SVC_Cancer.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [],
   "source": [
    "import numpy as np\n",
    "import pandas as pd\n",
    "import matplotlib.pyplot as plt\n",
    "import seaborn as sns\n",
    "\n",
    "%matplotlib inline"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [],
   "source": [
    "from sklearn.datasets import load_breast_cancer\n",
    "cancer = load_breast_cancer()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "dict_keys(['data', 'target', 'target_names', 'DESCR', 'feature_names', 'filename'])"
      ]
     },
     "execution_count": 3,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "cancer.keys()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "sklearn.utils.Bunch"
      ]
     },
     "execution_count": 4,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "type(cancer)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      ".. _breast_cancer_dataset:\n",
      "\n",
      "Breast cancer wisconsin (diagnostic) dataset\n",
      "--------------------------------------------\n",
      "\n",
      "**Data Set Characteristics:**\n",
      "\n",
      "    :Number of Instances: 569\n",
      "\n",
      "    :Number of Attributes: 30 numeric, predictive attributes and the class\n",
      "\n",
      "    :Attribute Information:\n",
      "        - radius (mean of distances from center to points on the perimeter)\n",
      "        - texture (standard deviation of gray-scale values)\n",
      "        - perimeter\n",
      "        - area\n",
      "        - smoothness (local variation in radius lengths)\n",
      "        - compactness (perimeter^2 / area - 1.0)\n",
      "        - concavity (severity of concave portions of the contour)\n",
      "        - concave points (number of concave portions of the contour)\n",
      "        - symmetry \n",
      "        - fractal dimension (\"coastline approximation\" - 1)\n",
      "\n",
      "        The mean, standard error, and \"worst\" or largest (mean of the three\n",
      "        largest values) of these features were computed for each image,\n",
      "        resulting in 30 features.  For instance, field 3 is Mean Radius, field\n",
      "        13 is Radius SE, field 23 is Worst Radius.\n",
      "\n",
      "        - class:\n",
      "                - WDBC-Malignant\n",
      "                - WDBC-Benign\n",
      "\n",
      "    :Summary Statistics:\n",
      "\n",
      "    ===================================== ====== ======\n",
      "                                           Min    Max\n",
      "    ===================================== ====== ======\n",
      "    radius (mean):                        6.981  28.11\n",
      "    texture (mean):                       9.71   39.28\n",
      "    perimeter (mean):                     43.79  188.5\n",
      "    area (mean):                          143.5  2501.0\n",
      "    smoothness (mean):                    0.053  0.163\n",
      "    compactness (mean):                   0.019  0.345\n",
      "    concavity (mean):                     0.0    0.427\n",
      "    concave points (mean):                0.0    0.201\n",
      "    symmetry (mean):                      0.106  0.304\n",
      "    fractal dimension (mean):             0.05   0.097\n",
      "    radius (standard error):              0.112  2.873\n",
      "    texture (standard error):             0.36   4.885\n",
      "    perimeter (standard error):           0.757  21.98\n",
      "    area (standard error):                6.802  542.2\n",
      "    smoothness (standard error):          0.002  0.031\n",
      "    compactness (standard error):         0.002  0.135\n",
      "    concavity (standard error):           0.0    0.396\n",
      "    concave points (standard error):      0.0    0.053\n",
      "    symmetry (standard error):            0.008  0.079\n",
      "    fractal dimension (standard error):   0.001  0.03\n",
      "    radius (worst):                       7.93   36.04\n",
      "    texture (worst):                      12.02  49.54\n",
      "    perimeter (worst):                    50.41  251.2\n",
      "    area (worst):                         185.2  4254.0\n",
      "    smoothness (worst):                   0.071  0.223\n",
      "    compactness (worst):                  0.027  1.058\n",
      "    concavity (worst):                    0.0    1.252\n",
