ImageSegmentation.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [],
   "source": [
    "import pandas as pd\n",
    "import numpy as np\n",
    "import matplotlib.pyplot as plt\n",
    "import seaborn as sns\n",
    "sns.set()"
   ]
  },
  {
   "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>red_pixel</th>\n",
       "      <th>green_pixel</th>\n",
       "      <th>blue_pixel</th>\n",
       "      <th>mean_red</th>\n",
       "      <th>mean_green</th>\n",
       "      <th>mean_blue</th>\n",
       "      <th>std_red</th>\n",
       "      <th>std_green</th>\n",
       "      <th>std_blue</th>\n",
       "      <th>corr_rg</th>\n",
       "      <th>corr_rb</th>\n",
       "      <th>corr_gb</th>\n",
       "      <th>inside</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>43</td>\n",
       "      <td>72</td>\n",
       "      <td>6</td>\n",
       "      <td>41.061224</td>\n",
       "      <td>71.000000</td>\n",
       "      <td>7.408163</td>\n",
       "      <td>6.364468</td>\n",
       "      <td>6.144518</td>\n",
       "      <td>5.875992</td>\n",
       "      <td>0.984228</td>\n",
       "      <td>0.913393</td>\n",
       "      <td>0.920780</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>48</td>\n",
       "      <td>77</td>\n",
       "      <td>13</td>\n",
       "      <td>41.755102</td>\n",
       "      <td>71.591837</td>\n",
       "      <td>8.387755</td>\n",
       "      <td>6.634882</td>\n",
       "      <td>6.375714</td>\n",
       "      <td>6.577067</td>\n",
       "      <td>0.982776</td>\n",
       "      <td>0.910389</td>\n",
       "      <td>0.904618</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>46</td>\n",
       "      <td>76</td>\n",
       "      <td>12</td>\n",
       "      <td>42.326531</td>\n",
       "      <td>72.244898</td>\n",
       "      <td>9.591837</td>\n",
       "      <td>6.996757</td>\n",
       "      <td>6.579283</td>\n",
       "      <td>6.933852</td>\n",
       "      <td>0.982015</td>\n",
       "      <td>0.925678</td>\n",
       "      <td>0.901819</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>44</td>\n",
       "      <td>74</td>\n",
       "      <td>12</td>\n",
       "      <td>43.938776</td>\n",
       "      <td>73.918367</td>\n",
       "      <td>11.285714</td>\n",
       "      <td>7.426945</td>\n",
       "      <td>7.233247</td>\n",
       "      <td>7.687785</td>\n",
       "      <td>0.980029</td>\n",
       "      <td>0.933559</td>\n",
       "      <td>0.897007</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>45</td>\n",
       "      <td>75</td>\n",
       "      <td>13</td>\n",
       "      <td>44.857143</td>\n",
       "      <td>75.000000</td>\n",
       "      <td>12.632653</td>\n",
       "      <td>9.023778</td>\n",
       "      <td>9.122746</td>\n",
       "      <td>8.993635</td>\n",
       "      <td>0.983698</td>\n",
       "      <td>0.933300</td>\n",
       "      <td>0.887997</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   red_pixel  green_pixel  blue_pixel   mean_red  mean_green  mean_blue  \\\n",
       "0         43           72           6  41.061224   71.000000   7.408163   \n",
       "1         48           77          13  41.755102   71.591837   8.387755   \n",
       "2         46           76          12  42.326531   72.244898   9.591837   \n",
       "3         44           74          12  43.938776   73.918367  11.285714   \n",
       "4         45           75          13  44.857143   75.000000  12.632653   \n",
       "\n",
       "    std_red  std_green  std_blue   corr_rg   corr_rb   corr_gb  inside  \n",
       "0  6.364468   6.144518  5.875992  0.984228  0.913393  0.920780       1  \n",
       "1  6.634882   6.375714  6.577067  0.982776  0.910389  0.904618       1  \n",
       "2  6.996757   6.579283  6.933852  0.982015  0.925678  0.901819       1  \n",
       "3  7.426945   7.233247  7.687785  0.980029  0.933559  0.897007       1  \n",
       "4  9.023778   9.122746  8.993635  0.983698  0.933300  0.887997       1  "
      ]
     },
     "execution_count": 2,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "data_set_url = 'training_set/output_final.csv'\n",
    "training_set = pd.read_csv(data_set_url, header=0, sep=',') \n",
    "training_set.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [],
   "source": [
    "header = ['red_pixel','green_pixel','blue_pixel','mean_red','mean_green','mean_blue','std_red','std_green','std_blue','corr_rg','corr_rb','corr_gb','inside']"
   ]
  },
  {
   "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>red_pixel</th>\n",
       "      <th>green_pixel</th>\n",
       "      <th>blue_pixel</th>\n",
       "      <th>mean_red</th>\n",
       "      <th>mean_green</th>\n",
       "      <th>mean_blue</th>\n",
       "      <th>std_red</th>\n",
       "      <th>std_green</th>\n",
