div>\n<style>\n    .dataframe thead tr:only-child th {\n        text-align: right;\n    }\n\n    .dataframe thead th {\n        text-align: left;\n    }\n\n    .dataframe tbody tr th {\n        vertical-align: top;\n    }\n</style>\n<table border=\"1\" class=\"dataframe\">\n  <thead>\n    <tr style=\"text-align: right;\">\n      <th></th>\n      <th>ID</th>\n      <th>target</th>\n      <th>v1</th>\n      <th>v2</th>\n      <th>v3</th>\n      <th>v4</th>\n      <th>v5</th>\n      <th>v6</th>\n      <th>v7</th>\n      <th>v8</th>\n      <th>...</th>\n      <th>v122</th>\n      <th>v123</th>\n      <th>v124</th>\n      <th>v125</th>\n      <th>v126</th>\n      <th>v127</th>\n      <th>v128</th>\n      <th>v129</th>\n      <th>v130</th>\n      <th>v131</th>\n    </tr>\n  </thead>\n  <tbody>\n    <tr>\n      <th>count</th>\n      <td>114321.000000</td>\n      <td>114321.000000</td>\n      <td>1.143210e+05</td>\n      <td>1.143210e+05</td>\n      <td>114321.000000</td>\n      <td>1.143210e+05</td>\n      <td>1.143210e+05</td>\n      <td>1.143210e+05</td>\n      <td>1.143210e+05</td>\n      <td>1.143210e+05</td>\n      <td>...</td>\n      <td>1.143210e+05</td>\n      <td>114321.000000</td>\n      <td>1.143210e+05</td>\n      <td>114321.000000</td>\n      <td>1.143210e+05</td>\n      <td>1.143210e+05</td>\n      <td>1.143210e+05</td>\n      <td>114321.000000</td>\n      <td>1.143210e+05</td>\n      <td>1.143210e+05</td>\n    </tr>\n    <tr>\n      <th>mean</th>\n      <td>114228.928228</td>\n      <td>0.761199</td>\n      <td>1.630686e+00</td>\n      <td>7.464411e+00</td>\n      <td>2.904847</td>\n      <td>4.145098e+00</td>\n      <td>8.742359e+00</td>\n      <td>2.436402e+00</td>\n      <td>2.483921e+00</td>\n      <td>1.496569e+00</td>\n      <td>...</td>\n      <td>6.822439e+00</td>\n      <td>3.549938</td>\n      <td>9.198120e-01</td>\n      <td>46.719964</td>\n      <td>1.672658e+00</td>\n      <td>3.239542e+00</td>\n      <td>2.030373e+00</td>\n      <td>0.310144</td>\n      <td>1.925763e+00</td>\n      <td>1.739389e+00</td>\n    </tr>\n    <tr>\n      <th>std</th>\n      <td>65934.487362</td>\n      <td>0.426353</td>\n      <td>8.132649e-01</td>\n      <td>2.225036e+00</td>\n      <td>0.521065</td>\n      <td>8.626621e-01</td>\n      <td>1.543441e+00</td>\n      <td>4.506138e-01</td>\n      <td>4.427150e-01</td>\n      <td>2.109786e+00</td>\n      <td>...</td>\n      <td>1.348700e+00</td>\n      <td>1.943431</td>\n      <td>1.591555e+00</td>\n      <td>25.405608</td>\n      <td>3.779128e-01</td>\n      <td>1.221225e+00</td>\n      <td>8.143413e-01</td>\n      <td>0.693262</td>\n      <td>9.496402e-01</td>\n      <td>8.518204e-01</td>\n    </tr>\n    <tr>\n      <th>min</th>\n      <td>3.000000</td>\n      <td>0.000000</td>\n      <td>-9.996497e-07</td>\n      <td>-9.817614e-07</td>\n      <td>0.000000</td>\n      <td>-6.475929e-07</td>\n      <td>-5.287068e-07</td>\n      <td>-9.055091e-07</td>\n      <td>-9.468765e-07</td>\n      <td>-7.783778e-07</td>\n      <td>...</td>\n      <td>-9.978497e-07</td>\n      <td>0.019139</td>\n      <td>-9.994953e-07</td>\n      <td>0.000000</td>\n      <td>-9.564174e-07</td>\n      <td>-9.223798e-07</td>\n      <td>8.197812e-07</td>\n      <td>0.000000</td>\n      <td>-9.901257e-07</td>\n      <td>-9.999134e-07</td>\n    </tr>\n    <tr>\n      <th>25%</th>\n      <td>57280.000000</td>\n      <td>1.000000</td>\n      <td>1.346153e+00</td>\n      <td>6.575770e+00</td>\n      <td>3.000000</td>\n      <td>4.068697e+00</td>\n      <td>8.394090e+00</td>\n      <td>2.340968e+00</td>\n      <td>2.376586e+00</td>\n      <td>2.653147e-01</td>\n      <td>...