      "    concave points (worst):               0.0    0.291\n",
      "    symmetry (worst):                     0.156  0.664\n",
      "    fractal dimension (worst):            0.055  0.208\n",
      "    ===================================== ====== ======\n",
      "\n",
      "    :Missing Attribute Values: None\n",
      "\n",
      "    :Class Distribution: 212 - Malignant, 357 - Benign\n",
      "\n",
      "    :Creator:  Dr. William H. Wolberg, W. Nick Street, Olvi L. Mangasarian\n",
      "\n",
      "    :Donor: Nick Street\n",
      "\n",
      "    :Date: November, 1995\n",
      "\n",
      "This is a copy of UCI ML Breast Cancer Wisconsin (Diagnostic) datasets.\n",
      "https://goo.gl/U2Uwz2\n",
      "\n",
      "Features are computed from a digitized image of a fine needle\n",
      "aspirate (FNA) of a breast mass.  They describe\n",
      "characteristics of the cell nuclei present in the image.\n",
      "\n",
      "Separating plane described above was obtained using\n",
      "Multisurface Method-Tree (MSM-T) [K. P. Bennett, \"Decision Tree\n",
      "Construction Via Linear Programming.\" Proceedings of the 4th\n",
      "Midwest Artificial Intelligence and Cognitive Science Society,\n",
      "pp. 97-101, 1992], a classification method which uses linear\n",
      "programming to construct a decision tree.  Relevant features\n",
      "were selected using an exhaustive search in the space of 1-4\n",
      "features and 1-3 separating planes.\n",
      "\n",
      "The actual linear program used to obtain the separating plane\n",
      "in the 3-dimensional space is that described in:\n",
      "[K. P. Bennett and O. L. Mangasarian: \"Robust Linear\n",
      "Programming Discrimination of Two Linearly Inseparable Sets\",\n",
      "Optimization Methods and Software 1, 1992, 23-34].\n",
      "\n",
      "This database is also available through the UW CS ftp server:\n",
      "\n",
      "ftp ftp.cs.wisc.edu\n",
      "cd math-prog/cpo-dataset/machine-learn/WDBC/\n",
      "\n",
      ".. topic:: References\n",
      "\n",
      "   - W.N. Street, W.H. Wolberg and O.L. Mangasarian. Nuclear feature extraction \n",
      "     for breast tumor diagnosis. IS&T/SPIE 1993 International Symposium on \n",
      "     Electronic Imaging: Science and Technology, volume 1905, pages 861-870,\n",
      "     San Jose, CA, 1993.\n",
      "   - O.L. Mangasarian, W.N. Street and W.H. Wolberg. Breast cancer diagnosis and \n",
      "     prognosis via linear programming. Operations Research, 43(4), pages 570-577, \n",
      "     July-August 1995.\n",
      "   - W.H. Wolberg, W.N. Street, and O.L. Mangasarian. Machine learning techniques\n",
      "     to diagnose breast cancer from fine-needle aspirates. Cancer Letters 77 (1994) \n",
      "     163-171.\n"
     ]
    }
   ],
   "source": [
    "print(cancer['DESCR'])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [],
   "source": [
    "df = pd.DataFrame(cancer['data'], columns = cancer['feature_names'])"
   ]
  },
  {
   "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>mean radius</th>\n",
       "      <th>mean texture</th>\n",
       "      <th>mean perimeter</th>\n",
       "      <th>mean area</th>\n",
       "      <th>mean smoothness</th>\n",
       "      <th>mean compactness</th>\n",
       "      <th>mean concavity</th>\n",
       "      <th>mean concave points</th>\n",
       "      <th>mean symmetry</th>\n",
       "      <th>mean fractal dimension</th>\n",
       "      <th>...</th>\n",
       "      <th>worst radius</th>\n",
       "      <th>worst texture</th>\n",
       "      <th>worst perimeter</th>\n",
       "      <th>worst area</th>\n",
       "      <th>worst smoothness</th>\n",
       "      <th>worst compactness</th>\n",
       "      <th>worst concavity</th>\n",
       "      <th>worst concave points</th>\n",
       "      <th>worst symmetry</th>\n",
       "      <th>worst fractal dimension</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": [
       "   mean radius  mean texture  mean perimeter  mean area  mean smoothness  \\\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",
       "   mean compactness  mean concavity  mean concave points  mean symmetry  \\\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",
