Breast_Cancer_XgBoost_.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [],
   "source": [
    "import numpy as np # linear algebra\n",
    "import pandas as pd # data processing, CSV file I/O (e.g. pd.read_csv)\n",
    "import matplotlib.pyplot as plt\n",
    "import seaborn as sns\n",
    "\n",
    "from sklearn.model_selection import train_test_split\n",
    "from sklearn.ensemble import GradientBoostingClassifier \n",
    "from sklearn.metrics import classification_report, confusion_matrix, accuracy_score"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {
    "_cell_guid": "79c7e3d0-c299-4dcb-8224-4455121ee9b0",
    "_uuid": "d629ff2d2480ee46fbb7e2d37f6b5fab8052498a"
   },
   "outputs": [],
   "source": [
    "#loading the dataset\n",
    "data=pd.read_csv(\"data.csv\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "Index(['id', 'diagnosis', 'radius_mean', 'texture_mean', 'perimeter_mean',\n",
       "       'area_mean', 'smoothness_mean', 'compactness_mean', 'concavity_mean',\n",
       "       'concave points_mean', 'symmetry_mean', 'fractal_dimension_mean',\n",
       "       'radius_se', 'texture_se', 'perimeter_se', 'area_se', 'smoothness_se',\n",
       "       'compactness_se', 'concavity_se', 'concave points_se', 'symmetry_se',\n",
       "       'fractal_dimension_se', 'radius_worst', 'texture_worst',\n",
       "       'perimeter_worst', 'area_worst', 'smoothness_worst',\n",
       "       'compactness_worst', 'concavity_worst', 'concave points_worst',\n",
       "       'symmetry_worst', 'fractal_dimension_worst', 'Unnamed: 32'],\n",
       "      dtype='object')"
      ]
     },
     "execution_count": 6,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "#Column header\n",
    "data.keys()"
   ]
  },
  {
   "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>id</th>\n",
       "      <th>diagnosis</th>\n",
       "      <th>radius_mean</th>\n",
       "      <th>texture_mean</th>\n",
       "      <th>perimeter_mean</th>\n",
       "      <th>area_mean</th>\n",
       "      <th>smoothness_mean</th>\n",
       "      <th>compactness_mean</th>\n",
       "      <th>concavity_mean</th>\n",
       "      <th>concave points_mean</th>\n",
       "      <th>...</th>\n",
       "      <th>texture_worst</th>\n",
       "      <th>perimeter_worst</th>\n",
       "      <th>area_worst</th>\n",
       "      <th>smoothness_worst</th>\n",
       "      <th>compactness_worst</th>\n",
       "      <th>concavity_worst</th>\n",
       "      <th>concave points_worst</th>\n",
       "      <th>symmetry_worst</th>\n",
       "      <th>fractal_dimension_worst</th>\n",
       "      <th>Unnamed: 32</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>842302</td>\n",
       "      <td>M</td>\n",
       "      <td>17.99</td>\n",
       "      <td>10.38</td>\n",
       "      <td>122.80</td>\n",
       "      <td>1001.0</td>\n",
       "      <td>0.11840</td>\n",
       "      <td>0.27760</td>\n",
       "      <td>0.3001</td>\n",
       "      <td>0.14710</td>\n",
       "      <td>...</td>\n",
       "      <td>17.33</td>\n",
       "      <td>184.60</td>\n",
       "      <td>2019.0</td>\n",
       "      <td>0.1622</td>\n",
       "      <td>0.6656</td>\n",
       "      <td>0.7119</td>\n",
       "      <td>0.2654</td>\n",
       "      <td>0.4601</td>\n",
       "      <td>0.11890</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>842517</td>\n",
       "      <td>M</td>\n",
       "      <td>20.57</td>\n",
       "      <td>17.77</td>\n",
       "      <td>132.90</td>\n",
       "      <td>1326.0</td>\n",
       "      <td>0.08474</td>\n",
       "      <td>0.07864</td>\n",
       "      <td>0.0869</td>\n",
       "      <td>0.07017</td>\n",
       "      <td>...</td>\n",
       "      <td>23.41</td>\n",
       "      <td>158.80</td>\n",
       "      <td>1956.0</td>\n",
       "      <td>0.1238</td>\n",
       "      <td>0.1866</td>\n",
       "      <td>0.2416</td>\n",
       "      <td>0.1860</td>\n",
       "      <td>0.2750</td>\n",
       "      <td>0.08902</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>84300903</td>\n",
       "      <td>M</td>\n",
       "      <td>19.69</td>\n",
       "      <td>21.25</td>\n",
       "      <td>130.00</td>\n",
       "      <td>1203.0</td>\n",
       "      <td>0.10960</td>\n",
       "      <td>0.15990</td>\n",
       "      <td>0.1974</td>\n",
       "      <td>0.12790</td>\n",
       "      <td>...</td>\n",
       "      <td>25.53</td>\n",
       "      <td>152.50</td>\n",
       "      <td>1709.0</td>\n",
       "      <td>0.1444</td>\n",
       "      <td>0.4245</td>\n",
       "      <td>0.4504</td>\n",
       "      <td>0.2430</td>\n",
       "      <td>0.3613</td>\n",
       "      <td>0.08758</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>84348301</td>\n",
       "      <td>M</td>\n",
       "      <td>11.42</td>\n",
       "      <td>20.38</td>\n",
       "      <td>77.58</td>\n",
       "      <td>386.1</td>\n",
       "      <td>0.14250</td>\n",
       "      <td>0.28390</td>\n",
       "      <td>0.2414</td>\n",
       "      <td>0.10520</td>\n",
       "      <td>...</td>\n",
       "      <td>26.50</td>\n",
       "      <td>98.87</td>\n",
       "      <td>567.7</td>\n",
       "      <td>0.2098</td>\n",
       "      <td>0.8663</td>\n",