</td>\n      <td>6.519607e+00</td>\n      <td>2.571053</td>\n      <td>8.471320e-02</td>\n      <td>26.000000</td>\n      <td>1.570974e+00</td>\n      <td>2.762497e+00</td>\n      <td>1.681261e+00</td>\n      <td>0.000000</td>\n      <td>1.449477e+00</td>\n      <td>1.463414e+00</td>\n    </tr>\n    <tr>\n      <th>50%</th>\n      <td>114189.000000</td>\n      <td>1.000000</td>\n      <td>1.630686e+00</td>\n      <td>7.464411e+00</td>\n      <td>3.000000</td>\n      <td>4.145098e+00</td>\n      <td>8.742359e+00</td>\n      <td>2.436402e+00</td>\n      <td>2.483921e+00</td>\n      <td>1.496569e+00</td>\n      <td>...</td>\n      <td>6.822439e+00</td>\n      <td>3.549938</td>\n      <td>9.198120e-01</td>\n      <td>46.000000</td>\n      <td>1.672658e+00</td>\n      <td>3.239542e+00</td>\n      <td>2.030373e+00</td>\n      <td>0.000000</td>\n      <td>1.925763e+00</td>\n      <td>1.739389e+00</td>\n    </tr>\n    <tr>\n      <th>75%</th>\n      <td>171206.000000</td>\n      <td>1.000000</td>\n      <td>1.630686e+00</td>\n      <td>7.551501e+00</td>\n      <td>3.000000</td>\n      <td>4.340229e+00</td>\n      <td>8.924798e+00</td>\n      <td>2.484699e+00</td>\n      <td>2.528445e+00</td>\n      <td>1.496569e+00</td>\n      <td>...</td>\n      <td>6.999999e+00</td>\n      <td>3.549938</td>\n      <td>9.198120e-01</td>\n      <td>69.000000</td>\n      <td>1.672658e+00</td>\n      <td>3.239542e+00</td>\n      <td>2.030373e+00</td>\n      <td>0.000000</td>\n      <td>1.925763e+00</td>\n      <td>1.739389e+00</td>\n    </tr>\n    <tr>\n      <th>max</th>\n      <td>228713.000000</td>\n      <td>1.000000</td>\n      <td>2.000000e+01</td>\n      <td>2.000000e+01</td>\n      <td>3.000000</td>\n      <td>2.000000e+01</td>\n      <td>2.000000e+01</td>\n      <td>2.000000e+01</td>\n      <td>2.000000e+01</td>\n      <td>2.000000e+01</td>\n      <td>...</td>\n      <td>2.000000e+01</td>\n      <td>19.686069</td>\n      <td>2.000000e+01</td>\n      <td>90.000000</td>\n      <td>1.563161e+01</td>\n      <td>2.000000e+01</td>\n      <td>2.000000e+01</td>\n      <td>11.000000</td>\n      <td>2.000000e+01</td>\n      <td>2.000000e+01</td>\n    </tr>\n  </tbody>\n</table>\n<p>8 rows × 133 columns</p>\n</div>"
          },
          "metadata": {}
        }
      ]
    },
    {
      "metadata": {},
      "cell_type": "markdown",
      "source": "## 1.2 - Feature Importance\n### Estimating highly predictive features with a Ensemble Random Tree Classifier\n\nSometimes when we are faced with a large dataset with a large amount of features it may be useful to carry out an automatic variable selection on the columns. We can make use of machine learning to make an estimate on what are the most relevant feature for a predictive model scenario. To determine a list of predictive features a meta estimator can be used that fits a number of decision trees on sub-samples of the main dataset.\n\nThe n_estimators specifies the number of randomized trees to be used. It is also important to note that the max_features parameter can also be specified to look for the best split in the data. The log2 & square root of the number of features can be used, however for this example we have used the default \"auto\" which uses the square root of the number of features.\n\nSteps taken:\n\n- Encode Labels \"One Hot Encoder\"\n- Assign the target variable to Y for later processing and Remove the ID Column as not required. \n- Build ExtraTreesClassifier model to extract the best predictive features.\n- Rank the Important Variables in order\n- Subsetting the resulting data into a data frame with the top ranked features produced by the algorithim"
    },
    {
      "metadata": {},
      "cell_type": "markdown",
      "source": "### 1.2.1 - Encode Labels \"One Hot Encoder\"\n\nFirst we need to encode any categoral attributes to numeric representations."
