SVM Classification.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Importing the libraries "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [],
   "source": [
    "import numpy as np\n",
    "import pandas as pd\n",
    "import statsmodels.formula.api as sm"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Load Data"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>Email No.</th>\n",
       "      <th>the</th>\n",
       "      <th>to</th>\n",
       "      <th>ect</th>\n",
       "      <th>and</th>\n",
       "      <th>for</th>\n",
       "      <th>of</th>\n",
       "      <th>a</th>\n",
       "      <th>you</th>\n",
       "      <th>hou</th>\n",
       "      <th>...</th>\n",
       "      <th>connevey</th>\n",
       "      <th>jay</th>\n",
       "      <th>valued</th>\n",
       "      <th>lay</th>\n",
       "      <th>infrastructure</th>\n",
       "      <th>military</th>\n",
       "      <th>allowing</th>\n",
       "      <th>ff</th>\n",
       "      <th>dry</th>\n",
       "      <th>Prediction</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>Email 1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>2</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>...</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>Email 2</td>\n",
       "      <td>8</td>\n",
       "      <td>13</td>\n",
       "      <td>24</td>\n",
       "      <td>6</td>\n",
       "      <td>6</td>\n",
       "      <td>2</td>\n",
       "      <td>102</td>\n",
       "      <td>1</td>\n",
       "      <td>27</td>\n",
       "      <td>...</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>Email 3</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>8</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>...</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>Email 4</td>\n",
       "      <td>0</td>\n",
       "      <td>5</td>\n",
       "      <td>22</td>\n",
       "      <td>0</td>\n",
       "      <td>5</td>\n",
       "      <td>1</td>\n",
       "      <td>51</td>\n",
       "      <td>2</td>\n",
       "      <td>10</td>\n",
       "      <td>...</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>Email 5</td>\n",
       "      <td>7</td>\n",
       "      <td>6</td>\n",
       "      <td>17</td>\n",
       "      <td>1</td>\n",
       "      <td>5</td>\n",
       "      <td>2</td>\n",
       "      <td>57</td>\n",
       "      <td>0</td>\n",
       "      <td>9</td>\n",
       "      <td>...</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>5 rows × 3002 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "  Email No.  the  to  ect  and  for  of    a  you  hou  ...  connevey  jay  \\\n",
       "0   Email 1    0   0    1    0    0   0    2    0    0  ...         0    0   \n",
       "1   Email 2    8  13   24    6    6   2  102    1   27  ...         0    0   \n",
       "2   Email 3    0   0    1    0    0   0    8    0    0  ...         0    0   \n",
       "3   Email 4    0   5   22    0    5   1   51    2   10  ...         0    0   \n",
       "4   Email 5    7   6   17    1    5   2   57    0    9  ...         0    0   \n",
       "\n",
       "   valued  lay  infrastructure  military  allowing  ff  dry  Prediction  \n",
       "0       0    0               0         0         0   0    0           0  \n",
       "1       0    0               0         0         0   1    0           0  \n",
       "2       0    0               0         0         0   0    0           0  \n",
       "3       0    0               0         0         0   0    0           0  \n",
       "4       0    0               0         0         0   1    0           0  \n",
       "\n",
       "[5 rows x 3002 columns]"
      ]
     },
     "execution_count": 2,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "dataset=pd.read_csv('emails.csv') \n",
    "dataset.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>the</th>\n",
       "      <th>to</th>\n",
       "      <th>ect</th>\n",
       "      <th>and</th>\n",
       "      <th>for</th>\n",
       "      <th>of</th>\n",
       "      <th>a</th>\n",
       "      <th>you</th>\n",
       "      <th>hou</th>\n",
       "      <th>in</th>\n",
       "      <th>...</th>\n",
       "      <th>connevey</th>\n",
       "      <th>jay</th>\n",
       "      <th>valued</th>\n",
       "      <th>lay</th>\n",
       "      <th>infrastructure</th>\n",
       "      <th>military</th>\n",
       "      <th>allowing</th>\n",
       "      <th>ff</th>\n",
       "      <th>dry</th>\n",
       "      <th>Prediction</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>count</th>\n",
       "      <td>5172.000000</td>\n",
       "      <td>5172.000000</td>\n",
       "      <td>5172.000000</td>\n",
       "      <td>5172.000000</td>\n",
       "      <td>5172.000000</td>\n",
       "      <td>5172.000000</td>\n",
       "      <td>5172.000000</td>\n",
       "      <td>5172.000000</td>\n",