       "   mean fractal dimension  ...  worst radius  worst texture  worst perimeter  \\\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",
       "   worst area  worst smoothness  worst compactness  worst concavity  \\\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",
       "   worst concave points  worst symmetry  worst fractal dimension  \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": 9,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "Index(['mean radius', 'mean texture', 'mean perimeter', 'mean area',\n",
       "       'mean smoothness', 'mean compactness', 'mean concavity',\n",
       "       'mean concave points', 'mean symmetry', 'mean fractal dimension',\n",
       "       'radius error', 'texture error', 'perimeter error', 'area error',\n",
       "       'smoothness error', 'compactness error', 'concavity error',\n",
       "       'concave points error', 'symmetry error', 'fractal dimension error',\n",
       "       'worst radius', 'worst texture', 'worst perimeter', 'worst area',\n",
       "       'worst smoothness', 'worst compactness', 'worst concavity',\n",
       "       'worst concave points', 'worst symmetry', 'worst fractal dimension'],\n",
       "      dtype='object')"
      ]
     },
     "execution_count": 7,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.columns"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "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>mean radius</th>\n",
       "      <th>mean texture</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>17.990</td>\n",
       "      <td>10.38</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>20.570</td>\n",
       "      <td>17.77</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>19.690</td>\n",
       "      <td>21.25</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>11.420</td>\n",
       "      <td>20.38</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>20.290</td>\n",
       "      <td>14.34</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5</th>\n",
       "      <td>12.450</td>\n",
       "      <td>15.70</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6</th>\n",
       "      <td>18.250</td>\n",
       "      <td>19.98</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>7</th>\n",
       "      <td>13.710</td>\n",
       "      <td>20.83</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>8</th>\n",
       "      <td>13.000</td>\n",
       "      <td>21.82</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>9</th>\n",
       "      <td>12.460</td>\n",
       "      <td>24.04</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>10</th>\n",
       "      <td>16.020</td>\n",
       "      <td>23.24</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>11</th>\n",
       "      <td>15.780</td>\n",
       "      <td>17.89</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>12</th>\n",
       "      <td>19.170</td>\n",
       "      <td>24.80</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>13</th>\n",
       "      <td>15.850</td>\n",
       "      <td>23.95</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>14</th>\n",
       "      <td>13.730</td>\n",
       "      <td>22.61</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>15</th>\n",
       "      <td>14.540</td>\n",
       "      <td>27.54</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>16</th>\n",
       "      <td>14.680</td>\n",
       "      <td>20.13</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>17</th>\n",
       "      <td>16.130</td>\n",
       "      <td>20.68</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>18</th>\n",
       "      <td>19.810</td>\n",
       "      <td>22.15</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>19</th>\n",
       "      <td>13.540</td>\n",
       "      <td>14.36</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>20</th>\n",
       "      <td>13.080</td>\n",
       "      <td>15.71</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>21</th>\n",
       "      <td>9.504</td>\n",
       "      <td>12.44</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>22</th>\n",
       "      <td>15.340</td>\n",
       "      <td>14.26</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>23</th>\n",
       "      <td>21.160</td>\n",
       "      <td>23.04</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>24</th>\n",
       "      <td>16.650</td>\n",