    },
    {
      "metadata": {
        "collapsed": false,
        "trusted": true
      },
      "cell_type": "code",
      "source": "#Label encoder tranforms any label or attribute for input to the algorithim \n#we can also see some missing values in the top few rows of the data set these will also\n#need to be treated in a suitable mannor.\nfor feature in x.columns:\n    if x[feature].dtype=='object':\n        le = LabelEncoder()\n        df[feature] = le.fit_transform(x[feature])\nx.tail(3)",
      "execution_count": 13,
      "outputs": [
        {
          "execution_count": 13,
          "output_type": "execute_result",
          "data": {
            "text/plain": "            ID  target        v1        v2  v3        v4         v5        v6  \\\n114318  228711       1  1.630686  7.464411   3  4.145098  10.069277  2.436402   \n114319  228712       1  1.630686  7.464411   3  4.145098  10.106144  2.436402   \n114320  228713       1  1.619763  7.932978   3  4.640085   8.473141  2.351470   \n\n              v7        v8    ...         v122      v123      v124  v125  \\\n114318  2.483921  0.323324    ...     6.822439  3.549938  0.156764    81   \n114319  2.483921  0.309226    ...     6.822439  3.549938  0.490658    51   \n114320  2.826766  3.479754    ...     7.936508  2.944285  3.135205    86   \n\n            v126      v127      v128  v129      v130      v131  \n114318  1.672658  3.239542  2.417606     2  1.925763  1.739389  \n114319  1.672658  3.239542  3.526650     0  1.925763  1.739389  \n114320  1.943149  4.385553  1.604493     0  1.787610  1.386138  \n\n[3 rows x 133 columns]",
            "text/html": "<div>\n<style>\n    .dataframe thead tr:only-child th {\n        text-align: right;\n    }\n\n    .dataframe thead th {\n        text-align: left;\n    }\n\n    .dataframe tbody tr th {\n        vertical-align: top;\n    }\n</style>\n<table border=\"1\" class=\"dataframe\">\n  <thead>\n    <tr style=\"text-align: right;\">\n      <th></th>\n      <th>ID</th>\n      <th>target</th>\n      <th>v1</th>\n      <th>v2</th>\n      <th>v3</th>\n      <th>v4</th>\n      <th>v5</th>\n      <th>v6</th>\n      <th>v7</th>\n      <th>v8</th>\n      <th>...</th>\n      <th>v122</th>\n      <th>v123</th>\n      <th>v124</th>\n      <th>v125</th>\n      <th>v126</th>\n      <th>v127</th>\n      <th>v128</th>\n      <th>v129</th>\n      <th>v130</th>\n      <th>v131</th>\n    </tr>\n  </thead>\n  <tbody>\n    <tr>\n      <th>114318</th>\n      <td>228711</td>\n      <td>1</td>\n      <td>1.630686</td>\n      <td>7.464411</td>\n      <td>3</td>\n      <td>4.145098</td>\n      <td>10.069277</td>\n      <td>2.436402</td>\n      <td>2.483921</td>\n      <td>0.323324</td>\n      <td>...</td>\n      <td>6.822439</td>\n      <td>3.549938</td>\n      <td>0.156764</td>\n      <td>81</td>\n      <td>1.672658</td>\n      <td>3.239542</td>\n      <td>2.417606</td>\n      <td>2</td>\n      <td>1.925763</td>\n      <td>1.739389</td>\n    </tr>\n    <tr>\n      <th>114319</th>\n      <td>228712</td>\n      <td>1</td>\n      <td>1.630686</td>\n      <td>7.464411</td>\n      <td>3</td>\n      <td>4.145098</td>\n      <td>10.106144</td>\n      <td>2.436402</td>\n      <td>2.483921</td>\n      <td>0.309226</td>\n      <td>...</td>\n      <td>6.822439</td>\n      <td>3.549938</td>\n      <td>0.490658</td>\n      <td>51</td>\n      <td>1.672658</td>\n      <td>3.239542</td>\n      <td>3.526650</td>\n      <td>0</td>\n      <td>1.925763</td>\n      <td>1.739389</td>\n    </tr>\n    <tr>\n      <th>114320</th>\n      <td>228713</td>\n      <td>1</td>\n      <td>1.619763</td>\n      <td>7.932978</td>\n      <td>3</td>\n      <td>4.640085</td>\n      <td>8.473141</td>\n      <td>2.351470</td>\n      <td>2.826766</td>\n      <td>3.479754</td>\n      <td>...</td>\n      <td>7.936508</td>\n      <td>2.944285</td>\n      <td>3.135205</td>\n      <td>86</td>\n      <td>1.943149</td>\n      <td>4.385553</td>\n      <td>1.604493</td>\n      <td>0</td>\n      <td>1.787610</td>\n      <td>1.386138</td>\n    </tr>\n  </tbody>\n</table>\n<p>3 rows × 133 columns</p>\n</div>"
          },
          "metadata": {}
        }
      ]
    },
    {
      "metadata": {
        "collapsed": false,
        "trusted": true
      },
      "cell_type": "code",
      "source": "#Assign the target variable to Y for later processing and \n#Remove the ID Column that is not needed \ny = x.target.values\nx = x.drop(['ID'], axis = 1)",
      "execution_count": 14,
      "outputs": []
    },
    {
      "metadata": {
        "scrolled": true,
        "collapsed": false,
        "trusted": true
      },
      "cell_type": "code",
      "source": "#Feature Importance - selecting only highly prdictive features using random forest Model\nfrom sklearn.ensemble import ExtraTreesClassifier\nx.shape\n# feature extraction\nmodel = ExtraTreesClassifier(n_estimators = 250, max_features = \"auto\", random_state=0)\nmodel.fit(x, y)\nprint(model.feature_importances_)",