       "      <td>5172.000000</td>\n",
       "      <td>5172.000000</td>\n",
       "      <td>...</td>\n",
       "      <td>5172.000000</td>\n",
       "      <td>5172.000000</td>\n",
       "      <td>5172.000000</td>\n",
       "      <td>5172.000000</td>\n",
       "      <td>5172.000000</td>\n",
       "      <td>5172.000000</td>\n",
       "      <td>5172.000000</td>\n",
       "      <td>5172.000000</td>\n",
       "      <td>5172.000000</td>\n",
       "      <td>5172.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>mean</th>\n",
       "      <td>6.640565</td>\n",
       "      <td>6.188128</td>\n",
       "      <td>5.143852</td>\n",
       "      <td>3.075599</td>\n",
       "      <td>3.124710</td>\n",
       "      <td>2.627030</td>\n",
       "      <td>55.517401</td>\n",
       "      <td>2.466551</td>\n",
       "      <td>2.024362</td>\n",
       "      <td>10.600155</td>\n",
       "      <td>...</td>\n",
       "      <td>0.005027</td>\n",
       "      <td>0.012568</td>\n",
       "      <td>0.010634</td>\n",
       "      <td>0.098028</td>\n",
       "      <td>0.004254</td>\n",
       "      <td>0.006574</td>\n",
       "      <td>0.004060</td>\n",
       "      <td>0.914733</td>\n",
       "      <td>0.006961</td>\n",
       "      <td>0.290023</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>std</th>\n",
       "      <td>11.745009</td>\n",
       "      <td>9.534576</td>\n",
       "      <td>14.101142</td>\n",
       "      <td>6.045970</td>\n",
       "      <td>4.680522</td>\n",
       "      <td>6.229845</td>\n",
       "      <td>87.574172</td>\n",
       "      <td>4.314444</td>\n",
       "      <td>6.967878</td>\n",
       "      <td>19.281892</td>\n",
       "      <td>...</td>\n",
       "      <td>0.105788</td>\n",
       "      <td>0.199682</td>\n",
       "      <td>0.116693</td>\n",
       "      <td>0.569532</td>\n",
       "      <td>0.096252</td>\n",
       "      <td>0.138908</td>\n",
       "      <td>0.072145</td>\n",
       "      <td>2.780203</td>\n",
       "      <td>0.098086</td>\n",
       "      <td>0.453817</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>min</th>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>...</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>25%</th>\n",
       "      <td>0.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>12.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>...</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>50%</th>\n",
       "      <td>3.000000</td>\n",
       "      <td>3.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>2.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>28.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>5.000000</td>\n",
       "      <td>...</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>75%</th>\n",
       "      <td>8.000000</td>\n",
       "      <td>7.000000</td>\n",
       "      <td>4.000000</td>\n",
       "      <td>3.000000</td>\n",
       "      <td>4.000000</td>\n",
       "      <td>2.000000</td>\n",
       "      <td>62.250000</td>\n",
       "      <td>3.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>12.000000</td>\n",
       "      <td>...</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>1.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>max</th>\n",
       "      <td>210.000000</td>\n",
       "      <td>132.000000</td>\n",
       "      <td>344.000000</td>\n",
       "      <td>89.000000</td>\n",
       "      <td>47.000000</td>\n",
       "      <td>77.000000</td>\n",
       "      <td>1898.000000</td>\n",
       "      <td>70.000000</td>\n",
       "      <td>167.000000</td>\n",
       "      <td>223.000000</td>\n",
       "      <td>...</td>\n",
       "      <td>4.000000</td>\n",
       "      <td>7.000000</td>\n",
       "      <td>2.000000</td>\n",
       "      <td>12.000000</td>\n",
       "      <td>3.000000</td>\n",
       "      <td>4.000000</td>\n",
       "      <td>3.000000</td>\n",
       "      <td>114.000000</td>\n",
       "      <td>4.000000</td>\n",
       "      <td>1.000000</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>8 rows × 3001 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "               the           to          ect          and          for  \\\n",
       "count  5172.000000  5172.000000  5172.000000  5172.000000  5172.000000   \n",
       "mean      6.640565     6.188128     5.143852     3.075599     3.124710   \n",
       "std      11.745009     9.534576    14.101142     6.045970     4.680522   \n",
       "min       0.000000     0.000000     1.000000     0.000000     0.000000   \n",
       "25%       0.000000     1.000000     1.000000     0.000000     1.000000   \n",
       "50%       3.000000     3.000000     1.000000     1.000000     2.000000   \n",
       "75%       8.000000     7.000000     4.000000     3.000000     4.000000   \n",