       "      <th>std_blue</th>\n",
       "      <th>corr_rg</th>\n",
       "      <th>corr_rb</th>\n",
       "      <th>corr_gb</th>\n",
       "      <th>inside</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>44</td>\n",
       "      <td>57</td>\n",
       "      <td>4</td>\n",
       "      <td>46.836735</td>\n",
       "      <td>59.571429</td>\n",
       "      <td>6.653061</td>\n",
       "      <td>2.682878</td>\n",
       "      <td>2.747912</td>\n",
       "      <td>2.684430</td>\n",
       "      <td>0.920630</td>\n",
       "      <td>0.964088</td>\n",
       "      <td>0.986892</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>50</td>\n",
       "      <td>63</td>\n",
       "      <td>10</td>\n",
       "      <td>46.367347</td>\n",
       "      <td>59.142857</td>\n",
       "      <td>6.224490</td>\n",
       "      <td>2.154197</td>\n",
       "      <td>2.128523</td>\n",
       "      <td>2.062941</td>\n",
       "      <td>0.865366</td>\n",
       "      <td>0.936645</td>\n",
       "      <td>0.978010</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>42</td>\n",
       "      <td>55</td>\n",
       "      <td>2</td>\n",
       "      <td>45.775510</td>\n",
       "      <td>58.591837</td>\n",
       "      <td>5.673469</td>\n",
       "      <td>2.224771</td>\n",
       "      <td>2.098769</td>\n",
       "      <td>2.054242</td>\n",
       "      <td>0.863264</td>\n",
       "      <td>0.935106</td>\n",
       "      <td>0.977335</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>42</td>\n",
       "      <td>55</td>\n",
       "      <td>2</td>\n",
       "      <td>45.428571</td>\n",
       "      <td>58.367347</td>\n",
       "      <td>5.551020</td>\n",
       "      <td>2.347382</td>\n",
       "      <td>2.274023</td>\n",
       "      <td>2.100158</td>\n",
       "      <td>0.907187</td>\n",
       "      <td>0.941485</td>\n",
       "      <td>0.944735</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>45</td>\n",
       "      <td>58</td>\n",
       "      <td>5</td>\n",
       "      <td>45.142857</td>\n",
       "      <td>58.000000</td>\n",
       "      <td>5.387755</td>\n",
       "      <td>2.080031</td>\n",
       "      <td>2.175935</td>\n",
       "      <td>1.925302</td>\n",
       "      <td>0.870253</td>\n",
       "      <td>0.939132</td>\n",
       "      <td>0.871991</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   red_pixel  green_pixel  blue_pixel   mean_red  mean_green  mean_blue  \\\n",
       "0         44           57           4  46.836735   59.571429   6.653061   \n",
       "1         50           63          10  46.367347   59.142857   6.224490   \n",
       "2         42           55           2  45.775510   58.591837   5.673469   \n",
       "3         42           55           2  45.428571   58.367347   5.551020   \n",
       "4         45           58           5  45.142857   58.000000   5.387755   \n",
       "\n",
       "    std_red  std_green  std_blue   corr_rg   corr_rb   corr_gb  inside  \n",
       "0  2.682878   2.747912  2.684430  0.920630  0.964088  0.986892       1  \n",
       "1  2.154197   2.128523  2.062941  0.865366  0.936645  0.978010       1  \n",
       "2  2.224771   2.098769  2.054242  0.863264  0.935106  0.977335       1  \n",
       "3  2.347382   2.274023  2.100158  0.907187  0.941485  0.944735       1  \n",
       "4  2.080031   2.175935  1.925302  0.870253  0.939132  0.871991       1  "
      ]
     },
     "execution_count": 3,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "test_set_url = 'test_set/output_test_set.csv'\n",
    "test_set = pd.read_csv(test_set_url, header=0, sep=',') \n",
    "test_set.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "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>red_pixel</th>\n",
       "      <th>green_pixel</th>\n",
       "      <th>blue_pixel</th>\n",
       "      <th>mean_red</th>\n",
       "      <th>mean_green</th>\n",
       "      <th>mean_blue</th>\n",
       "      <th>std_red</th>\n",
       "      <th>std_green</th>\n",
       "      <th>std_blue</th>\n",
       "      <th>corr_rg</th>\n",
       "      <th>corr_rb</th>\n",
       "      <th>corr_gb</th>\n",
       "      <th>inside</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>count</th>\n",
       "      <td>997941.000000</td>\n",
       "      <td>997941.000000</td>\n",
       "      <td>997941.000000</td>\n",
       "      <td>997941.000000</td>\n",
       "      <td>997941.000000</td>\n",
       "      <td>997941.000000</td>\n",
       "      <td>997941.000000</td>\n",
       "      <td>997941.000000</td>\n",
       "      <td>997941.000000</td>\n",
       "      <td>997941.000000</td>\n",
       "      <td>997941.000000</td>\n",
       "      <td>997941.000000</td>\n",
       "      <td>997941.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>mean</th>\n",