      "execution_count": 15,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": "[  8.59747486e-01   6.49149406e-04   6.48240229e-04   2.35306696e-04\n   6.44989081e-04   6.54041387e-04   6.85861167e-04   6.45662100e-04\n   5.82026343e-04   6.33884435e-04   3.78767425e-03   5.99661664e-04\n   2.38747724e-03   6.02269023e-04   2.69156300e-03   6.22218504e-04\n   6.72080243e-04   6.14551541e-04   6.48057213e-04   5.98859933e-04\n   6.20538100e-04   2.06448005e-03   1.58215363e-03   7.21670390e-04\n   1.86642660e-03   5.87842171e-04   6.35629110e-04   6.40484732e-04\n   6.82761877e-04   5.66945889e-04   1.40852440e-03   4.22241328e-03\n   5.95350433e-04   6.20893277e-04   2.59562992e-03   6.28390446e-04\n   6.47273307e-04   6.51065347e-04   4.49284005e-04   6.42504466e-04\n   2.32761475e-03   5.90911164e-04   6.08185456e-04   6.07408830e-04\n   6.28350982e-04   6.33693113e-04   5.82212537e-04   5.74973320e-03\n   6.13149400e-04   5.82923395e-04   8.94366957e-03   6.58771934e-04\n   1.64379057e-03   6.05700059e-04   6.00073854e-04   6.44485140e-04\n   2.62486875e-03   6.87948704e-04   7.12451867e-04   6.27393960e-04\n   6.02550305e-04   6.55542193e-04   2.49141806e-03   5.97167734e-04\n   6.23145881e-04   6.10573145e-04   6.14221927e-03   5.93678540e-04\n   6.26523012e-04   6.79267707e-04   6.58716471e-04   9.26695201e-04\n   1.36560106e-03   6.29150397e-04   2.15942203e-04   8.19147258e-04\n   6.05335635e-04   5.99842402e-04   6.50437179e-04   2.02483933e-03\n   6.52552299e-04   6.51959803e-04   6.76534012e-04   6.13289963e-04\n   6.38002850e-04   6.84751296e-04   6.27876726e-04   6.55589221e-04\n   6.78538879e-04   6.16683445e-04   6.19057523e-04   1.41801404e-03\n   5.87724331e-04   6.14874384e-04   5.95500661e-04   6.18845108e-04\n   5.88122290e-04   6.17805929e-04   6.77774246e-04   6.66463523e-04\n   6.81253123e-04   6.74039855e-04   6.40397158e-04   6.17465745e-04\n   6.03949934e-04   6.00547181e-04   6.21316123e-04   1.41494538e-03\n   6.34662934e-04   6.49741679e-04   4.36367721e-03   6.32819311e-04\n   1.46391749e-03   3.39516438e-03   2.93169692e-03   6.63516174e-04\n   6.10565393e-04   6.59969155e-04   6.27320095e-04   8.11194472e-04\n   6.60139043e-04   6.44714066e-04   6.60805204e-04   7.01021040e-04\n   6.08050711e-04   1.55138864e-03   6.07439361e-04   6.30254314e-04\n   6.24697628e-04   1.70277232e-03   6.00015079e-04   6.38131230e-04]\n"
        }
      ]
    },
    {
      "metadata": {},
      "cell_type": "markdown",
      "source": "### 1.2.2 - Ranking Important Variables"
    },
    {
      "metadata": {
        "collapsed": false,
        "trusted": true
      },
      "cell_type": "code",
      "source": "#Ranking the most imporatnt predictive variables potentially build model based on top ranked i.e 1 -16\nfeatureimportance = model.feature_importances_\nstd = np.std([tree.feature_importances_ for tree in model.estimators_], axis=0)\nindices = np.argsort(featureimportance)[::-1]\n#Print top ranked predictive featurescdata = pd.DataFrame(x, columns = [ 'target','v50','v66','v47','v110','v31','v10','v113','v114'..])\nprint(\"Feature ranking:\")\n\nfor feature in range(x.shape[1]):\n    print(\"%d. feature %d (%f)\" % (feature + 1, indices[feature], featureimportance[indices[feature]]))   ",
      "execution_count": 16,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": "Feature ranking:\n1. feature 0 (0.859747)\n2. feature 50 (0.008944)\n3. feature 66 (0.006142)\n4. feature 47 (0.005750)\n5. feature 110 (0.004364)\n6. feature 31 (0.004222)\n7. feature 10 (0.003788)\n8. feature 113 (0.003395)\n9. feature 114 (0.002932)\n10. feature 14 (0.002692)\n11. feature 56 (0.002625)\n12. feature 34 (0.002596)\n13. feature 62 (0.002491)\n14. feature 12 (0.002387)\n15. feature 40 (0.002328)\n16. feature 21 (0.002064)\n17. feature 79 (0.002025)\n18. feature 24 (0.001866)\n19. feature 129 (0.001703)\n20. feature 52 (0.001644)\n21. feature 22 (0.001582)\n22. feature 125 (0.001551)\n23. feature 112 (0.001464)\n24. feature 91 (0.001418)\n25. feature 107 (0.001415)\n26. feature 30 (0.001409)\n27. feature 72 (0.001366)\n28. feature 71 (0.000927)\n29. feature 75 (0.000819)\n30. feature 119 (0.000811)\n31. feature 23 (0.000722)\n32. feature 58 (0.000712)\n33. feature 123 (0.000701)\n34. feature 57 (0.000688)\n35. feature 6 (0.000686)\n36. feature 85 (0.000685)\n37. feature 28 (0.000683)\n38. feature 100 (0.000681)\n39. feature 69 (0.000679)\n40. feature 88 (0.000679)\n41. feature 98 (0.000678)\n42. feature 82 (0.000677)\n43. feature 101 (0.000674)\n44. feature 16 (0.000672)\n45. feature 99 (0.000666)\n46. feature 115 (0.000664)\n47. feature 122 (0.000661)\n48. feature 120 (0.000660)\n49. feature 117 (0.000660)\n50. feature 51 (0.000659)\n51. feature 70 (0.000659)\n52. feature 87 (0.000656)\n53. feature 61 (0.000656)\n54. feature 5 (0.000654)\n55. feature 80 (0.000653)\n56. feature 81 (0.000652)\n57. feature 37 (0.000651)\n58. feature 78 (0.000650)\n59. feature 109 (0.000650)\n60. feature 1 (0.000649)\n61. feature 2 (0.000648)\n62. feature 18 (0.000648)\n63. feature 36 (0.000647)\n64. feature 7 (0.000646)\n65. feature 4 (0.000645)\n66. feature 121 (0.000645)\n67. feature 55 (0.000644)\n68. feature 39 (0.000643)\n69. feature 27 (0.000640)\n70. feature 102 (0.000640)\n71. feature 131 (0.000638)\n72. feature 84 (0.000638)\n73. feature 26 (0.000636)\n74. feature 108 (0.000635)\n75. feature 9 (0.000634)\n76. feature 45 (0.000634)\n77. feature 111 (0.000633)\n78. feature 127 (0.000630)\n79. feature 73 (0.000629)\n80. feature 35 (0.000628)\n81. feature 44 (0.000628)\n82. feature 86 (0.000628)\n83. feature 59 (0.000627)\n84. feature 118 (0.000627)\n85. feature 68 (0.000627)\n86. feature 128 (0.000625)\n87. feature 64 (0.000623)\n88. feature 15 (0.000622)\n89. feature 106 (0.000621)\n90. feature 33 (0.000621)\n91. feature 20 (0.000621)\n92. feature 90 (0.000619)\n93. feature 95 (0.000619)\n94. feature 97 (0.000618)\n95. feature 103 (0.000617)\n96. feature 89 (0.000617)\n97. feature 93 (0.000615)\n98. feature 17 (0.000615)\n99. feature 83 (0.000613)\n100. feature 48 (0.000613)\n101. feature 65 (0.000611)\n102. feature 116 (0.000611)\n103. feature 42 (0.000608)\n104. feature 124 (0.000608)\n105. feature 126 (0.000607)\n106. feature 43 (0.000607)\n107. feature 53 (0.000606)\n108. feature 76 (0.000605)\n109. feature 104 (0.000604)\n110. feature 60 (0.000603)\n111. feature 13 (0.000602)\n112. feature 105 (0.000601)\n113. feature 54 (0.000600)\n114. feature 130 (0.000600)\n115. feature 77 (0.000600)\n116. feature 11 (0.000600)\n117. feature 19 (0.000599)\n118. feature 63 (0.000597)\n119. feature 94 (0.000596)\n120. feature 32 (0.000595)\n121. feature 67 (0.000594)\n122. feature 41 (0.000591)\n123. feature 96 (0.000588)\n124. feature 25 (0.000588)\n125. feature 92 (0.000588)\n126. feature 49 (0.000583)\n127. feature 46 (0.000582)\n128. feature 8 (0.000582)\n129. feature 29 (0.000567)\n130. feature 38 (0.000449)\n131. feature 3 (0.000235)\n132. feature 74 (0.000216)\n"
        }
      ]
    },
    {
      "metadata": {
        "collapsed": false,
        "trusted": true
      },
      "cell_type": "code",
      "source": "#Subsetting the data set using the top ranked variable produced by the algorithim\ncdata = pd.DataFrame(x, columns = [ 'target','v50','v66','v47','v110','v31','v10','v114'])\ncdata.tail(4)",
      "execution_count": 37,
      "outputs": [
        {
          "execution_count": 37,
          "output_type": "execute_result",
          "data": {
            "text/plain": "        target       v50  v66  v47  v110  v31       v10       v114\n114317       1  3.269020    0    2     1    2  6.236324  11.248736\n114318       1  2.410681    0    2     1    2  2.078775   8.893134\n114319       1  0.821657    0    2     1    1  1.291029  12.381113\n114320       1  1.000661    2    2     1    1  0.853391  14.635298",
            "text/html": "<div>\n<style>\n    .dataframe thead tr:only-child th {\n        text-align: right;\n    }\n\n    .dataframe thead th {\n        text-align: left;\n    }\n\n    .dataframe tbody tr th {\n        vertical-align: top;\n    }\n</style>\n<table border=\"1\" class=\"dataframe\">\n  <thead>\n    <tr style=\"text-align: right;\">\n      <th></th>\n      <th>target</th>\n      <th>v50</th>\n      <th>v66</th>\n      <th>v47</th>\n      <th>v110</th>\n      <th>v31</th>\n      <th>v10</th>\n      <th>v114</th>\n    </tr>\n  </thead>\n  <tbody>\n    <tr>\n      <th>114317</th>\n      <td>1</td>\n      <td>3.269020</td>\n      <td>0</td>\n      <td>2</td>\n      <td>1</td>\n      <td>2</td>\n      <td>6.236324</td>\n      <td>11.248736</td>\n    </tr>\n    <tr>\n      <th>114318</th>\n      <td>1</td>\n      <td>2.410681</td>\n      <td>0</td>\n      <td>2</td>\n      <td>1</td>\n      <td>2</td>\n      <td>2.078775</td>\n      <td>8.893134</td>\n    </tr>\n    <tr>\n      <th>114319</th>\n      <td>1</td>\n      <td>0.821657</td>\n      <td>0</td>\n      <td>2</td>\n      <td>1</td>\n      <td>1</td>\n      <td>1.291029</td>\n      <td>12.381113</td>\n    </tr>\n    <tr>\n      <th>114320</th>\n      <td>1</td>\n      <td>1.000661</td>\n      <td>2</td>\n      <td>2</td>\n      <td>1</td>\n      <td>1</td>\n      <td>0.853391</td>\n      <td>14.635298</td>\n    </tr>\n  </tbody>\n</table>\n</div>"
          },
          "metadata": {}
        }
      ]
    },
    {
      "metadata": {
        "collapsed": false,
        "trusted": true
      },
      "cell_type": "code",
      "source": "#entire dataset - removed the target variable\n#X = x.drop(['target'], axis = 1)\n#Y = x.target.values",
      "execution_count": 27,
      "outputs": []
    },
    {
      "metadata": {},
      "cell_type": "markdown",
      "source": "### 2.0 - Building Machine Learning Models"
    },
    {
      "metadata": {
        "collapsed": true
      },
      "cell_type": "markdown",
      "source": "### 2.1 - Random Forest Algorithm"
    },
    {
      "metadata": {},
      "cell_type": "markdown",