       "max     210.000000   132.000000   344.000000    89.000000    47.000000   \n",
       "\n",
       "                of            a          you          hou           in  ...  \\\n",
       "count  5172.000000  5172.000000  5172.000000  5172.000000  5172.000000  ...   \n",
       "mean      2.627030    55.517401     2.466551     2.024362    10.600155  ...   \n",
       "std       6.229845    87.574172     4.314444     6.967878    19.281892  ...   \n",
       "min       0.000000     0.000000     0.000000     0.000000     0.000000  ...   \n",
       "25%       0.000000    12.000000     0.000000     0.000000     1.000000  ...   \n",
       "50%       1.000000    28.000000     1.000000     0.000000     5.000000  ...   \n",
       "75%       2.000000    62.250000     3.000000     1.000000    12.000000  ...   \n",
       "max      77.000000  1898.000000    70.000000   167.000000   223.000000  ...   \n",
       "\n",
       "          connevey          jay       valued          lay  infrastructure  \\\n",
       "count  5172.000000  5172.000000  5172.000000  5172.000000     5172.000000   \n",
       "mean      0.005027     0.012568     0.010634     0.098028        0.004254   \n",
       "std       0.105788     0.199682     0.116693     0.569532        0.096252   \n",
       "min       0.000000     0.000000     0.000000     0.000000        0.000000   \n",
       "25%       0.000000     0.000000     0.000000     0.000000        0.000000   \n",
       "50%       0.000000     0.000000     0.000000     0.000000        0.000000   \n",
       "75%       0.000000     0.000000     0.000000     0.000000        0.000000   \n",
       "max       4.000000     7.000000     2.000000    12.000000        3.000000   \n",
       "\n",
       "          military     allowing           ff          dry   Prediction  \n",
       "count  5172.000000  5172.000000  5172.000000  5172.000000  5172.000000  \n",
       "mean      0.006574     0.004060     0.914733     0.006961     0.290023  \n",
       "std       0.138908     0.072145     2.780203     0.098086     0.453817  \n",
       "min       0.000000     0.000000     0.000000     0.000000     0.000000  \n",
       "25%       0.000000     0.000000     0.000000     0.000000     0.000000  \n",
       "50%       0.000000     0.000000     0.000000     0.000000     0.000000  \n",
       "75%       0.000000     0.000000     1.000000     0.000000     1.000000  \n",
       "max       4.000000     3.000000   114.000000     4.000000     1.000000  \n",
       "\n",
       "[8 rows x 3001 columns]"
      ]
     },
     "execution_count": 3,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "dataset.describe()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>Email No.</th>\n",
       "      <th>the</th>\n",
       "      <th>to</th>\n",
       "      <th>ect</th>\n",
       "      <th>and</th>\n",
       "      <th>for</th>\n",
       "      <th>of</th>\n",
       "      <th>a</th>\n",
       "      <th>you</th>\n",
       "      <th>hou</th>\n",
       "      <th>...</th>\n",
       "      <th>connevey</th>\n",
       "      <th>jay</th>\n",
       "      <th>valued</th>\n",
       "      <th>lay</th>\n",
       "      <th>infrastructure</th>\n",
       "      <th>military</th>\n",
       "      <th>allowing</th>\n",
       "      <th>ff</th>\n",
       "      <th>dry</th>\n",
       "      <th>Prediction</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>0 rows × 3002 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "Empty DataFrame\n",
       "Columns: [Email No., the, to, ect, and, for, of, a, you, hou, in, on, is, this, enron, i, be, that, will, have, with, your, at, we, s, are, it, by, com, as, from, gas, or, not, me, deal, if, meter, hpl, please, re, e, any, our, corp, can, d, all, has, was, know, need, an, forwarded, new, t, may, up, j, mmbtu, should, do, am, get, out, see, no, there, price, daren, but, been, company, l, these, let, so, would, m, into, xls, farmer, attached, us, information, they, message, day, time, my, one, what, only, http, th, volume, mail, contract, which, month, ...]\n",
       "Index: []\n",
       "\n",
       "[0 rows x 3002 columns]"
      ]
     },
     "execution_count": 4,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# verify that there are no null columns in the dataset\n",
    "dataset[dataset.isnull().any(axis=1)]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [],
   "source": [
    "categorical = [var for var in dataset.columns if dataset[var].dtype=='O']\n",
    "numerical = [var for var in dataset.columns if dataset[var].dtype!='O']"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "There are 1 categorical variables : \n",
      " ['Email No.']\n"
     ]
    }
   ],
   "source": [
    "print('There are {} categorical variables : \\n'.format(len(categorical)), categorical)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Email No.  contains  5172  labels\n"
     ]
    }
   ],
   "source": [