       "      <td>21.38</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>25</th>\n",
       "      <td>17.140</td>\n",
       "      <td>16.40</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>26</th>\n",
       "      <td>14.580</td>\n",
       "      <td>21.53</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>27</th>\n",
       "      <td>18.610</td>\n",
       "      <td>20.25</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>28</th>\n",
       "      <td>15.300</td>\n",
       "      <td>25.27</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>29</th>\n",
       "      <td>17.570</td>\n",
       "      <td>15.05</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>539</th>\n",
       "      <td>7.691</td>\n",
       "      <td>25.44</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>540</th>\n",
       "      <td>11.540</td>\n",
       "      <td>14.44</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>541</th>\n",
       "      <td>14.470</td>\n",
       "      <td>24.99</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>542</th>\n",
       "      <td>14.740</td>\n",
       "      <td>25.42</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>543</th>\n",
       "      <td>13.210</td>\n",
       "      <td>28.06</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>544</th>\n",
       "      <td>13.870</td>\n",
       "      <td>20.70</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>545</th>\n",
       "      <td>13.620</td>\n",
       "      <td>23.23</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>546</th>\n",
       "      <td>10.320</td>\n",
       "      <td>16.35</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>547</th>\n",
       "      <td>10.260</td>\n",
       "      <td>16.58</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>548</th>\n",
       "      <td>9.683</td>\n",
       "      <td>19.34</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>549</th>\n",
       "      <td>10.820</td>\n",
       "      <td>24.21</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>550</th>\n",
       "      <td>10.860</td>\n",
       "      <td>21.48</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>551</th>\n",
       "      <td>11.130</td>\n",
       "      <td>22.44</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>552</th>\n",
       "      <td>12.770</td>\n",
       "      <td>29.43</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>553</th>\n",
       "      <td>9.333</td>\n",
       "      <td>21.94</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>554</th>\n",
       "      <td>12.880</td>\n",
       "      <td>28.92</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>555</th>\n",
       "      <td>10.290</td>\n",
       "      <td>27.61</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>556</th>\n",
       "      <td>10.160</td>\n",
       "      <td>19.59</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>557</th>\n",
       "      <td>9.423</td>\n",
       "      <td>27.88</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>558</th>\n",
       "      <td>14.590</td>\n",
       "      <td>22.68</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>559</th>\n",
       "      <td>11.510</td>\n",
       "      <td>23.93</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>560</th>\n",
       "      <td>14.050</td>\n",
       "      <td>27.15</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>561</th>\n",
       "      <td>11.200</td>\n",
       "      <td>29.37</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>562</th>\n",
       "      <td>15.220</td>\n",
       "      <td>30.62</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>563</th>\n",
       "      <td>20.920</td>\n",
       "      <td>25.09</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>564</th>\n",
       "      <td>21.560</td>\n",
       "      <td>22.39</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>565</th>\n",
       "      <td>20.130</td>\n",
       "      <td>28.25</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>566</th>\n",
       "      <td>16.600</td>\n",
       "      <td>28.08</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>567</th>\n",
       "      <td>20.600</td>\n",
       "      <td>29.33</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>568</th>\n",
       "      <td>7.760</td>\n",