      "source": "There are many advantages to applying a tree model with bootstrap aggregation and building each tree from different random subset of features which encourages ensemble diversity and thus reduces training time significantly.\n\nScaling or transforming the data is not necessary for random forests.\nThis algorithim deals with convergence and numerical precision issues,\nwhich can sometimes trip up the algorithms used in logistic and linear regression, as well as neural networks, aren't so important. Because of this, you don't need to transform variables to a common scale like you might with a Neural Net.\n\nsteps taken: \n\n- First split the data 70% training 30% test\n- Create the Random Forest Classification Model with 60 estimators on entire dataset:\n \n     **precision    recall  f1-score   support**\n\n          0       0.73      0.07      0.12     10868\n          1       0.77      0.99      0.87     34861\n      avg/tot     0.76      0.77      0.69     45729\n    \n- Improve model Performance\n- Create the Random Forest Classification Model with 150 estimators, with a max depth of tree at 25 and minimum sample split 50 on subseted data with selected important features:\n\n     **precision    recall  f1-score   support**\n\n          0       0.65      0.16      0.25      8145\n          1       0.79      0.97      0.87     26152\n\n       avg / tot  0.76      0.78      0.72     34297\n\n\n\n"
    },
    {
      "metadata": {},
      "cell_type": "markdown",
      "source": "**Cross-Validation**"
    },
    {
      "metadata": {
        "collapsed": false,
        "trusted": true
      },
      "cell_type": "code",
      "source": "#Cross - Validation - split the data into 70% training and the remainder for testing the model\nfrom sklearn.cross_validation import train_test_split\nX_train, X_test, Y_train, Y_test = train_test_split(X, Y, test_size=0.30, random_state=0)",
      "execution_count": 38,
      "outputs": []
    },
    {
      "metadata": {},
      "cell_type": "markdown",
      "source": "**Building the Random Forest Model**\n\n"
    },
    {
      "metadata": {
        "collapsed": false,
        "trusted": true
      },
      "cell_type": "code",
      "source": "#Create the Random Forest Classification Model\nnp.random.seed(42)\nfrom sklearn.ensemble import RandomForestClassifier\nRFmodel = RandomForestClassifier(n_estimators=150, min_samples_split=50, max_depth=25, max_features='auto')\n#Prediction on held for testing\nRFpredict = RFmodel.fit(X_train, Y_train).predict(X_test)\nRFpredict",
      "execution_count": 45,
      "outputs": [
        {
          "execution_count": 45,
          "output_type": "execute_result",
          "data": {
            "text/plain": "array([1, 1, 1, ..., 1, 1, 1], dtype=int64)"
          },
          "metadata": {}
        }
      ]
    },
    {
      "metadata": {
        "collapsed": false,
        "trusted": true
      },
      "cell_type": "code",
      "source": "#scale the data \n#from sklearn.preprocessing import StandardScaler\n#scaler = preprocessing.StandardScaler().fit(x)\n#X = scaler.transform(x)\n#Y = cdata.target.values",
      "execution_count": null,
      "outputs": []
    },
    {
      "metadata": {},
      "cell_type": "markdown",
      "source": "**Evaluate Model Performance - Classification Accuracy**"
    },
    {
      "metadata": {
        "collapsed": false,
        "trusted": true
      },
      "cell_type": "code",
      "source": "from sklearn.metrics import confusion_matrix\nfrom sklearn.metrics import classification_report\ncmatrix = confusion_matrix(Y_test, RFpredict)\nprint (cmatrix)",
      "execution_count": 46,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": "[[ 1272  6873]\n [  681 25471]]\n"
        }
      ]
    },
    {
      "metadata": {},
      "cell_type": "markdown",
      "source": "**Classification Report**\n\nThe f1-score is equal to the weighted average of the precision and recall. \n\n"
    },
    {
      "metadata": {
        "collapsed": false,
        "trusted": true
      },
      "cell_type": "code",
      "source": "creport1 = classification_report(Y_test, RFpredict)\nprint (creport1)",
      "execution_count": 47,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": "             precision    recall  f1-score   support\n\n          0       0.65      0.16      0.25      8145\n          1       0.79      0.97      0.87     26152\n\navg / total       0.76      0.78      0.72     34297\n\n"
        }
      ]
    },
    {
      "metadata": {
        "collapsed": true
      },
      "cell_type": "markdown",
      "source": "-------------------------------------------------------------------------------------------\n\n### 2.2 K-Nearest Neighbour Classification\n\nK-Nearest Neighbors often known as the lazy learning algorithm and one of the simple forms of classification. This method is most suitable for un-skewed data as it makes it easier to arrange data into groups. It is also suitable for establishing groups which differ but are not categorically distinct. It uses machine learning functions to group data into loosely knit categories. Each category is given a label. It does so by grouping data where there is a common pattern. It extracts sample data from the set as test data. This data is then classified. All future data is measured in relation to the test data. This is measured by way of Euclidean distance. Euclidean distance is the observed distance between two values.  A majority voting method is used to determine the closeness of the data to the test data.  The votes are weighted according to the distance between the values a neighboring value is always given a stronger weight than a value that is further away."