       "      <td>0.6869</td>\n",
       "      <td>0.2575</td>\n",
       "      <td>0.6638</td>\n",
       "      <td>0.17300</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>84358402</td>\n",
       "      <td>M</td>\n",
       "      <td>20.29</td>\n",
       "      <td>14.34</td>\n",
       "      <td>135.10</td>\n",
       "      <td>1297.0</td>\n",
       "      <td>0.10030</td>\n",
       "      <td>0.13280</td>\n",
       "      <td>0.1980</td>\n",
       "      <td>0.10430</td>\n",
       "      <td>...</td>\n",
       "      <td>16.67</td>\n",
       "      <td>152.20</td>\n",
       "      <td>1575.0</td>\n",
       "      <td>0.1374</td>\n",
       "      <td>0.2050</td>\n",
       "      <td>0.4000</td>\n",
       "      <td>0.1625</td>\n",
       "      <td>0.2364</td>\n",
       "      <td>0.07678</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>5 rows × 33 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "         id diagnosis  radius_mean  texture_mean  perimeter_mean  area_mean  \\\n",
       "0    842302         M        17.99         10.38          122.80     1001.0   \n",
       "1    842517         M        20.57         17.77          132.90     1326.0   \n",
       "2  84300903         M        19.69         21.25          130.00     1203.0   \n",
       "3  84348301         M        11.42         20.38           77.58      386.1   \n",
       "4  84358402         M        20.29         14.34          135.10     1297.0   \n",
       "\n",
       "   smoothness_mean  compactness_mean  concavity_mean  concave points_mean  \\\n",
       "0          0.11840           0.27760          0.3001              0.14710   \n",
       "1          0.08474           0.07864          0.0869              0.07017   \n",
       "2          0.10960           0.15990          0.1974              0.12790   \n",
       "3          0.14250           0.28390          0.2414              0.10520   \n",
       "4          0.10030           0.13280          0.1980              0.10430   \n",
       "\n",
       "   ...  texture_worst  perimeter_worst  area_worst  smoothness_worst  \\\n",
       "0  ...          17.33           184.60      2019.0            0.1622   \n",
       "1  ...          23.41           158.80      1956.0            0.1238   \n",
       "2  ...          25.53           152.50      1709.0            0.1444   \n",
       "3  ...          26.50            98.87       567.7            0.2098   \n",
       "4  ...          16.67           152.20      1575.0            0.1374   \n",
       "\n",
       "   compactness_worst  concavity_worst  concave points_worst  symmetry_worst  \\\n",
       "0             0.6656           0.7119                0.2654          0.4601   \n",
       "1             0.1866           0.2416                0.1860          0.2750   \n",
       "2             0.4245           0.4504                0.2430          0.3613   \n",
       "3             0.8663           0.6869                0.2575          0.6638   \n",
       "4             0.2050           0.4000                0.1625          0.2364   \n",
       "\n",
       "   fractal_dimension_worst  Unnamed: 32  \n",
       "0                  0.11890          NaN  \n",
       "1                  0.08902          NaN  \n",
       "2                  0.08758          NaN  \n",
       "3                  0.17300          NaN  \n",
       "4                  0.07678          NaN  \n",
       "\n",
       "[5 rows x 33 columns]"
      ]
     },
     "execution_count": 7,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "#Top 5 rows\n",
    "data.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "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>id</th>\n",
       "      <th>diagnosis</th>\n",
       "      <th>radius_mean</th>\n",
       "      <th>texture_mean</th>\n",
       "      <th>perimeter_mean</th>\n",
       "      <th>area_mean</th>\n",
       "      <th>smoothness_mean</th>\n",
       "      <th>compactness_mean</th>\n",
       "      <th>concavity_mean</th>\n",
       "      <th>concave points_mean</th>\n",
       "      <th>...</th>\n",
       "      <th>texture_worst</th>\n",
       "      <th>perimeter_worst</th>\n",
       "      <th>area_worst</th>\n",
       "      <th>smoothness_worst</th>\n",
       "      <th>compactness_worst</th>\n",
       "      <th>concavity_worst</th>\n",
       "      <th>concave points_worst</th>\n",
       "      <th>symmetry_worst</th>\n",
       "      <th>fractal_dimension_worst</th>\n",
       "      <th>Unnamed: 32</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>35</th>\n",
       "      <td>854253</td>\n",
       "      <td>M</td>\n",
       "      <td>16.74</td>\n",
       "      <td>21.59</td>\n",
       "      <td>110.1</td>\n",
       "      <td>869.5</td>\n",
       "      <td>0.0961</td>\n",
       "      <td>0.1336</td>\n",
       "      <td>0.1348</td>\n",
       "      <td>0.06018</td>\n",
       "      <td>...</td>\n",
       "      <td>29.02</td>\n",
       "      <td>133.5</td>\n",
       "      <td>1229.0</td>\n",
       "      <td>0.1563</td>\n",
       "      <td>0.3835</td>\n",
       "      <td>0.5409</td>\n",
       "      <td>0.1813</td>\n",
       "      <td>0.4863</td>\n",