       "      <td>113.301585</td>\n",
       "      <td>116.017949</td>\n",
       "      <td>62.162957</td>\n",
       "      <td>113.298216</td>\n",
       "      <td>116.016227</td>\n",
       "      <td>62.162576</td>\n",
       "      <td>8.418757</td>\n",
       "      <td>8.134905</td>\n",
       "      <td>7.757816</td>\n",
       "      <td>0.952901</td>\n",
       "      <td>0.927246</td>\n",
       "      <td>0.929797</td>\n",
       "      <td>0.501032</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>std</th>\n",
       "      <td>60.198424</td>\n",
       "      <td>52.148720</td>\n",
       "      <td>54.090336</td>\n",
       "      <td>58.970564</td>\n",
       "      <td>50.841150</td>\n",
       "      <td>52.926082</td>\n",
       "      <td>8.705783</td>\n",
       "      <td>8.296806</td>\n",
       "      <td>8.021638</td>\n",
       "      <td>0.146928</td>\n",
       "      <td>0.151160</td>\n",
       "      <td>0.152088</td>\n",
       "      <td>0.499999</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>min</th>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>1.244898</td>\n",
       "      <td>0.020408</td>\n",
       "      <td>0.204082</td>\n",
       "      <td>0.141392</td>\n",
       "      <td>0.141392</td>\n",
       "      <td>0.141392</td>\n",
       "      <td>-1.000000</td>\n",
       "      <td>-1.000000</td>\n",
       "      <td>-1.000000</td>\n",
       "      <td>0.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>25%</th>\n",
       "      <td>66.000000</td>\n",
       "      <td>79.000000</td>\n",
       "      <td>18.000000</td>\n",
       "      <td>68.142857</td>\n",
       "      <td>80.551020</td>\n",
       "      <td>19.387755</td>\n",
       "      <td>1.848038</td>\n",
       "      <td>1.812999</td>\n",
       "      <td>1.877329</td>\n",
       "      <td>0.978886</td>\n",
       "      <td>0.934812</td>\n",
       "      <td>0.941280</td>\n",
       "      <td>0.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>50%</th>\n",
       "      <td>97.000000</td>\n",
       "      <td>104.000000</td>\n",
       "      <td>44.000000</td>\n",
       "      <td>96.040816</td>\n",
       "      <td>103.448980</td>\n",
       "      <td>43.020408</td>\n",
       "      <td>5.267600</td>\n",
       "      <td>5.170399</td>\n",
       "      <td>5.002040</td>\n",
       "      <td>0.996343</td>\n",
       "      <td>0.981474</td>\n",
       "      <td>0.983263</td>\n",
       "      <td>1.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>75%</th>\n",
       "      <td>165.000000</td>\n",
       "      <td>158.000000</td>\n",
       "      <td>104.000000</td>\n",
       "      <td>164.653061</td>\n",
       "      <td>156.469388</td>\n",
       "      <td>101.836735</td>\n",
       "      <td>12.502461</td>\n",
       "      <td>12.113375</td>\n",
       "      <td>11.305386</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.996440</td>\n",
       "      <td>0.996977</td>\n",
       "      <td>1.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>max</th>\n",
       "      <td>255.000000</td>\n",
       "      <td>255.000000</td>\n",
       "      <td>248.000000</td>\n",
       "      <td>241.693878</td>\n",
       "      <td>230.367347</td>\n",
       "      <td>215.795918</td>\n",
       "      <td>89.248069</td>\n",
       "      <td>81.959367</td>\n",
       "      <td>86.375805</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "           red_pixel    green_pixel     blue_pixel       mean_red  \\\n",
       "count  997941.000000  997941.000000  997941.000000  997941.000000   \n",
       "mean      113.301585     116.017949      62.162957     113.298216   \n",
       "std        60.198424      52.148720      54.090336      58.970564   \n",
       "min         0.000000       0.000000       0.000000       1.244898   \n",
       "25%        66.000000      79.000000      18.000000      68.142857   \n",
       "50%        97.000000     104.000000      44.000000      96.040816   \n",
       "75%       165.000000     158.000000     104.000000     164.653061   \n",
       "max       255.000000     255.000000     248.000000     241.693878   \n",
       "\n",
       "          mean_green      mean_blue        std_red      std_green  \\\n",
       "count  997941.000000  997941.000000  997941.000000  997941.000000   \n",
       "mean      116.016227      62.162576       8.418757       8.134905   \n",
       "std        50.841150      52.926082       8.705783       8.296806   \n",
       "min         0.020408       0.204082       0.141392       0.141392   \n",
       "25%        80.551020      19.387755       1.848038       1.812999   \n",
       "50%       103.448980      43.020408       5.267600       5.170399   \n",
       "75%       156.469388     101.836735      12.502461      12.113375   \n",
       "max       230.367347     215.795918      89.248069      81.959367   \n",