    },
    {
      "metadata": {},
      "cell_type": "markdown",
      "source": "Euclidean distance is specified by the following formula\n\n$$ dist(p,q) = sqrt{(p1-q2)^2 +(p2-q2)^2+...+(pn-qn)^2} $$"
    },
    {
      "metadata": {},
      "cell_type": "markdown",
      "source": "**Methodolgy**\n\nIn relation to the nearest neighbor classification, the method most used utilized in banking & Insurance to determine the granting or rejecting of loan application will be adapted and attuned to the practice of granting insurance claims. An anonymous data set was provided by BNP Paribas which includes categorical and numerical data. This will determine a likelihood of a claim being successful or not. The train dataset had 133 columns. There is a target of 1 for claims with accelerated approval to meet.  This takes into account the insurers guidelines for the awarding of claims. This data will be used to predict the probability for each claim in the test data set.  An analysis of the normalized data will be created based on nearest neighbor classifications normalization formula using MinMaxScaler(). This model will determine the suitability of nearest neighbor classification for the task described."
    },
    {
      "metadata": {},
      "cell_type": "markdown",
      "source": "**Data Preperation**\n"
    },
    {
      "metadata": {},
      "cell_type": "markdown",
      "source": "__Outlier Detection- Ensemble unsupervised learning method - Isolation Forest__\n\nBack to ensemble trees i.e Random Forests for help!! this time we need isolation forests!\nThe isolation algorithm is an unsupervised machine learning method used to detect abnormal anomalies in data such as outliers. This is once again a randomized & recursive partition of the training data in a tree structure. The number of sub samples and tree size is specified and tuned appropriately. The distance to the outlier is averaged calculating an anomaly detection score: 1 = outlier 0 = close to zero are normal data. "
    },
    {
      "metadata": {
        "collapsed": false,
        "trusted": true
      },
      "cell_type": "code",
      "source": "#A quick look a the data for outliers using a boxplot using seaborn\nax = sns.boxplot(data=cdata, orient=\"t\", palette=\"Set1\")",
      "execution_count": 48,
      "outputs": [
        {
          "output_type": "display_data",
          "data": {
            "image/png": "iVBORw0KGgoAAAANSUhEUgAAAW8AAAECCAYAAAAxVlaQAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\n8JakEvr/9MK6+2UU7mIAAAAASUVORK5CYII=\n",
            "text/plain": "<matplotlib.figure.Figure at 0xe66f3c8>"
          },
          "metadata": {}
        }
      ]
    },
    {
      "metadata": {},
      "cell_type": "markdown",
      "source": "**Cross Validation -Train/test split method:** is by far the most optimal method for training and testing a classifier to unseen data the data into 70% training and the remainder for testing the model."
    },
    {
      "metadata": {
        "collapsed": false,
        "trusted": true
      },
      "cell_type": "code",
      "source": "#Cross Validation -Train Test split method is by far the most optimal method for training and testing a classifier to unseen data the data into 70% training and the remainder for testing the model \n#using the subsetted data determined from the feature importance stage\nX = cdata\nY = cdata.target.values\nX_train, X_test, Y_train, Y_test = train_test_split(X, Y, test_size=0.30, random_state=0)",
      "execution_count": 49,
      "outputs": []
    },
    {
      "metadata": {},
      "cell_type": "markdown",
      "source": "### 2.2.1 - Scaling Data - Min Max Scaler\nSubtracts the minimum of feature X from each value and divide by the range of X.or min - max scaling in sklearn data needs to be a numpy array."
    },
    {
      "metadata": {
        "collapsed": false,
        "trusted": true
      },
      "cell_type": "code",
      "source": "#subtracts the minimum of feature X from each value and divide by the range of X.\nfrom sklearn.preprocessing import MinMaxScaler\nX= np.array(X)#for min - max scaling in sklearn data needs to be a numpy array\nmin_max_scaler = preprocessing.MinMaxScaler()\nrescaled_cdata = min_max_scaler.fit_transform(X)",
      "execution_count": 51,
      "outputs": []
    },
    {
      "metadata": {
        "collapsed": false,
        "trusted": true
      },
      "cell_type": "code",
      "source": "rescaled_cdata",
      "execution_count": 52,
      "outputs": [
        {
          "execution_count": 52,
          "output_type": "execute_result",
          "data": {
            "text/plain": "array([[ 1.        ,  0.04497105,  1.        , ...,  0.33333333,\n         0.02715467,  0.78174538],\n       [ 1.        ,  0.06896055,  0.        , ...,  0.33333333,\n         0.07083828,  0.51540218],\n       [ 1.        ,  0.03022525,  0.        , ...,  0.33333333,\n         0.04132235,  0.56027808],\n       ..., \n       [ 1.        ,  0.12053412,  0.        , ...,  0.66666667,\n         0.11216063,  0.4446567 ],\n       [ 1.        ,  0.04108287,  0.        , ...,  0.33333333,\n         0.06965767,  0.61905567],\n       [ 1.        ,  0.05003309,  1.        , ...,  0.33333333,\n         0.0460449 ,  0.73176489]])"
          },
          "metadata": {}
        }
      ]
    },
    {
      "metadata": {},
      "cell_type": "markdown",
      "source": "#### 2.2.2 - Cross - Validation on rescaled data for KNN\n\nFor this model we have we will used our sub sample date created during our feature importance stage of the analysis, the dataframe produced is \"cdata\". There is a fine balance between over-fitting and under-fitting the training data with this model which is sometimes reffered to as the \"bias-variance trade-off\". Assigning a large K will reduce this effect caused by noise."