       "      <td>0.08633</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>1 rows × 33 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "        id diagnosis  radius_mean  texture_mean  perimeter_mean  area_mean  \\\n",
       "35  854253         M        16.74         21.59           110.1      869.5   \n",
       "\n",
       "    smoothness_mean  compactness_mean  concavity_mean  concave points_mean  \\\n",
       "35           0.0961            0.1336          0.1348              0.06018   \n",
       "\n",
       "    ...  texture_worst  perimeter_worst  area_worst  smoothness_worst  \\\n",
       "35  ...          29.02            133.5      1229.0            0.1563   \n",
       "\n",
       "    compactness_worst  concavity_worst  concave points_worst  symmetry_worst  \\\n",
       "35             0.3835           0.5409                0.1813          0.4863   \n",
       "\n",
       "    fractal_dimension_worst  Unnamed: 32  \n",
       "35                  0.08633          NaN  \n",
       "\n",
       "[1 rows x 33 columns]"
      ]
     },
     "execution_count": 8,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "#sample from the dataset\n",
    "data.sample()"
   ]
  },
  {
   "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>id</th>\n",
       "      <th>radius_mean</th>\n",
       "      <th>texture_mean</th>\n",
       "      <th>perimeter_mean</th>\n",
       "      <th>area_mean</th>\n",
       "      <th>smoothness_mean</th>\n",
       "      <th>compactness_mean</th>\n",
       "      <th>concavity_mean</th>\n",
       "      <th>concave points_mean</th>\n",
       "      <th>symmetry_mean</th>\n",
       "      <th>...</th>\n",
       "      <th>texture_worst</th>\n",
       "      <th>perimeter_worst</th>\n",
       "      <th>area_worst</th>\n",
       "      <th>smoothness_worst</th>\n",
       "      <th>compactness_worst</th>\n",
       "      <th>concavity_worst</th>\n",
       "      <th>concave points_worst</th>\n",
       "      <th>symmetry_worst</th>\n",
       "      <th>fractal_dimension_worst</th>\n",
       "      <th>Unnamed: 32</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>count</th>\n",
       "      <td>5.690000e+02</td>\n",
       "      <td>569.000000</td>\n",
       "      <td>569.000000</td>\n",
       "      <td>569.000000</td>\n",
       "      <td>569.000000</td>\n",
       "      <td>569.000000</td>\n",
       "      <td>569.000000</td>\n",
       "      <td>569.000000</td>\n",
       "      <td>569.000000</td>\n",
       "      <td>569.000000</td>\n",
       "      <td>...</td>\n",
       "      <td>569.000000</td>\n",
       "      <td>569.000000</td>\n",
       "      <td>569.000000</td>\n",
       "      <td>569.000000</td>\n",
       "      <td>569.000000</td>\n",
       "      <td>569.000000</td>\n",
       "      <td>569.000000</td>\n",
       "      <td>569.000000</td>\n",
       "      <td>569.000000</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>mean</th>\n",
       "      <td>3.037183e+07</td>\n",
       "      <td>14.127292</td>\n",
       "      <td>19.289649</td>\n",
       "      <td>91.969033</td>\n",
       "      <td>654.889104</td>\n",
       "      <td>0.096360</td>\n",
       "      <td>0.104341</td>\n",
       "      <td>0.088799</td>\n",
       "      <td>0.048919</td>\n",
       "      <td>0.181162</td>\n",
       "      <td>...</td>\n",
       "      <td>25.677223</td>\n",
       "      <td>107.261213</td>\n",
       "      <td>880.583128</td>\n",
       "      <td>0.132369</td>\n",
       "      <td>0.254265</td>\n",
       "      <td>0.272188</td>\n",
       "      <td>0.114606</td>\n",
       "      <td>0.290076</td>\n",
       "      <td>0.083946</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>std</th>\n",
       "      <td>1.250206e+08</td>\n",
       "      <td>3.524049</td>\n",
       "      <td>4.301036</td>\n",
       "      <td>24.298981</td>\n",
       "      <td>351.914129</td>\n",
       "      <td>0.014064</td>\n",
       "      <td>0.052813</td>\n",
       "      <td>0.079720</td>\n",
       "      <td>0.038803</td>\n",
       "      <td>0.027414</td>\n",
       "      <td>...</td>\n",
       "      <td>6.146258</td>\n",
       "      <td>33.602542</td>\n",
       "      <td>569.356993</td>\n",
       "      <td>0.022832</td>\n",
       "      <td>0.157336</td>\n",
       "      <td>0.208624</td>\n",
       "      <td>0.065732</td>\n",
       "      <td>0.061867</td>\n",
       "      <td>0.018061</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>min</th>\n",
       "      <td>8.670000e+03</td>\n",
       "      <td>6.981000</td>\n",
       "      <td>9.710000</td>\n",
       "      <td>43.790000</td>\n",
       "      <td>143.500000</td>\n",
       "      <td>0.052630</td>\n",
       "      <td>0.019380</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.106000</td>\n",
       "      <td>...</td>\n",
       "      <td>12.020000</td>\n",
       "      <td>50.410000</td>\n",
       "      <td>185.200000</td>\n",
       "      <td>0.071170</td>\n",
       "      <td>0.027290</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.156500</td>\n",
       "      <td>0.055040</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>25%</th>\n",
       "      <td>8.692180e+05</td>\n",
       "      <td>11.700000</td>\n",
       "      <td>16.170000</td>\n",