       "\n",
       "            std_blue        corr_rg        corr_rb        corr_gb  \\\n",
       "count  997941.000000  997941.000000  997941.000000  997941.000000   \n",
       "mean        7.757816       0.952901       0.927246       0.929797   \n",
       "std         8.021638       0.146928       0.151160       0.152088   \n",
       "min         0.141392      -1.000000      -1.000000      -1.000000   \n",
       "25%         1.877329       0.978886       0.934812       0.941280   \n",
       "50%         5.002040       0.996343       0.981474       0.983263   \n",
       "75%        11.305386       1.000000       0.996440       0.996977   \n",
       "max        86.375805       1.000000       1.000000       1.000000   \n",
       "\n",
       "              inside  \n",
       "count  997941.000000  \n",
       "mean        0.501032  \n",
       "std         0.499999  \n",
       "min         0.000000  \n",
       "25%         0.000000  \n",
       "50%         1.000000  \n",
       "75%         1.000000  \n",
       "max         1.000000  "
      ]
     },
     "execution_count": 5,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "test_set.describe()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "red_pixel      float64\n",
       "green_pixel    float64\n",
       "blue_pixel     float64\n",
       "mean_red       float64\n",
       "mean_green     float64\n",
       "mean_blue      float64\n",
       "std_red        float64\n",
       "std_green      float64\n",
       "std_blue       float64\n",
       "corr_rg        float64\n",
       "corr_rb        float64\n",
       "corr_gb        float64\n",
       "inside         float64\n",
       "dtype: object"
      ]
     },
     "execution_count": 6,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "training_set[header] = training_set[header].astype(float)\n",
    "training_set.dtypes"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "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>red_pixel</th>\n",
       "      <th>green_pixel</th>\n",
       "      <th>blue_pixel</th>\n",
       "      <th>mean_red</th>\n",
       "      <th>mean_green</th>\n",
       "      <th>mean_blue</th>\n",
       "      <th>std_red</th>\n",
       "      <th>std_green</th>\n",
       "      <th>std_blue</th>\n",
       "      <th>corr_rg</th>\n",
       "      <th>corr_rb</th>\n",
       "      <th>corr_gb</th>\n",
       "      <th>inside</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>count</th>\n",
       "      <td>8.874329e+06</td>\n",
       "      <td>8.874329e+06</td>\n",
       "      <td>8.874329e+06</td>\n",
       "      <td>8.874329e+06</td>\n",
       "      <td>8.874329e+06</td>\n",
       "      <td>8.874329e+06</td>\n",
       "      <td>8.874329e+06</td>\n",
       "      <td>8.874329e+06</td>\n",
       "      <td>8.874329e+06</td>\n",
       "      <td>8.874329e+06</td>\n",
       "      <td>8.874329e+06</td>\n",
       "      <td>8.874329e+06</td>\n",
       "      <td>8.874329e+06</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>mean</th>\n",
       "      <td>1.225020e+02</td>\n",
       "      <td>1.262246e+02</td>\n",
       "      <td>7.254746e+01</td>\n",
       "      <td>1.225035e+02</td>\n",
       "      <td>1.262269e+02</td>\n",
       "      <td>7.254785e+01</td>\n",
       "      <td>8.015108e+00</td>\n",
       "      <td>7.763847e+00</td>\n",
       "      <td>7.432946e+00</td>\n",
       "      <td>9.434956e-01</td>\n",
       "      <td>9.160396e-01</td>\n",
       "      <td>9.178913e-01</td>\n",
       "      <td>5.014433e-01</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>std</th>\n",
       "      <td>6.069691e+01</td>\n",
       "      <td>5.207789e+01</td>\n",
       "      <td>5.859685e+01</td>\n",
       "      <td>5.948741e+01</td>\n",
       "      <td>5.077811e+01</td>\n",
       "      <td>5.755836e+01</td>\n",
       "      <td>8.989863e+00</td>\n",
       "      <td>8.554959e+00</td>\n",
       "      <td>8.078582e+00</td>\n",
       "      <td>1.598772e-01</td>\n",
       "      <td>1.655050e-01</td>\n",
       "      <td>1.745431e-01</td>\n",
       "      <td>4.999979e-01</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>min</th>\n",
       "      <td>0.000000e+00</td>\n",
       "      <td>0.000000e+00</td>\n",
       "      <td>0.000000e+00</td>\n",
       "      <td>2.632653e+00</td>\n",
       "      <td>1.204082e+00</td>\n",
       "      <td>2.040816e-02</td>\n",
       "      <td>1.413919e-01</td>\n",
       "      <td>1.413919e-01</td>\n",
       "      <td>1.413919e-01</td>\n",
       "      <td>-1.000000e+00</td>\n",
       "      <td>-1.000000e+00</td>\n",
       "      <td>-1.000000e+00</td>\n",
       "      <td>0.000000e+00</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>25%</th>\n",
       "      <td>7.200000e+01</td>\n",