       "      <td>24.54</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>569 rows × 2 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "     mean radius  mean texture\n",
       "0         17.990         10.38\n",
       "1         20.570         17.77\n",
       "2         19.690         21.25\n",
       "3         11.420         20.38\n",
       "4         20.290         14.34\n",
       "5         12.450         15.70\n",
       "6         18.250         19.98\n",
       "7         13.710         20.83\n",
       "8         13.000         21.82\n",
       "9         12.460         24.04\n",
       "10        16.020         23.24\n",
       "11        15.780         17.89\n",
       "12        19.170         24.80\n",
       "13        15.850         23.95\n",
       "14        13.730         22.61\n",
       "15        14.540         27.54\n",
       "16        14.680         20.13\n",
       "17        16.130         20.68\n",
       "18        19.810         22.15\n",
       "19        13.540         14.36\n",
       "20        13.080         15.71\n",
       "21         9.504         12.44\n",
       "22        15.340         14.26\n",
       "23        21.160         23.04\n",
       "24        16.650         21.38\n",
       "25        17.140         16.40\n",
       "26        14.580         21.53\n",
       "27        18.610         20.25\n",
       "28        15.300         25.27\n",
       "29        17.570         15.05\n",
       "..           ...           ...\n",
       "539        7.691         25.44\n",
       "540       11.540         14.44\n",
       "541       14.470         24.99\n",
       "542       14.740         25.42\n",
       "543       13.210         28.06\n",
       "544       13.870         20.70\n",
       "545       13.620         23.23\n",
       "546       10.320         16.35\n",
       "547       10.260         16.58\n",
       "548        9.683         19.34\n",
       "549       10.820         24.21\n",
       "550       10.860         21.48\n",
       "551       11.130         22.44\n",
       "552       12.770         29.43\n",
       "553        9.333         21.94\n",
       "554       12.880         28.92\n",
       "555       10.290         27.61\n",
       "556       10.160         19.59\n",
       "557        9.423         27.88\n",
       "558       14.590         22.68\n",
       "559       11.510         23.93\n",
       "560       14.050         27.15\n",
       "561       11.200         29.37\n",
       "562       15.220         30.62\n",
       "563       20.920         25.09\n",
       "564       21.560         22.39\n",
       "565       20.130         28.25\n",
       "566       16.600         28.08\n",
       "567       20.600         29.33\n",
       "568        7.760         24.54\n",
       "\n",
       "[569 rows x 2 columns]"
      ]
     },
     "execution_count": 16,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "test = df[['mean radius', 'mean texture']]\n",
    "test"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array(['malignant', 'benign'], dtype='<U9')"
      ]
     },
     "execution_count": 12,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "cancer['target_names']"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "metadata": {},
   "outputs": [],
   "source": [
    "##EDA"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "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>mean radius</th>\n",
       "      <th>mean texture</th>\n",
       "      <th>mean perimeter</th>\n",
       "      <th>mean area</th>\n",
       "      <th>mean smoothness</th>\n",
       "      <th>mean compactness</th>\n",
       "      <th>mean concavity</th>\n",
       "      <th>mean concave points</th>\n",
       "      <th>mean symmetry</th>\n",
       "      <th>mean fractal dimension</th>\n",
       "      <th>...</th>\n",
       "      <th>worst radius</th>\n",
       "      <th>worst texture</th>\n",
       "      <th>worst perimeter</th>\n",
       "      <th>worst area</th>\n",
       "      <th>worst smoothness</th>\n",
       "      <th>worst compactness</th>\n",
       "      <th>worst concavity</th>\n",
       "      <th>worst concave points</th>\n",
       "      <th>worst symmetry</th>\n",
       "      <th>worst fractal dimension</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": [