       "      <td>75.170000</td>\n",
       "      <td>420.300000</td>\n",
       "      <td>0.086370</td>\n",
       "      <td>0.064920</td>\n",
       "      <td>0.029560</td>\n",
       "      <td>0.020310</td>\n",
       "      <td>0.161900</td>\n",
       "      <td>...</td>\n",
       "      <td>21.080000</td>\n",
       "      <td>84.110000</td>\n",
       "      <td>515.300000</td>\n",
       "      <td>0.116600</td>\n",
       "      <td>0.147200</td>\n",
       "      <td>0.114500</td>\n",
       "      <td>0.064930</td>\n",
       "      <td>0.250400</td>\n",
       "      <td>0.071460</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>50%</th>\n",
       "      <td>9.060240e+05</td>\n",
       "      <td>13.370000</td>\n",
       "      <td>18.840000</td>\n",
       "      <td>86.240000</td>\n",
       "      <td>551.100000</td>\n",
       "      <td>0.095870</td>\n",
       "      <td>0.092630</td>\n",
       "      <td>0.061540</td>\n",
       "      <td>0.033500</td>\n",
       "      <td>0.179200</td>\n",
       "      <td>...</td>\n",
       "      <td>25.410000</td>\n",
       "      <td>97.660000</td>\n",
       "      <td>686.500000</td>\n",
       "      <td>0.131300</td>\n",
       "      <td>0.211900</td>\n",
       "      <td>0.226700</td>\n",
       "      <td>0.099930</td>\n",
       "      <td>0.282200</td>\n",
       "      <td>0.080040</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>75%</th>\n",
       "      <td>8.813129e+06</td>\n",
       "      <td>15.780000</td>\n",
       "      <td>21.800000</td>\n",
       "      <td>104.100000</td>\n",
       "      <td>782.700000</td>\n",
       "      <td>0.105300</td>\n",
       "      <td>0.130400</td>\n",
       "      <td>0.130700</td>\n",
       "      <td>0.074000</td>\n",
       "      <td>0.195700</td>\n",
       "      <td>...</td>\n",
       "      <td>29.720000</td>\n",
       "      <td>125.400000</td>\n",
       "      <td>1084.000000</td>\n",
       "      <td>0.146000</td>\n",
       "      <td>0.339100</td>\n",
       "      <td>0.382900</td>\n",
       "      <td>0.161400</td>\n",
       "      <td>0.317900</td>\n",
       "      <td>0.092080</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>max</th>\n",
       "      <td>9.113205e+08</td>\n",
       "      <td>28.110000</td>\n",
       "      <td>39.280000</td>\n",
       "      <td>188.500000</td>\n",
       "      <td>2501.000000</td>\n",
       "      <td>0.163400</td>\n",
       "      <td>0.345400</td>\n",
       "      <td>0.426800</td>\n",
       "      <td>0.201200</td>\n",
       "      <td>0.304000</td>\n",
       "      <td>...</td>\n",
       "      <td>49.540000</td>\n",
       "      <td>251.200000</td>\n",
       "      <td>4254.000000</td>\n",
       "      <td>0.222600</td>\n",
       "      <td>1.058000</td>\n",
       "      <td>1.252000</td>\n",
       "      <td>0.291000</td>\n",
       "      <td>0.663800</td>\n",
       "      <td>0.207500</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>8 rows × 32 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "                 id  radius_mean  texture_mean  perimeter_mean    area_mean  \\\n",
       "count  5.690000e+02   569.000000    569.000000      569.000000   569.000000   \n",
       "mean   3.037183e+07    14.127292     19.289649       91.969033   654.889104   \n",
       "std    1.250206e+08     3.524049      4.301036       24.298981   351.914129   \n",
       "min    8.670000e+03     6.981000      9.710000       43.790000   143.500000   \n",
       "25%    8.692180e+05    11.700000     16.170000       75.170000   420.300000   \n",
       "50%    9.060240e+05    13.370000     18.840000       86.240000   551.100000   \n",
       "75%    8.813129e+06    15.780000     21.800000      104.100000   782.700000   \n",
       "max    9.113205e+08    28.110000     39.280000      188.500000  2501.000000   \n",
       "\n",
       "       smoothness_mean  compactness_mean  concavity_mean  concave points_mean  \\\n",
       "count       569.000000        569.000000      569.000000           569.000000   \n",
       "mean          0.096360          0.104341        0.088799             0.048919   \n",
       "std           0.014064          0.052813        0.079720             0.038803   \n",
       "min           0.052630          0.019380        0.000000             0.000000   \n",
       "25%           0.086370          0.064920        0.029560             0.020310   \n",
       "50%           0.095870          0.092630        0.061540             0.033500   \n",
       "75%           0.105300          0.130400        0.130700             0.074000   \n",
       "max           0.163400          0.345400        0.426800             0.201200   \n",
       "\n",
       "       symmetry_mean  ...  texture_worst  perimeter_worst   area_worst  \\\n",
       "count     569.000000  ...     569.000000       569.000000   569.000000   \n",
       "mean        0.181162  ...      25.677223       107.261213   880.583128   \n",
       "std         0.027414  ...       6.146258        33.602542   569.356993   \n",
       "min         0.106000  ...      12.020000        50.410000   185.200000   \n",
       "25%         0.161900  ...      21.080000        84.110000   515.300000   \n",
       "50%         0.179200  ...      25.410000        97.660000   686.500000   \n",