    "# check for cardinality in categorical variables\n",
    "for var in categorical:\n",
    "    print(var, ' contains ', len(dataset[var].unique()), ' labels')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "          the      to     ect     and     for      of       a     you     hou  \\\n",
      "count  5172.0  5172.0  5172.0  5172.0  5172.0  5172.0  5172.0  5172.0  5172.0   \n",
      "mean      7.0     6.0     5.0     3.0     3.0     3.0    56.0     2.0     2.0   \n",
      "std      12.0    10.0    14.0     6.0     5.0     6.0    88.0     4.0     7.0   \n",
      "min       0.0     0.0     1.0     0.0     0.0     0.0     0.0     0.0     0.0   \n",
      "25%       0.0     1.0     1.0     0.0     1.0     0.0    12.0     0.0     0.0   \n",
      "50%       3.0     3.0     1.0     1.0     2.0     1.0    28.0     1.0     0.0   \n",
      "75%       8.0     7.0     4.0     3.0     4.0     2.0    62.0     3.0     1.0   \n",
      "max     210.0   132.0   344.0    89.0    47.0    77.0  1898.0    70.0   167.0   \n",
      "\n",
      "           in  ...  connevey     jay  valued     lay  infrastructure  \\\n",
      "count  5172.0  ...    5172.0  5172.0  5172.0  5172.0          5172.0   \n",
      "mean     11.0  ...       0.0     0.0     0.0     0.0             0.0   \n",
      "std      19.0  ...       0.0     0.0     0.0     1.0             0.0   \n",
      "min       0.0  ...       0.0     0.0     0.0     0.0             0.0   \n",
      "25%       1.0  ...       0.0     0.0     0.0     0.0             0.0   \n",
      "50%       5.0  ...       0.0     0.0     0.0     0.0             0.0   \n",
      "75%      12.0  ...       0.0     0.0     0.0     0.0             0.0   \n",
      "max     223.0  ...       4.0     7.0     2.0    12.0             3.0   \n",
      "\n",
      "       military  allowing      ff     dry  Prediction  \n",
      "count    5172.0    5172.0  5172.0  5172.0      5172.0  \n",
      "mean        0.0       0.0     1.0     0.0         0.0  \n",
      "std         0.0       0.0     3.0     0.0         0.0  \n",
      "min         0.0       0.0     0.0     0.0         0.0  \n",
      "25%         0.0       0.0     0.0     0.0         0.0  \n",
      "50%         0.0       0.0     0.0     0.0         0.0  \n",
      "75%         0.0       0.0     1.0     0.0         1.0  \n",
      "max         4.0       3.0   114.0     4.0         1.0  \n",
      "\n",
      "[8 rows x 3001 columns] 2\n"
     ]
    }
   ],
   "source": [
    "# view summary statistics in numerical variables to check for outliers\n",
    "print(round(dataset[numerical].describe()),2)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Data Preprocessing"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>Email No.</th>\n",
       "      <th>the</th>\n",
       "      <th>to</th>\n",
       "      <th>ect</th>\n",
       "      <th>and</th>\n",
       "      <th>for</th>\n",
       "      <th>of</th>\n",
       "      <th>a</th>\n",
       "      <th>you</th>\n",
       "      <th>hou</th>\n",
       "      <th>...</th>\n",
       "      <th>connevey</th>\n",
       "      <th>jay</th>\n",
       "      <th>valued</th>\n",
       "      <th>lay</th>\n",
       "      <th>infrastructure</th>\n",
       "      <th>military</th>\n",
       "      <th>allowing</th>\n",
       "      <th>ff</th>\n",
       "      <th>dry</th>\n",
       "      <th>Prediction</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>2</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>...</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>1111</td>\n",
       "      <td>8</td>\n",
       "      <td>13</td>\n",
       "      <td>24</td>\n",
       "      <td>6</td>\n",
       "      <td>6</td>\n",
       "      <td>2</td>\n",
       "      <td>102</td>\n",
       "      <td>1</td>\n",
       "      <td>27</td>\n",
       "      <td>...</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>2222</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>8</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>...</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>3333</td>\n",
       "      <td>0</td>\n",
       "      <td>5</td>\n",
       "      <td>22</td>\n",
       "      <td>0</td>\n",
       "      <td>5</td>\n",
       "      <td>1</td>\n",
       "      <td>51</td>\n",
       "      <td>2</td>\n",
       "      <td>10</td>\n",
       "      <td>...</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>4444</td>\n",
       "      <td>7</td>\n",
       "      <td>6</td>\n",
       "      <td>17</td>\n",
       "      <td>1</td>\n",
       "      <td>5</td>\n",
       "      <td>2</td>\n",
       "      <td>57</td>\n",
       "      <td>0</td>\n",
       "      <td>9</td>\n",
       "      <td>...</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>5 rows × 3002 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "   Email No.  the  to  ect  and  for  of    a  you  hou  ...  connevey  jay  \\\n",