       "      <td>8.600000e+01</td>\n",
       "      <td>2.400000e+01</td>\n",
       "      <td>7.295918e+01</td>\n",
       "      <td>8.759184e+01</td>\n",
       "      <td>2.446939e+01</td>\n",
       "      <td>1.504955e+00</td>\n",
       "      <td>1.456863e+00</td>\n",
       "      <td>1.570235e+00</td>\n",
       "      <td>9.709500e-01</td>\n",
       "      <td>9.177738e-01</td>\n",
       "      <td>9.292004e-01</td>\n",
       "      <td>0.000000e+00</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>50%</th>\n",
       "      <td>1.080000e+02</td>\n",
       "      <td>1.150000e+02</td>\n",
       "      <td>5.200000e+01</td>\n",
       "      <td>1.061429e+02</td>\n",
       "      <td>1.133878e+02</td>\n",
       "      <td>5.006122e+01</td>\n",
       "      <td>4.547038e+00</td>\n",
       "      <td>4.489981e+00</td>\n",
       "      <td>4.397474e+00</td>\n",
       "      <td>9.954165e-01</td>\n",
       "      <td>9.778953e-01</td>\n",
       "      <td>9.811000e-01</td>\n",
       "      <td>1.000000e+00</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>75%</th>\n",
       "      <td>1.800000e+02</td>\n",
       "      <td>1.730000e+02</td>\n",
       "      <td>1.240000e+02</td>\n",
       "      <td>1.791020e+02</td>\n",
       "      <td>1.724286e+02</td>\n",
       "      <td>1.231020e+02</td>\n",
       "      <td>1.137454e+01</td>\n",
       "      <td>1.110943e+01</td>\n",
       "      <td>1.058241e+01</td>\n",
       "      <td>1.000000e+00</td>\n",
       "      <td>9.960366e-01</td>\n",
       "      <td>9.969647e-01</td>\n",
       "      <td>1.000000e+00</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>max</th>\n",
       "      <td>2.550000e+02</td>\n",
       "      <td>2.550000e+02</td>\n",
       "      <td>2.550000e+02</td>\n",
       "      <td>2.549796e+02</td>\n",
       "      <td>2.549796e+02</td>\n",
       "      <td>2.549796e+02</td>\n",
       "      <td>9.653856e+01</td>\n",
       "      <td>9.247682e+01</td>\n",
       "      <td>9.291633e+01</td>\n",
       "      <td>1.000000e+00</td>\n",
       "      <td>1.000000e+00</td>\n",
       "      <td>1.000000e+00</td>\n",
       "      <td>1.000000e+00</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "          red_pixel   green_pixel    blue_pixel      mean_red    mean_green  \\\n",
       "count  8.874329e+06  8.874329e+06  8.874329e+06  8.874329e+06  8.874329e+06   \n",
       "mean   1.225020e+02  1.262246e+02  7.254746e+01  1.225035e+02  1.262269e+02   \n",
       "std    6.069691e+01  5.207789e+01  5.859685e+01  5.948741e+01  5.077811e+01   \n",
       "min    0.000000e+00  0.000000e+00  0.000000e+00  2.632653e+00  1.204082e+00   \n",
       "25%    7.200000e+01  8.600000e+01  2.400000e+01  7.295918e+01  8.759184e+01   \n",
       "50%    1.080000e+02  1.150000e+02  5.200000e+01  1.061429e+02  1.133878e+02   \n",
       "75%    1.800000e+02  1.730000e+02  1.240000e+02  1.791020e+02  1.724286e+02   \n",
       "max    2.550000e+02  2.550000e+02  2.550000e+02  2.549796e+02  2.549796e+02   \n",
       "\n",
       "          mean_blue       std_red     std_green      std_blue       corr_rg  \\\n",
       "count  8.874329e+06  8.874329e+06  8.874329e+06  8.874329e+06  8.874329e+06   \n",
       "mean   7.254785e+01  8.015108e+00  7.763847e+00  7.432946e+00  9.434956e-01   \n",
       "std    5.755836e+01  8.989863e+00  8.554959e+00  8.078582e+00  1.598772e-01   \n",
       "min    2.040816e-02  1.413919e-01  1.413919e-01  1.413919e-01 -1.000000e+00   \n",
       "25%    2.446939e+01  1.504955e+00  1.456863e+00  1.570235e+00  9.709500e-01   \n",
       "50%    5.006122e+01  4.547038e+00  4.489981e+00  4.397474e+00  9.954165e-01   \n",
       "75%    1.231020e+02  1.137454e+01  1.110943e+01  1.058241e+01  1.000000e+00   \n",
       "max    2.549796e+02  9.653856e+01  9.247682e+01  9.291633e+01  1.000000e+00   \n",
       "\n",
       "            corr_rb       corr_gb        inside  \n",
       "count  8.874329e+06  8.874329e+06  8.874329e+06  \n",
       "mean   9.160396e-01  9.178913e-01  5.014433e-01  \n",
       "std    1.655050e-01  1.745431e-01  4.999979e-01  \n",
       "min   -1.000000e+00 -1.000000e+00  0.000000e+00  \n",
       "25%    9.177738e-01  9.292004e-01  0.000000e+00  \n",
       "50%    9.778953e-01  9.811000e-01  1.000000e+00  \n",
       "75%    9.960366e-01  9.969647e-01  1.000000e+00  \n",
       "max    1.000000e+00  1.000000e+00  1.000000e+00  "
      ]
     },
     "execution_count": 7,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "training_set.describe()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "MinMaxScaler(copy=True, feature_range=(0, 1))"
      ]
     },
     "execution_count": 7,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "from sklearn.preprocessing import MinMaxScaler\n",
    "\n",
    "scaler = MinMaxScaler()\n",