       "75%         0.195700  ...      29.720000       125.400000  1084.000000   \n",
       "max         0.304000  ...      49.540000       251.200000  4254.000000   \n",
       "\n",
       "       smoothness_worst  compactness_worst  concavity_worst  \\\n",
       "count        569.000000         569.000000       569.000000   \n",
       "mean           0.132369           0.254265         0.272188   \n",
       "std            0.022832           0.157336         0.208624   \n",
       "min            0.071170           0.027290         0.000000   \n",
       "25%            0.116600           0.147200         0.114500   \n",
       "50%            0.131300           0.211900         0.226700   \n",
       "75%            0.146000           0.339100         0.382900   \n",
       "max            0.222600           1.058000         1.252000   \n",
       "\n",
       "       concave points_worst  symmetry_worst  fractal_dimension_worst  \\\n",
       "count            569.000000      569.000000               569.000000   \n",
       "mean               0.114606        0.290076                 0.083946   \n",
       "std                0.065732        0.061867                 0.018061   \n",
       "min                0.000000        0.156500                 0.055040   \n",
       "25%                0.064930        0.250400                 0.071460   \n",
       "50%                0.099930        0.282200                 0.080040   \n",
       "75%                0.161400        0.317900                 0.092080   \n",
       "max                0.291000        0.663800                 0.207500   \n",
       "\n",
       "       Unnamed: 32  \n",
       "count          0.0  \n",
       "mean           NaN  \n",
       "std            NaN  \n",
       "min            NaN  \n",
       "25%            NaN  \n",
       "50%            NaN  \n",
       "75%            NaN  \n",
       "max            NaN  \n",
       "\n",
       "[8 rows x 32 columns]"
      ]
     },
     "execution_count": 9,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "#Statistical information\n",
    "data.describe()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(569, 33)"
      ]
     },
     "execution_count": 10,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "#Shape of the dataset\n",
    "data.shape"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {},
   "outputs": [],
   "source": [
    "#loading the data and the target\n",
    "X = data.iloc[:, 2:-1]\n",
    "y = data.iloc[:,1]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "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>radius_mean</th>\n",
       "      <th>texture_mean</th>\n",
       "      <th>perimeter_mean</th>\n",
       "      <th>area_mean</th>\n",
       "      <th>smoothness_mean</th>\n",
       "      <th>compactness_mean</th>\n",
       "      <th>concavity_mean</th>\n",
       "      <th>concave points_mean</th>\n",
       "      <th>symmetry_mean</th>\n",
       "      <th>fractal_dimension_mean</th>\n",
       "      <th>...</th>\n",
       "      <th>radius_worst</th>\n",
       "      <th>texture_worst</th>\n",
       "      <th>perimeter_worst</th>\n",
       "      <th>area_worst</th>\n",
       "      <th>smoothness_worst</th>\n",
       "      <th>compactness_worst</th>\n",
       "      <th>concavity_worst</th>\n",
       "      <th>concave points_worst</th>\n",
       "      <th>symmetry_worst</th>\n",
       "      <th>fractal_dimension_worst</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>17.99</td>\n",
       "      <td>10.38</td>\n",
       "      <td>122.80</td>\n",
       "      <td>1001.0</td>\n",
       "      <td>0.11840</td>\n",
       "      <td>0.27760</td>\n",
       "      <td>0.3001</td>\n",
       "      <td>0.14710</td>\n",
       "      <td>0.2419</td>\n",
       "      <td>0.07871</td>\n",
       "      <td>...</td>\n",
       "      <td>25.38</td>\n",
       "      <td>17.33</td>\n",
       "      <td>184.60</td>\n",
       "      <td>2019.0</td>\n",
       "      <td>0.1622</td>\n",
       "      <td>0.6656</td>\n",
       "      <td>0.7119</td>\n",
       "      <td>0.2654</td>\n",
       "      <td>0.4601</td>\n",
       "      <td>0.11890</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>20.57</td>\n",
       "      <td>17.77</td>\n",
       "      <td>132.90</td>\n",
       "      <td>1326.0</td>\n",
       "      <td>0.08474</td>\n",
       "      <td>0.07864</td>\n",
       "      <td>0.0869</td>\n",
       "      <td>0.07017</td>\n",
       "      <td>0.1812</td>\n",
       "      <td>0.05667</td>\n",
       "      <td>...</td>\n",
       "      <td>24.99</td>\n",
       "      <td>23.41</td>\n",
       "      <td>158.80</td>\n",
       "      <td>1956.0</td>\n",
       "      <td>0.1238</td>\n",
       "      <td>0.1866</td>\n",
       "      <td>0.2416</td>\n",
       "      <td>0.1860</td>\n",
       "      <td>0.2750</td>\n",
       "      <td>0.08902</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>19.69</td>\n",
       "      <td>21.25</td>\n",
       "      <td>130.00</td>\n",
       "      <td>1203.0</td>\n",
       "      <td>0.10960</td>\n",
       "      <td>0.15990</td>\n",
       "      <td>0.1974</td>\n",
       "      <td>0.12790</td>\n",