       "0          0    0   0    1    0    0   0    2    0    0  ...         0    0   \n",
       "1       1111    8  13   24    6    6   2  102    1   27  ...         0    0   \n",
       "2       2222    0   0    1    0    0   0    8    0    0  ...         0    0   \n",
       "3       3333    0   5   22    0    5   1   51    2   10  ...         0    0   \n",
       "4       4444    7   6   17    1    5   2   57    0    9  ...         0    0   \n",
       "\n",
       "   valued  lay  infrastructure  military  allowing  ff  dry  Prediction  \n",
       "0       0    0               0         0         0   0    0           0  \n",
       "1       0    0               0         0         0   1    0           0  \n",
       "2       0    0               0         0         0   0    0           0  \n",
       "3       0    0               0         0         0   0    0           0  \n",
       "4       0    0               0         0         0   1    0           0  \n",
       "\n",
       "[5 rows x 3002 columns]"
      ]
     },
     "execution_count": 9,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# use LabelEncoder to replace purchased (dependent variable) with 0 and 1 \n",
    "from sklearn.preprocessing import LabelEncoder\n",
    "dataset['Email No.']= LabelEncoder().fit_transform(dataset['Email No.'])\n",
    "dataset.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {},
   "outputs": [],
   "source": [
    "y = dataset['Prediction']\n",
    "x = dataset.drop(['Prediction'], axis=1)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "   Email No.  the  to  ect  and  for  of    a  you  hou  ...  enhancements  \\\n",
      "0          0    0   0    1    0    0   0    2    0    0  ...             0   \n",
      "1       1111    8  13   24    6    6   2  102    1   27  ...             0   \n",
      "2       2222    0   0    1    0    0   0    8    0    0  ...             0   \n",
      "3       3333    0   5   22    0    5   1   51    2   10  ...             0   \n",
      "4       4444    7   6   17    1    5   2   57    0    9  ...             0   \n",
      "\n",
      "   connevey  jay  valued  lay  infrastructure  military  allowing  ff  dry  \n",
      "0         0    0       0    0               0         0         0   0    0  \n",
      "1         0    0       0    0               0         0         0   1    0  \n",
      "2         0    0       0    0               0         0         0   0    0  \n",
      "3         0    0       0    0               0         0         0   0    0  \n",
      "4         0    0       0    0               0         0         0   1    0  \n",
      "\n",
      "[5 rows x 3001 columns]\n"
     ]
    }
   ],
   "source": [
    "print(x.head())"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "0    0\n",
      "1    0\n",
      "2    0\n",
      "3    0\n",
      "4    0\n",
      "Name: Prediction, dtype: int64\n"
     ]
    }
   ],
   "source": [
    "print(y.head())"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Splitting the dataset into training and test set  "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "metadata": {},
   "outputs": [],
   "source": [
    "from sklearn.model_selection import train_test_split\n",
    "x_train,x_test,y_train,y_test = train_test_split(x,y,test_size=0.3,random_state = 0) # func returns train and test data. It takes dataset and then split size test_size =0.3 means 30% data is for test and rest for training and random_state \n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "      Email No.  the  to  ect  and  for  of    a  you  hou  ...  enhancements  \\\n",
      "3459       2735    5   4    1    2    2   3   27    7    0  ...             0   \n",
      "1385        430    3   6    4    6    0   2   57    2    0  ...             0   \n",
      "1380        425    1   0    1    0    0   1    8    0    0  ...             0   \n",
      "4462       3849   37  16    5   22    5  19  228    6    2  ...             0   \n",
      "3840       3158    2   1    1    0    2   0   10    0    0  ...             0   \n",
      "\n",
      "      connevey  jay  valued  lay  infrastructure  military  allowing  ff  dry  \n",
      "3459         0    0       0    0               0         0         0   0    0  \n",
      "1385         0    0       0    0               0         0         0   1    0  \n",
      "1380         0    0       0    0               0         0         0   0    0  \n",
      "4462         0    0       0    2               0         0         0   1    0  \n",
      "3840         0    0       0    0               0         0         0   0    0  \n",
      "\n",
      "[5 rows x 3001 columns]\n"
     ]
    }
   ],
   "source": [
    "print(x_train.head())"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "      Email No.  the  to  ect  and  for  of    a  you  hou  ...  enhancements  \\\n",