       "   mean radius  mean texture  mean perimeter  mean area  mean smoothness  \\\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",
       "   mean compactness  mean concavity  mean concave points  mean symmetry  \\\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",
       "   mean fractal dimension  ...  worst radius  worst texture  worst perimeter  \\\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",
       "   worst area  worst smoothness  worst compactness  worst concavity  \\\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",
       "   worst concave points  worst symmetry  worst fractal dimension  \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": 14,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 1, 1,\n",
       "       0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0, 0, 0, 0, 0,\n",
       "       0, 0, 1, 0, 1, 1, 1, 1, 1, 0, 0, 1, 0, 0, 1, 1, 1, 1, 0, 1, 0, 0,\n",
       "       1, 1, 1, 1, 0, 1, 0, 0, 1, 0, 1, 0, 0, 1, 1, 1, 0, 0, 1, 0, 0, 0,\n",
       "       1, 1, 1, 0, 1, 1, 0, 0, 1, 1, 1, 0, 0, 1, 1, 1, 1, 0, 1, 1, 0, 1,\n",
       "       1, 1, 1, 1, 1, 1, 1, 0, 0, 0, 1, 0, 0, 1, 1, 1, 0, 0, 1, 0, 1, 0,\n",
       "       0, 1, 0, 0, 1, 1, 0, 1, 1, 0, 1, 1, 1, 1, 0, 1, 1, 1, 1, 1, 1, 1,\n",
       "       1, 1, 0, 1, 1, 1, 1, 0, 0, 1, 0, 1, 1, 0, 0, 1, 1, 0, 0, 1, 1, 1,\n",
       "       1, 0, 1, 1, 0, 0, 0, 1, 0, 1, 0, 1, 1, 1, 0, 1, 1, 0, 0, 1, 0, 0,\n",
       "       0, 0, 1, 0, 0, 0, 1, 0, 1, 0, 1, 1, 0, 1, 0, 0, 0, 0, 1, 1, 0, 0,\n",
       "       1, 1, 1, 0, 1, 1, 1, 1, 1, 0, 0, 1, 1, 0, 1, 1, 0, 0, 1, 0, 1, 1,\n",
       "       1, 1, 0, 1, 1, 1, 1, 1, 0, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,\n",
       "       0, 0, 1, 1, 1, 1, 1, 1, 0, 1, 0, 1, 1, 0, 1, 1, 0, 1, 0, 0, 1, 1,\n",
       "       1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 1, 1, 0, 1, 0, 1, 1, 1, 1, 1,\n",
       "       1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 1, 1, 1, 0, 1, 0, 1, 1, 1, 1, 0, 0,\n",
       "       0, 1, 1, 1, 1, 0, 1, 0, 1, 0, 1, 1, 1, 0, 1, 1, 1, 1, 1, 1, 1, 0,\n",
       "       0, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 0, 1, 0, 0, 0, 1, 0, 0,\n",
       "       1, 1, 1, 1, 1, 0, 1, 1, 1, 1, 1, 0, 1, 1, 1, 0, 1, 1, 0, 0, 1, 1,\n",
       "       1, 1, 1, 1, 0, 1, 1, 1, 1, 1, 1, 1, 0, 1, 1, 1, 1, 1, 0, 1, 1, 0,\n",
       "       1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 1, 0, 0, 1, 0, 1, 1, 1, 1,\n",
       "       1, 0, 1, 1, 0, 1, 0, 1, 1, 0, 1, 0, 1, 1, 1, 1, 1, 1, 1, 1, 0, 0,\n",
       "       1, 1, 1, 1, 1, 1, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 1, 1, 1, 1,\n",
       "       1, 1, 1, 0, 1, 0, 1, 1, 0, 1, 1, 1, 1, 1, 0, 0, 1, 0, 1, 0, 1, 1,\n",
       "       1, 1, 1, 0, 1, 1, 0, 1, 0, 1, 0, 0, 1, 1, 1, 0, 1, 1, 1, 1, 1, 1,\n",
       "       1, 1, 1, 1, 1, 0, 1, 0, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,\n",
       "       1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 0, 0, 0, 0, 0, 1])"
      ]
     },
     "execution_count": 15,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "X = df\n",
    "y = cancer['target']\n",
    "y"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "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>mean radius</th>\n",
       "      <th>mean texture</th>\n",
       "      <th>mean perimeter</th>\n",
       "      <th>mean area</th>\n",
       "      <th>mean smoothness</th>\n",
       "      <th>mean compactness</th>\n",
       "      <th>mean concavity</th>\n",
       "      <th>mean concave points</th>\n",
       "      <th>mean symmetry</th>\n",
       "      <th>mean fractal dimension</th>\n",
       "      <th>...</th>\n",
       "      <th>worst radius</th>\n",
       "      <th>worst texture</th>\n",
       "      <th>worst perimeter</th>\n",
       "      <th>worst area</th>\n",
       "      <th>worst smoothness</th>\n",
       "      <th>worst compactness</th>\n",
       "      <th>worst concavity</th>\n",
       "      <th>worst concave points</th>\n",
       "      <th>worst symmetry</th>\n",
       "      <th>worst fractal dimension</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": [
       "   mean radius  mean texture  mean perimeter  mean area  mean smoothness  \\\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",
       "   mean compactness  mean concavity  mean concave points  mean symmetry  \\\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",