       "      <td>0.2069</td>\n",
       "      <td>0.05999</td>\n",
       "      <td>...</td>\n",
       "      <td>23.57</td>\n",
       "      <td>25.53</td>\n",
       "      <td>152.50</td>\n",
       "      <td>1709.0</td>\n",
       "      <td>0.1444</td>\n",
       "      <td>0.4245</td>\n",
       "      <td>0.4504</td>\n",
       "      <td>0.2430</td>\n",
       "      <td>0.3613</td>\n",
       "      <td>0.08758</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>11.42</td>\n",
       "      <td>20.38</td>\n",
       "      <td>77.58</td>\n",
       "      <td>386.1</td>\n",
       "      <td>0.14250</td>\n",
       "      <td>0.28390</td>\n",
       "      <td>0.2414</td>\n",
       "      <td>0.10520</td>\n",
       "      <td>0.2597</td>\n",
       "      <td>0.09744</td>\n",
       "      <td>...</td>\n",
       "      <td>14.91</td>\n",
       "      <td>26.50</td>\n",
       "      <td>98.87</td>\n",
       "      <td>567.7</td>\n",
       "      <td>0.2098</td>\n",
       "      <td>0.8663</td>\n",
       "      <td>0.6869</td>\n",
       "      <td>0.2575</td>\n",
       "      <td>0.6638</td>\n",
       "      <td>0.17300</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>20.29</td>\n",
       "      <td>14.34</td>\n",
       "      <td>135.10</td>\n",
       "      <td>1297.0</td>\n",
       "      <td>0.10030</td>\n",
       "      <td>0.13280</td>\n",
       "      <td>0.1980</td>\n",
       "      <td>0.10430</td>\n",
       "      <td>0.1809</td>\n",
       "      <td>0.05883</td>\n",
       "      <td>...</td>\n",
       "      <td>22.54</td>\n",
       "      <td>16.67</td>\n",
       "      <td>152.20</td>\n",
       "      <td>1575.0</td>\n",
       "      <td>0.1374</td>\n",
       "      <td>0.2050</td>\n",
       "      <td>0.4000</td>\n",
       "      <td>0.1625</td>\n",
       "      <td>0.2364</td>\n",
       "      <td>0.07678</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>5 rows × 30 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "   radius_mean  texture_mean  perimeter_mean  area_mean  smoothness_mean  \\\n",
       "0        17.99         10.38          122.80     1001.0          0.11840   \n",
       "1        20.57         17.77          132.90     1326.0          0.08474   \n",
       "2        19.69         21.25          130.00     1203.0          0.10960   \n",
       "3        11.42         20.38           77.58      386.1          0.14250   \n",
       "4        20.29         14.34          135.10     1297.0          0.10030   \n",
       "\n",
       "   compactness_mean  concavity_mean  concave points_mean  symmetry_mean  \\\n",
       "0           0.27760          0.3001              0.14710         0.2419   \n",
       "1           0.07864          0.0869              0.07017         0.1812   \n",
       "2           0.15990          0.1974              0.12790         0.2069   \n",
       "3           0.28390          0.2414              0.10520         0.2597   \n",
       "4           0.13280          0.1980              0.10430         0.1809   \n",
       "\n",
       "   fractal_dimension_mean  ...  radius_worst  texture_worst  perimeter_worst  \\\n",
       "0                 0.07871  ...         25.38          17.33           184.60   \n",
       "1                 0.05667  ...         24.99          23.41           158.80   \n",
       "2                 0.05999  ...         23.57          25.53           152.50   \n",
       "3                 0.09744  ...         14.91          26.50            98.87   \n",
       "4                 0.05883  ...         22.54          16.67           152.20   \n",
       "\n",
       "   area_worst  smoothness_worst  compactness_worst  concavity_worst  \\\n",
       "0      2019.0            0.1622             0.6656           0.7119   \n",
       "1      1956.0            0.1238             0.1866           0.2416   \n",
       "2      1709.0            0.1444             0.4245           0.4504   \n",
       "3       567.7            0.2098             0.8663           0.6869   \n",
       "4      1575.0            0.1374             0.2050           0.4000   \n",
       "\n",
       "   concave points_worst  symmetry_worst  fractal_dimension_worst  \n",
       "0                0.2654          0.4601                  0.11890  \n",
       "1                0.1860          0.2750                  0.08902  \n",
       "2                0.2430          0.3613                  0.08758  \n",
       "3                0.2575          0.6638                  0.17300  \n",
       "4                0.1625          0.2364                  0.07678  \n",
       "\n",
       "[5 rows x 30 columns]"
      ]
     },
     "execution_count": 12,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "#top 5 rows of head\n",
    "X.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0    M\n",
       "1    M\n",
       "2    M\n",
       "3    M\n",
       "4    M\n",
       "Name: diagnosis, dtype: object"
      ]
     },
     "execution_count": 13,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "#top 5 rows of y\n",
    "y.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "metadata": {},
   "outputs": [],
   "source": [
    "#converting value of B and M into 1 and 0\n",