    },
    {
      "metadata": {
        "collapsed": false,
        "trusted": true
      },
      "cell_type": "code",
      "source": "#Cross - Validation \nfrom sklearn import cross_validation\nx = rescaled_cdata\ny = cdata.target.values\nx_train, x_test, y_train, y_test = cross_validation.train_test_split(x, y, test_size=0.3, random_state=0)",
      "execution_count": 53,
      "outputs": []
    },
    {
      "metadata": {},
      "cell_type": "markdown",
      "source": "### 2.2.3 - Estimating the number of Neighbours\n\nIn practice, choosing k depends on the difficulty of the concept to be learned and the number of records in the training data.\nTypically, k is set somewhere between 3 and 10.\nOne common practice is to set k equal to the square root of the number of training examples."
    },
    {
      "metadata": {
        "collapsed": false,
        "trusted": true
      },
      "cell_type": "code",
      "source": "#get length of training data to determine the number of neighbours to select for KNN Model\nlen(x_train)",
      "execution_count": 54,
      "outputs": [
        {
          "execution_count": 54,
          "output_type": "execute_result",
          "data": {
            "text/plain": "80024"
          },
          "metadata": {}
        }
      ]
    },
    {
      "metadata": {
        "collapsed": false,
        "trusted": true
      },
      "cell_type": "code",
      "source": "#standard use square root of training data length for n_neighbours = 240\nimport cmath\ntrainlen = 57160\ntrain_sqrt = cmath.sqrt(trainlen)\nprint (train_sqrt)",
      "execution_count": 55,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": "(239.081576036+0j)\n"
        }
      ]
    },
    {
      "metadata": {},
      "cell_type": "markdown",
      "source": "$$n = \\sqrt{57160} = 239.08157$$"
    },
    {
      "metadata": {},
      "cell_type": "markdown",
      "source": "### 2.2.4 - Build the KNN Model"
    },
    {
      "metadata": {
        "collapsed": false,
        "trusted": true
      },
      "cell_type": "code",
      "source": "#Model 1 - Training K Nearest Neighbour Classification\nfrom sklearn.neighbors import KNeighborsClassifier\nclf = KNeighborsClassifier(n_neighbors= 239,weights='uniform')\ny_pred2 = clf.fit(x_train, y_train).predict(x_test)\ny_pred2",
      "execution_count": 64,
      "outputs": [
        {
          "execution_count": 64,
          "output_type": "execute_result",
          "data": {
            "text/plain": "array([1, 0, 1, ..., 0, 1, 1], dtype=int64)"
          },
          "metadata": {}
        }
      ]
    },
    {
      "metadata": {},
      "cell_type": "markdown",
      "source": "**Evaluating Model Performance - Classification Accuracy**"
    },
    {
      "metadata": {},
      "cell_type": "markdown",
      "source": "**Classification Report**"
    },
    {
      "metadata": {
        "collapsed": false,
        "trusted": true
      },
      "cell_type": "code",
      "source": "#Evaluating KNN model performance\ncreport2 = classification_report(y_test, y_pred2)\nprint (creport2)",
      "execution_count": 68,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": "             precision    recall  f1-score   support\n\n          0       1.00      1.00      1.00      8145\n          1       1.00      1.00      1.00     26152\n\navg / total       1.00      1.00      1.00     34297\n\n"
        }
      ]
    },
    {
      "metadata": {},
      "cell_type": "markdown",
      "source": "Data source: https://www.kaggle.com/c/bnp-paribas-cardif-claims-management"
    }
  ],
  "metadata": {
    "kernelspec": {
      "name": "python2",
      "display_name": "Python 2",
      "language": "python"
    },
    "_draft": {
      "nbviewer_url": "https://gist.github.com/26ee49f750948dae2b03870429d51a51"
    },
    "language_info": {
      "mimetype": "text/x-python",
      "nbconvert_exporter": "python",
      "name": "python",
      "pygments_lexer": "ipython2",
      "version": "2.7.11",
      "file_extension": ".py",
      "codemirror_mode": {
        "version": 2,
        "name": "ipython"
      }
    },
    "gist": {
      "id": "26ee49f750948dae2b03870429d51a51",
      "data": {
        "description": "BNP Paribas Cardif Claims Management Problem - Accelarating Claims Management Process.ipynb",
        "public": true
      }
    }
  },
  "nbformat": 4,
  "nbformat_minor": 0
}