      "3324       2585   14   7    2    2    2   4   37    0    1  ...             0   \n",
      "15          667    6   2    1    0    2   0   36    3    1  ...             0   \n",
      "4950       4391   40   6    4    6    5  11  130    3    0  ...             0   \n",
      "3964       3295   42  19    1    8    7   7  214    1    3  ...             0   \n",
      "2315       1464    8  14    8    3    3   0   87    0    4  ...             0   \n",
      "\n",
      "      connevey  jay  valued  lay  infrastructure  military  allowing  ff  dry  \n",
      "3324         0    0       0    0               0         0         0   0    0  \n",
      "15           0    0       0    0               0         0         0   0    0  \n",
      "4950         0    0       0    0               0         0         0   1    0  \n",
      "3964         0    0       0    1               0         4         0   3    0  \n",
      "2315         0    0       0    0               0         0         0   5    0  \n",
      "\n",
      "[5 rows x 3001 columns]\n"
     ]
    }
   ],
   "source": [
    "print(x_test.head())"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "3459    1\n",
      "1385    0\n",
      "1380    0\n",
      "4462    1\n",
      "3840    0\n",
      "1452    1\n",
      "2849    0\n",
      "3145    0\n",
      "1271    0\n",
      "1021    0\n",
      "Name: Prediction, dtype: int64\n"
     ]
    }
   ],
   "source": [
    "print(y_train[:10])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "3324    0\n",
      "15      0\n",
      "4950    0\n",
      "3964    1\n",
      "2315    0\n",
      "861     1\n",
      "2350    0\n",
      "1767    0\n",
      "965     0\n",
      "2630    1\n",
      "Name: Prediction, dtype: int64\n"
     ]
    }
   ],
   "source": [
    "print(y_test[:10])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "metadata": {},
   "outputs": [],
   "source": [
    "from sklearn.preprocessing import StandardScaler\n",
    "scaler = StandardScaler()\n",
    "x_train=scaler.fit_transform(x_train) # apply on whole x data \n",
    "x_test=scaler.transform(x_test)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Build Model "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 19,
   "metadata": {},
   "outputs": [],
   "source": [
    "from sklearn.svm import SVC \n",
    "svr_lin = SVC(kernel='linear', C=100, gamma='auto')\n",
    "svr_lin.fit(x_train,y_train)\n",
    "y_pred_lin= svr_lin.predict(x_test)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 20,
   "metadata": {},
   "outputs": [],
   "source": [
    "svr_rbf = SVC(kernel='rbf', C=100, gamma=0.1)\n",
    "svr_rbf.fit(x_train,y_train)\n",
    "y_pred_rbf= svr_rbf.predict(x_test)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 21,
   "metadata": {},
   "outputs": [],
   "source": [
    "# poly kernel type to be used in the algorithm\n",
    "svr_poly = SVC(kernel='poly', C=100, gamma='auto', degree=3,  coef0=1)\n",
    "svr_poly.fit(x_train,y_train)\n",
    "y_pred_poly= svr_poly.predict(x_test)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 22,
   "metadata": {},
   "outputs": [],
   "source": [
    "# sigmoid kernel type to be used in the algorithm\n",
    "svr_sig = SVC(kernel='sigmoid', C=1, gamma='auto',  coef0=1)\n",
    "svr_sig.fit(x_train,y_train)\n",
    "y_pred_sig= svr_sig.predict(x_test)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Evaluate Model "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 23,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Evaluate linear model"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 24,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "[[1057   54]\n",
      " [  38  403]]\n"
     ]
    }
   ],
   "source": [
    "from sklearn.metrics import accuracy_score, confusion_matrix, classification_report, average_precision_score\n",
    "cm = confusion_matrix(y_test,y_pred_lin)\n",
    "print(cm)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 25,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "              precision    recall  f1-score   support\n",
      "\n",
      "           0       0.97      0.95      0.96      1111\n",
      "           1       0.88      0.91      0.90       441\n",
      "\n",
      "    accuracy                           0.94      1552\n",
      "   macro avg       0.92      0.93      0.93      1552\n",
      "weighted avg       0.94      0.94      0.94      1552\n",
      "\n"
     ]
    }
   ],
   "source": [
    "cr = classification_report(y_test,y_pred_lin)\n",
    "print(cr)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 26,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0.9407216494845361"
      ]
     },
     "execution_count": 26,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "accuracy_score(y_test,y_pred_lin)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 27,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0.8303365632536637"