    "y = [1 if i=='M' else 0 for i in y]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "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>id</th>\n",
       "      <th>diagnosis</th>\n",
       "      <th>radius_mean</th>\n",
       "      <th>texture_mean</th>\n",
       "      <th>perimeter_mean</th>\n",
       "      <th>area_mean</th>\n",
       "      <th>smoothness_mean</th>\n",
       "      <th>compactness_mean</th>\n",
       "      <th>concavity_mean</th>\n",
       "      <th>concave points_mean</th>\n",
       "      <th>...</th>\n",
       "      <th>texture_worst</th>\n",
       "      <th>perimeter_worst</th>\n",
       "      <th>area_worst</th>\n",
       "      <th>smoothness_worst</th>\n",
       "      <th>compactness_worst</th>\n",
       "      <th>concavity_worst</th>\n",
       "      <th>concave points_worst</th>\n",
       "      <th>symmetry_worst</th>\n",
       "      <th>fractal_dimension_worst</th>\n",
       "      <th>Unnamed: 32</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>564</th>\n",
       "      <td>926424</td>\n",
       "      <td>M</td>\n",
       "      <td>21.56</td>\n",
       "      <td>22.39</td>\n",
       "      <td>142.00</td>\n",
       "      <td>1479.0</td>\n",
       "      <td>0.11100</td>\n",
       "      <td>0.11590</td>\n",
       "      <td>0.24390</td>\n",
       "      <td>0.13890</td>\n",
       "      <td>...</td>\n",
       "      <td>26.40</td>\n",
       "      <td>166.10</td>\n",
       "      <td>2027.0</td>\n",
       "      <td>0.14100</td>\n",
       "      <td>0.21130</td>\n",
       "      <td>0.4107</td>\n",
       "      <td>0.2216</td>\n",
       "      <td>0.2060</td>\n",
       "      <td>0.07115</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>565</th>\n",
       "      <td>926682</td>\n",
       "      <td>M</td>\n",
       "      <td>20.13</td>\n",
       "      <td>28.25</td>\n",
       "      <td>131.20</td>\n",
       "      <td>1261.0</td>\n",
       "      <td>0.09780</td>\n",
       "      <td>0.10340</td>\n",
       "      <td>0.14400</td>\n",
       "      <td>0.09791</td>\n",
       "      <td>...</td>\n",
       "      <td>38.25</td>\n",
       "      <td>155.00</td>\n",
       "      <td>1731.0</td>\n",
       "      <td>0.11660</td>\n",
       "      <td>0.19220</td>\n",
       "      <td>0.3215</td>\n",
       "      <td>0.1628</td>\n",
       "      <td>0.2572</td>\n",
       "      <td>0.06637</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>566</th>\n",
       "      <td>926954</td>\n",
       "      <td>M</td>\n",
       "      <td>16.60</td>\n",
       "      <td>28.08</td>\n",
       "      <td>108.30</td>\n",
       "      <td>858.1</td>\n",
       "      <td>0.08455</td>\n",
       "      <td>0.10230</td>\n",
       "      <td>0.09251</td>\n",
       "      <td>0.05302</td>\n",
       "      <td>...</td>\n",
       "      <td>34.12</td>\n",
       "      <td>126.70</td>\n",
       "      <td>1124.0</td>\n",
       "      <td>0.11390</td>\n",
       "      <td>0.30940</td>\n",
       "      <td>0.3403</td>\n",
       "      <td>0.1418</td>\n",
       "      <td>0.2218</td>\n",
       "      <td>0.07820</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>567</th>\n",
       "      <td>927241</td>\n",
       "      <td>M</td>\n",
       "      <td>20.60</td>\n",
       "      <td>29.33</td>\n",
       "      <td>140.10</td>\n",
       "      <td>1265.0</td>\n",
       "      <td>0.11780</td>\n",
       "      <td>0.27700</td>\n",
       "      <td>0.35140</td>\n",
       "      <td>0.15200</td>\n",
       "      <td>...</td>\n",
       "      <td>39.42</td>\n",
       "      <td>184.60</td>\n",
       "      <td>1821.0</td>\n",
       "      <td>0.16500</td>\n",
       "      <td>0.86810</td>\n",
       "      <td>0.9387</td>\n",
       "      <td>0.2650</td>\n",
       "      <td>0.4087</td>\n",
       "      <td>0.12400</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>568</th>\n",
       "      <td>92751</td>\n",
       "      <td>B</td>\n",
       "      <td>7.76</td>\n",
       "      <td>24.54</td>\n",
       "      <td>47.92</td>\n",
       "      <td>181.0</td>\n",
       "      <td>0.05263</td>\n",
       "      <td>0.04362</td>\n",
       "      <td>0.00000</td>\n",
       "      <td>0.00000</td>\n",
       "      <td>...</td>\n",
       "      <td>30.37</td>\n",
       "      <td>59.16</td>\n",
       "      <td>268.6</td>\n",
       "      <td>0.08996</td>\n",
       "      <td>0.06444</td>\n",
       "      <td>0.0000</td>\n",
       "      <td>0.0000</td>\n",
       "      <td>0.2871</td>\n",
       "      <td>0.07039</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>5 rows × 33 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "         id diagnosis  radius_mean  texture_mean  perimeter_mean  area_mean  \\\n",
       "564  926424         M        21.56         22.39          142.00     1479.0   \n",
       "565  926682         M        20.13         28.25          131.20     1261.0   \n",
       "566  926954         M        16.60         28.08          108.30      858.1   \n",
       "567  927241         M        20.60         29.33          140.10     1265.0   \n",
       "568   92751         B         7.76         24.54           47.92      181.0   \n",
       "\n",
       "     smoothness_mean  compactness_mean  concavity_mean  concave points_mean  \\\n",