    "scaler.fit(training_set)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {},
   "outputs": [],
   "source": [
    "training_set[header] = scaler.fit_transform(training_set[header])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "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>red_pixel</th>\n",
       "      <th>green_pixel</th>\n",
       "      <th>blue_pixel</th>\n",
       "      <th>mean_red</th>\n",
       "      <th>mean_green</th>\n",
       "      <th>mean_blue</th>\n",
       "      <th>std_red</th>\n",
       "      <th>std_green</th>\n",
       "      <th>std_blue</th>\n",
       "      <th>corr_rg</th>\n",
       "      <th>corr_rb</th>\n",
       "      <th>corr_gb</th>\n",
       "      <th>inside</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>count</th>\n",
       "      <td>8.874329e+06</td>\n",
       "      <td>8.874329e+06</td>\n",
       "      <td>8.874329e+06</td>\n",
       "      <td>8.874329e+06</td>\n",
       "      <td>8.874329e+06</td>\n",
       "      <td>8.874329e+06</td>\n",
       "      <td>8.874329e+06</td>\n",
       "      <td>8.874329e+06</td>\n",
       "      <td>8.874329e+06</td>\n",
       "      <td>8.874329e+06</td>\n",
       "      <td>8.874329e+06</td>\n",
       "      <td>8.874329e+06</td>\n",
       "      <td>8.874329e+06</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>mean</th>\n",
       "      <td>4.803999e-01</td>\n",
       "      <td>4.949984e-01</td>\n",
       "      <td>2.844998e-01</td>\n",
       "      <td>4.750240e-01</td>\n",
       "      <td>4.926514e-01</td>\n",
       "      <td>2.844669e-01</td>\n",
       "      <td>8.167995e-02</td>\n",
       "      <td>8.255179e-02</td>\n",
       "      <td>7.859400e-02</td>\n",
       "      <td>9.717478e-01</td>\n",
       "      <td>9.580198e-01</td>\n",
       "      <td>9.589456e-01</td>\n",
       "      <td>5.014433e-01</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>std</th>\n",
       "      <td>2.380271e-01</td>\n",
       "      <td>2.042270e-01</td>\n",
       "      <td>2.297916e-01</td>\n",
       "      <td>2.357366e-01</td>\n",
       "      <td>2.000907e-01</td>\n",
       "      <td>2.257552e-01</td>\n",
       "      <td>9.325858e-02</td>\n",
       "      <td>9.265088e-02</td>\n",
       "      <td>8.707719e-02</td>\n",
       "      <td>7.993862e-02</td>\n",
       "      <td>8.275250e-02</td>\n",
       "      <td>8.727155e-02</td>\n",
       "      <td>4.999979e-01</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>min</th>\n",
       "      <td>0.000000e+00</td>\n",
       "      <td>0.000000e+00</td>\n",
       "      <td>0.000000e+00</td>\n",
       "      <td>0.000000e+00</td>\n",
       "      <td>0.000000e+00</td>\n",
       "      <td>0.000000e+00</td>\n",
       "      <td>0.000000e+00</td>\n",
       "      <td>0.000000e+00</td>\n",
       "      <td>0.000000e+00</td>\n",
       "      <td>0.000000e+00</td>\n",
       "      <td>0.000000e+00</td>\n",
       "      <td>0.000000e+00</td>\n",
       "      <td>0.000000e+00</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>25%</th>\n",
       "      <td>2.823529e-01</td>\n",
       "      <td>3.372549e-01</td>\n",
       "      <td>9.411765e-02</td>\n",
       "      <td>2.786899e-01</td>\n",
       "      <td>3.404101e-01</td>\n",
       "      <td>9.589370e-02</td>\n",
       "      <td>1.414526e-02</td>\n",
       "      <td>1.424665e-02</td>\n",
       "      <td>1.540118e-02</td>\n",
       "      <td>9.854750e-01</td>\n",
       "      <td>9.588869e-01</td>\n",
       "      <td>9.646002e-01</td>\n",
       "      <td>0.000000e+00</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>50%</th>\n",
       "      <td>4.235294e-01</td>\n",
       "      <td>4.509804e-01</td>\n",
       "      <td>2.039216e-01</td>\n",
       "      <td>4.101901e-01</td>\n",
       "      <td>4.420587e-01</td>\n",
       "      <td>1.962699e-01</td>\n",
       "      <td>4.570306e-02</td>\n",
       "      <td>4.709557e-02</td>\n",
       "      <td>4.587534e-02</td>\n",
       "      <td>9.977083e-01</td>\n",
       "      <td>9.889477e-01</td>\n",
       "      <td>9.905500e-01</td>\n",
       "      <td>1.000000e+00</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>75%</th>\n",
       "      <td>7.058824e-01</td>\n",
       "      <td>6.784314e-01</td>\n",
       "      <td>4.862745e-01</td>\n",
       "      <td>6.993126e-01</td>\n",
       "      <td>6.747085e-01</td>\n",
       "      <td>4.827503e-01</td>\n",
       "      <td>1.165299e-01</td>\n",
       "      <td>1.187847e-01</td>\n",
       "      <td>1.125414e-01</td>\n",
       "      <td>1.000000e+00</td>\n",
       "      <td>9.980183e-01</td>\n",
       "      <td>9.984824e-01</td>\n",
       "      <td>1.000000e+00</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>max</th>\n",
       "      <td>1.000000e+00</td>\n",