      ]
     },
     "execution_count": 27,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "average_precision_score(y_test,y_pred_lin)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 28,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Evaluate rbf model"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 29,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "[[1108    3]\n",
      " [ 412   29]]\n"
     ]
    }
   ],
   "source": [
    "cm = confusion_matrix(y_test,y_pred_rbf)\n",
    "print(cm)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 30,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "              precision    recall  f1-score   support\n",
      "\n",
      "           0       0.73      1.00      0.84      1111\n",
      "           1       0.91      0.07      0.12       441\n",
      "\n",
      "    accuracy                           0.73      1552\n",
      "   macro avg       0.82      0.53      0.48      1552\n",
      "weighted avg       0.78      0.73      0.64      1552\n",
      "\n"
     ]
    }
   ],
   "source": [
    "cr = classification_report(y_test,y_pred_rbf)\n",
    "print(cr)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 31,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0.7326030927835051"
      ]
     },
     "execution_count": 31,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "accuracy_score(y_test,y_pred_rbf)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 32,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0.32505858872758725"
      ]
     },
     "execution_count": 32,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "average_precision_score(y_test,y_pred_rbf)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 33,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Evaluate poly model"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 34,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "[[1067   44]\n",
      " [  44  397]]\n"
     ]
    }
   ],
   "source": [
    "cm = confusion_matrix(y_test,y_pred_poly)\n",
    "print(cm)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 35,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "              precision    recall  f1-score   support\n",
      "\n",
      "           0       0.96      0.96      0.96      1111\n",
      "           1       0.90      0.90      0.90       441\n",
      "\n",
      "    accuracy                           0.94      1552\n",
      "   macro avg       0.93      0.93      0.93      1552\n",
      "weighted avg       0.94      0.94      0.94      1552\n",
      "\n"
     ]
    }
   ],
   "source": [
    "cr = classification_report(y_test,y_pred_poly)\n",
    "print(cr)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 36,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0.9432989690721649"
      ]
     },
     "execution_count": 36,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "accuracy_score(y_test,y_pred_poly)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 37,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0.8387587301481284"
      ]
     },
     "execution_count": 37,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "average_precision_score(y_test,y_pred_poly)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 38,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Evaluate sigmoid model"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 39,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "[[1058   53]\n",
      " [ 158  283]]\n"
     ]
    }
   ],
   "source": [
    "cm = confusion_matrix(y_test,y_pred_sig)\n",
    "print(cm)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 40,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "              precision    recall  f1-score   support\n",
      "\n",
      "           0       0.87      0.95      0.91      1111\n",
      "           1       0.84      0.64      0.73       441\n",
      "\n",
      "    accuracy                           0.86      1552\n",
      "   macro avg       0.86      0.80      0.82      1552\n",
      "weighted avg       0.86      0.86      0.86      1552\n",
      "\n"
     ]
    }
   ],
   "source": [
    "cr = classification_report(y_test,y_pred_sig)\n",
    "print(cr)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 41,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0.8640463917525774"
      ]
     },
     "execution_count": 41,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "accuracy_score(y_test,y_pred_sig)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 42,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0.6423032598737416"
      ]
     },
     "execution_count": 42,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "average_precision_score(y_test,y_pred_sig)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.8.3"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 4
}