       "564          0.11100           0.11590         0.24390              0.13890   \n",
       "565          0.09780           0.10340         0.14400              0.09791   \n",
       "566          0.08455           0.10230         0.09251              0.05302   \n",
       "567          0.11780           0.27700         0.35140              0.15200   \n",
       "568          0.05263           0.04362         0.00000              0.00000   \n",
       "\n",
       "     ...  texture_worst  perimeter_worst  area_worst  smoothness_worst  \\\n",
       "564  ...          26.40           166.10      2027.0           0.14100   \n",
       "565  ...          38.25           155.00      1731.0           0.11660   \n",
       "566  ...          34.12           126.70      1124.0           0.11390   \n",
       "567  ...          39.42           184.60      1821.0           0.16500   \n",
       "568  ...          30.37            59.16       268.6           0.08996   \n",
       "\n",
       "     compactness_worst  concavity_worst  concave points_worst  symmetry_worst  \\\n",
       "564            0.21130           0.4107                0.2216          0.2060   \n",
       "565            0.19220           0.3215                0.1628          0.2572   \n",
       "566            0.30940           0.3403                0.1418          0.2218   \n",
       "567            0.86810           0.9387                0.2650          0.4087   \n",
       "568            0.06444           0.0000                0.0000          0.2871   \n",
       "\n",
       "     fractal_dimension_worst  Unnamed: 32  \n",
       "564                  0.07115          NaN  \n",
       "565                  0.06637          NaN  \n",
       "566                  0.07820          NaN  \n",
       "567                  0.12400          NaN  \n",
       "568                  0.07039          NaN  \n",
       "\n",
       "[5 rows x 33 columns]"
      ]
     },
     "execution_count": 15,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "#Tail of the dataset\n",
    "data.tail()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "metadata": {},
   "outputs": [],
   "source": [
    "#train test split into 80 % and 20% dataset\n",
    "X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=0)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "(455, 30)\n",
      "(114, 30)\n"
     ]
    }
   ],
   "source": [
    "#shape of the dataset\n",
    "print(X_train.shape)\n",
    "print(X_test.shape)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "455"
      ]
     },
     "execution_count": 18,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "len(y_train)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 19,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "GradientBoostingClassifier(learning_rate=0.01, n_estimators=50, random_state=0)"
      ]
     },
     "execution_count": 19,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "#initalizing the Adaboost model\n",
    "classifier = GradientBoostingClassifier (min_samples_split=2,max_depth=3,max_features=None,learning_rate=0.01 , n_estimators = 50,random_state=0)\n",
    "classifier.fit(X_train, y_train)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 20,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 0, 1, 0, 1, 1, 1, 1, 1,\n",
       "       0, 0, 1, 0, 0, 1, 0, 1, 0, 1, 0, 1, 0, 1, 0, 1, 0, 1, 0, 0, 1, 0,\n",
       "       0, 1, 0, 0, 0, 1, 1, 1, 1, 0, 0, 0, 0, 0, 0, 1, 1, 1, 0, 0, 1, 0,\n",
       "       1, 1, 1, 0, 0, 1, 0, 0, 1, 0, 0, 0, 0, 0, 1, 1, 1, 0, 1, 0, 0, 0,\n",
       "       1, 1, 0, 1, 0, 1, 0, 0, 1, 0, 0, 0, 0, 0, 0, 0, 1, 0, 1, 0, 1, 0,\n",
       "       0, 1, 1, 0])"
      ]
     },
     "execution_count": 20,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "#predicting values\n",
    "y_predict = classifier.predict(X_test)\n",
    "y_predict"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 21,
   "metadata": {},
   "outputs": [],
   "source": [
    "#confusion matrix\n",
    "cm = confusion_matrix(y_test, y_predict)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 22,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<matplotlib.axes._subplots.AxesSubplot at 0x1d940417198>"
      ]
     },
     "execution_count": 22,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x288 with 2 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "sns.heatmap(cm, annot= True)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 23,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "0.9649122807017544\n",
      "              precision    recall  f1-score   support\n",
      "\n",
      "           0       0.96      0.99      0.97        67\n",
      "           1       0.98      0.94      0.96        47\n",
      "\n",
      "    accuracy                           0.96       114\n",
      "   macro avg       0.97      0.96      0.96       114\n",
      "weighted avg       0.97      0.96      0.96       114\n",
      "\n"
     ]
    }
   ],
   "source": [
    "#Accuracy and Classification report\n",
    "print(accuracy_score(y_test,y_predict))\n",
    "print(classification_report(y_test, y_predict))"
   ]
  },
  {
   "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": "3.6.1"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 4
}