       "      <td>1.000000e+00</td>\n",
       "      <td>1.000000e+00</td>\n",
       "      <td>1.000000e+00</td>\n",
       "      <td>1.000000e+00</td>\n",
       "      <td>1.000000e+00</td>\n",
       "      <td>1.000000e+00</td>\n",
       "      <td>1.000000e+00</td>\n",
       "      <td>1.000000e+00</td>\n",
       "      <td>1.000000e+00</td>\n",
       "      <td>1.000000e+00</td>\n",
       "      <td>1.000000e+00</td>\n",
       "      <td>1.000000e+00</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "          red_pixel   green_pixel    blue_pixel      mean_red    mean_green  \\\n",
       "count  8.874329e+06  8.874329e+06  8.874329e+06  8.874329e+06  8.874329e+06   \n",
       "mean   4.803999e-01  4.949984e-01  2.844998e-01  4.750240e-01  4.926514e-01   \n",
       "std    2.380271e-01  2.042270e-01  2.297916e-01  2.357366e-01  2.000907e-01   \n",
       "min    0.000000e+00  0.000000e+00  0.000000e+00  0.000000e+00  0.000000e+00   \n",
       "25%    2.823529e-01  3.372549e-01  9.411765e-02  2.786899e-01  3.404101e-01   \n",
       "50%    4.235294e-01  4.509804e-01  2.039216e-01  4.101901e-01  4.420587e-01   \n",
       "75%    7.058824e-01  6.784314e-01  4.862745e-01  6.993126e-01  6.747085e-01   \n",
       "max    1.000000e+00  1.000000e+00  1.000000e+00  1.000000e+00  1.000000e+00   \n",
       "\n",
       "          mean_blue       std_red     std_green      std_blue       corr_rg  \\\n",
       "count  8.874329e+06  8.874329e+06  8.874329e+06  8.874329e+06  8.874329e+06   \n",
       "mean   2.844669e-01  8.167995e-02  8.255179e-02  7.859400e-02  9.717478e-01   \n",
       "std    2.257552e-01  9.325858e-02  9.265088e-02  8.707719e-02  7.993862e-02   \n",
       "min    0.000000e+00  0.000000e+00  0.000000e+00  0.000000e+00  0.000000e+00   \n",
       "25%    9.589370e-02  1.414526e-02  1.424665e-02  1.540118e-02  9.854750e-01   \n",
       "50%    1.962699e-01  4.570306e-02  4.709557e-02  4.587534e-02  9.977083e-01   \n",
       "75%    4.827503e-01  1.165299e-01  1.187847e-01  1.125414e-01  1.000000e+00   \n",
       "max    1.000000e+00  1.000000e+00  1.000000e+00  1.000000e+00  1.000000e+00   \n",
       "\n",
       "            corr_rb       corr_gb        inside  \n",
       "count  8.874329e+06  8.874329e+06  8.874329e+06  \n",
       "mean   9.580198e-01  9.589456e-01  5.014433e-01  \n",
       "std    8.275250e-02  8.727155e-02  4.999979e-01  \n",
       "min    0.000000e+00  0.000000e+00  0.000000e+00  \n",
       "25%    9.588869e-01  9.646002e-01  0.000000e+00  \n",
       "50%    9.889477e-01  9.905500e-01  1.000000e+00  \n",
       "75%    9.980183e-01  9.984824e-01  1.000000e+00  \n",
       "max    1.000000e+00  1.000000e+00  1.000000e+00  "
      ]
     },
     "execution_count": 10,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "training_set.describe()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Naive Bayes"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {},
   "outputs": [],
   "source": [
    "from sklearn.naive_bayes import GaussianNB"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {},
   "outputs": [],
   "source": [
    "y_train = targets = training_set['inside'] # dependent variable\n",
    "x_train = training_set.drop(['inside'],axis=1)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "GaussianNB(priors=None, var_smoothing=1e-09)"
      ]
     },
     "execution_count": 13,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "classifier = GaussianNB()\n",
    "classifier.fit(x_train, y_train)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "red_pixel      float64\n",
       "green_pixel    float64\n",
       "blue_pixel     float64\n",
       "mean_red       float64\n",
       "mean_green     float64\n",
       "mean_blue      float64\n",
       "std_red        float64\n",
       "std_green      float64\n",
       "std_blue       float64\n",
       "corr_rg        float64\n",
       "corr_rb        float64\n",
       "corr_gb        float64\n",
       "inside         float64\n",
       "dtype: object"
      ]
     },
     "execution_count": 14,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "test_set[header] = test_set[header].astype(float)\n",
    "test_set.dtypes"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "metadata": {},
   "outputs": [],
   "source": [
    "scaler = MinMaxScaler()\n",
    "scaler.fit(test_set)\n",
    "test_set[header] = scaler.fit_transform(test_set[header])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "metadata": {},
   "outputs": [],
   "source": [
    "y_test = test_set['inside'] # dependent variable\n",
    "x_test = test_set.drop(['inside'],axis=1)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "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>1</th>\n",
       "      <th>0</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>325883</td>\n",