       "   mean fractal dimension  ...  worst radius  worst texture  worst perimeter  \\\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",
       "   worst area  worst smoothness  worst compactness  worst concavity  \\\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",
       "   worst concave points  worst symmetry  worst fractal dimension  \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": 16,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "X.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "metadata": {},
   "outputs": [],
   "source": [
    "from sklearn.model_selection import train_test_split\n",
    "X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.3, random_state=101)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\svm\\base.py:193: FutureWarning: The default value of gamma will change from 'auto' to 'scale' in version 0.22 to account better for unscaled features. Set gamma explicitly to 'auto' or 'scale' to avoid this warning.\n",
      "  \"avoid this warning.\", FutureWarning)\n"
     ]
    }
   ],
   "source": [
    "from sklearn.svm import SVC\n",
    "svm = SVC()\n",
    "svm.fit(X_train, y_train)\n",
    "\n",
    "pred = svm.predict(X_test)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 19,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,\n",
       "       1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,\n",
       "       1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,\n",
       "       1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,\n",
       "       1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,\n",
       "       1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,\n",
       "       1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,\n",
       "       1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1])"
      ]
     },
     "execution_count": 19,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "pred"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 20,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([1, 1, 1, 0, 1, 1, 1, 0, 1, 1, 0, 1, 1, 1, 0, 1, 1, 1, 0, 0, 1, 1,\n",
       "       1, 1, 0, 1, 0, 1, 0, 0, 1, 0, 1, 0, 1, 1, 0, 0, 0, 0, 0, 1, 1, 1,\n",
       "       1, 1, 0, 1, 0, 1, 0, 1, 1, 0, 1, 1, 0, 0, 1, 1, 0, 0, 1, 1, 0, 1,\n",
       "       1, 0, 0, 1, 0, 1, 1, 1, 0, 0, 1, 0, 0, 1, 1, 1, 1, 1, 1, 1, 0, 1,\n",
       "       0, 0, 1, 0, 0, 1, 1, 1, 1, 1, 0, 0, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1,\n",
       "       1, 1, 1, 0, 1, 1, 1, 0, 0, 0, 0, 0, 0, 1, 1, 1, 1, 1, 1, 1, 0, 0,\n",
       "       1, 1, 1, 1, 0, 0, 0, 1, 0, 1, 0, 1, 1, 1, 1, 1, 1, 1, 1, 0, 0, 0,\n",
       "       1, 0, 1, 0, 1, 1, 0, 1, 1, 0, 0, 0, 1, 1, 1, 0, 0])"
      ]
     },
     "execution_count": 20,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "y_test"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 21,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([1, 1, 0, 0, 1, 1, 1, 1, 1, 1, 0, 0, 1, 1, 1, 0, 1, 0, 0, 1, 0, 1,\n",
       "       1, 1, 1, 1, 1, 0, 1, 1, 1, 0, 1, 1, 0, 1, 0, 0, 0, 0, 1, 1, 1, 1,\n",
       "       1, 1, 1, 1, 1, 1, 1, 1, 0, 0, 1, 1, 1, 1, 1, 0, 0, 0, 1, 1, 1, 0,\n",
       "       1, 1, 1, 1, 1, 0, 0, 0, 1, 1, 0, 0, 1, 1, 0, 0, 0, 0, 0, 0, 1, 1,\n",
       "       0, 1, 1, 1, 1, 1, 0, 0, 0, 0, 1, 0, 1, 1, 1, 0, 1, 1, 1, 1, 0, 1,\n",
       "       1, 1, 0, 0, 0, 0, 1, 0, 0, 0, 1, 1, 0, 1, 1, 1, 1, 0, 1, 0, 0, 0,\n",
       "       1, 0, 1, 1, 1, 1, 0, 1, 1, 1, 1, 0, 1, 0, 1, 0, 1, 0, 1, 0, 1, 1,\n",
       "       0, 1, 0, 1, 1, 0, 1, 1, 1, 0, 1, 1, 0, 0, 1, 0, 1, 1, 0, 1, 0, 0,\n",
       "       1, 0, 1, 1, 1, 1, 1, 1, 1, 0, 0, 0, 0, 1, 1, 0, 1, 1, 1, 1, 1, 1,\n",
       "       1, 1, 0, 0, 1, 0, 1, 0, 0, 1, 0, 1, 1, 1, 1, 1, 1, 0, 1, 0, 1, 0,\n",
       "       1, 1, 1, 0, 1, 1, 1, 0, 1, 1, 0, 1, 1, 1, 1, 1, 0, 1, 1, 1, 0, 1,\n",
       "       0, 1, 1, 0, 1, 1, 1, 1, 1, 1, 1, 0, 1, 1, 0, 1, 1, 1, 1, 1, 0, 1,\n",
       "       0, 0, 1, 0, 0, 1, 1, 0, 1, 1, 1, 1, 1, 1, 0, 1, 1, 0, 0, 1, 1, 1,\n",
       "       1, 0, 1, 0, 1, 0, 1, 0, 1, 0, 1, 1, 1, 1, 1, 1, 1, 0, 1, 0, 0, 1,\n",
       "       0, 1, 0, 1, 1, 0, 1, 1, 1, 0, 0, 1, 1, 0, 0, 1, 1, 0, 0, 0, 0, 1,\n",
       "       1, 0, 0, 0, 1, 1, 1, 1, 1, 1, 1, 1, 0, 1, 1, 0, 0, 0, 1, 1, 0, 0,\n",