       "      <td>172058</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>18607</td>\n",
       "      <td>481393</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "        1       0\n",
       "1  325883  172058\n",
       "0   18607  481393"
      ]
     },
     "execution_count": 17,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "from sklearn.metrics import confusion_matrix\n",
    "y_pred = classifier.predict(x_test)\n",
    "cm = confusion_matrix(y_test, y_pred)\n",
    "cm_df = pd.DataFrame(cm)\n",
    "cm_df\n",
    "cm_df.columns = ['1','0']\n",
    "cm_df = cm_df.rename(index={0: '1',1:'0'})\n",
    "cm_df"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "              precision    recall  f1-score   support\n",
      "\n",
      "         0.0       0.95      0.65      0.77    497941\n",
      "         1.0       0.74      0.96      0.83    500000\n",
      "\n",
      "    accuracy                           0.81    997941\n",
      "   macro avg       0.84      0.81      0.80    997941\n",
      "weighted avg       0.84      0.81      0.80    997941\n",
      "\n"
     ]
    }
   ],
   "source": [
    "from sklearn.metrics import classification_report\n",
    "print(classification_report(y_test,y_pred))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 25,
   "metadata": {},
   "outputs": [],
   "source": [
    "import pickle\n",
    "model_file_name = 'naive_bayes_classifier_model.pkl'\n",
    "file = open(model_file_name, 'wb')\n",
    "pickle.dump(classifier, file)\n",
    "file.close()\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 27,
   "metadata": {},
   "outputs": [],
   "source": [
    "loaded_model = pickle.load(open('naive_bayes_classifier_model.pkl', 'rb'))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 28,
   "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>1</th>\n",
       "      <th>0</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>325883</td>\n",
       "      <td>172058</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>18607</td>\n",
       "      <td>481393</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "        1       0\n",
       "1  325883  172058\n",
       "0   18607  481393"
      ]
     },
     "execution_count": 28,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "from sklearn.metrics import confusion_matrix\n",
    "y_pred = loaded_model.predict(x_test)\n",
    "cm = confusion_matrix(y_test, y_pred)\n",
    "cm_df = pd.DataFrame(cm)\n",
    "cm_df\n",
    "cm_df.columns = ['1','0']\n",
    "cm_df = cm_df.rename(index={0: '1',1:'0'})\n",
    "cm_df"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Random Forest Classifier"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "metadata": {},
   "outputs": [],
   "source": [
    "from sklearn.ensemble import RandomForestClassifier"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "metadata": {},
   "outputs": [],
   "source": [
    "y_train = targets = training_set['inside'] # dependent variable\n",
    "x_train = training_set.drop(['inside'],axis=1)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "metadata": {},
   "outputs": [],
   "source": [
    "classifier = RandomForestClassifier(verbose=3)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "[Parallel(n_jobs=1)]: Using backend SequentialBackend with 1 concurrent workers.\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "building tree 1 of 100\n"
     ]
    }
   ],
   "source": [
    "classifier.fit(x_train,y_train)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "test_set[header] = test_set[header].astype(float)\n",
    "test_set.dtypes"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "scaler = MinMaxScaler()\n",
    "scaler.fit(test_set)\n",
    "test_set[header] = scaler.fit_transform(test_set[header])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "y_test = test_set['inside'] # dependent variable\n",
    "x_test = test_set.drop(['inside'],axis=1)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "from sklearn.metrics import confusion_matrix\n",
    "y_pred = classifier.predict(x_test)\n",
    "cm = confusion_matrix(y_test, y_pred)\n",
    "cm_df = pd.DataFrame(cm)\n",
    "cm_df\n",
    "cm_df.columns = ['1','0']\n",
    "cm_df = cm_df.rename(index={0: '1',1:'0'})\n",
    "cm_df"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "from sklearn.metrics import classification_report\n",
    "print(classification_report(y_test,y_pred))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "import pickle"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Save model to disk"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "model_file = 'randomforest_classifier_model.pkl'"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "pickle.dump(classifier, open(model_file, 'wb'))"
   ]
  }
 ],
 "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": "3.8.5"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 4
}