       "       1, 0, 1, 1, 0, 1, 1, 1, 0, 0, 1, 1, 1, 1, 0, 1, 1, 1, 1, 1, 0, 0,\n",
       "       0, 1, 0, 0, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 1, 0, 1, 1, 1, 0, 0,\n",
       "       0, 1])"
      ]
     },
     "execution_count": 21,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "y_train"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 22,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "[[  0  66]\n",
      " [  0 105]]\n",
      "\n",
      "\n",
      "              precision    recall  f1-score   support\n",
      "\n",
      "           0       0.00      0.00      0.00        66\n",
      "           1       0.61      1.00      0.76       105\n",
      "\n",
      "    accuracy                           0.61       171\n",
      "   macro avg       0.31      0.50      0.38       171\n",
      "weighted avg       0.38      0.61      0.47       171\n",
      "\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\metrics\\classification.py:1437: UndefinedMetricWarning: Precision and F-score are ill-defined and being set to 0.0 in labels with no predicted samples.\n",
      "  'precision', 'predicted', average, warn_for)\n"
     ]
    }
   ],
   "source": [
    "from sklearn.metrics import classification_report, confusion_matrix\n",
    "\n",
    "print(confusion_matrix(y_test, pred))\n",
    "print('\\n')\n",
    "print(classification_report(y_test, pred))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 23,
   "metadata": {},
   "outputs": [],
   "source": [
    "from sklearn.model_selection import GridSearchCV"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 26,
   "metadata": {},
   "outputs": [],
   "source": [
    "param_grid = {'C': [0.1, 1, 10, 100, 1000],\n",
    "            'gamma': [1, 0.1, 0.001, 0.0001, 0.1]}"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 27,
   "metadata": {},
   "outputs": [],
   "source": [
    "grid = GridSearchCV(SVC(), \n",
    "                   param_grid,\n",
    "                   verbose = 3)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 28,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "C:\\ProgramData\\Anaconda3\\lib\\site-packages\\sklearn\\model_selection\\_split.py:1978: FutureWarning: The default value of cv will change from 3 to 5 in version 0.22. Specify it explicitly to silence this warning.\n",
      "  warnings.warn(CV_WARNING, FutureWarning)\n",
      "[Parallel(n_jobs=1)]: Using backend SequentialBackend with 1 concurrent workers.\n",
      "[Parallel(n_jobs=1)]: Done   1 out of   1 | elapsed:    0.0s remaining:    0.0s\n",
      "[Parallel(n_jobs=1)]: Done   2 out of   2 | elapsed:    0.0s remaining:    0.0s\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Fitting 3 folds for each of 25 candidates, totalling 75 fits\n",
      "[CV] C=0.1, gamma=1 ..................................................\n",
      "[CV] ...................... C=0.1, gamma=1, score=0.632, total=   0.0s\n",
      "[CV] C=0.1, gamma=1 ..................................................\n",
      "[CV] ...................... C=0.1, gamma=1, score=0.632, total=   0.0s\n",
      "[CV] C=0.1, gamma=1 ..................................................\n",
      "[CV] ...................... C=0.1, gamma=1, score=0.636, total=   0.0s\n",
      "[CV] C=0.1, gamma=0.1 ................................................\n",
      "[CV] .................... C=0.1, gamma=0.1, score=0.632, total=   0.0s\n",
      "[CV] C=0.1, gamma=0.1 ................................................\n",
      "[CV] .................... C=0.1, gamma=0.1, score=0.632, total=   0.0s\n",
      "[CV] C=0.1, gamma=0.1 ................................................\n",
      "[CV] .................... C=0.1, gamma=0.1, score=0.636, total=   0.0s\n",
      "[CV] C=0.1, gamma=0.001 ..............................................\n",
      "[CV] .................. C=0.1, gamma=0.001, score=0.632, total=   0.0s\n",
      "[CV] C=0.1, gamma=0.001 ..............................................\n",
      "[CV] .................. C=0.1, gamma=0.001, score=0.632, total=   0.0s\n",
      "[CV] C=0.1, gamma=0.001 ..............................................\n",
      "[CV] .................. C=0.1, gamma=0.001, score=0.636, total=   0.0s\n",
      "[CV] C=0.1, gamma=0.0001 .............................................\n",
      "[CV] ................. C=0.1, gamma=0.0001, score=0.902, total=   0.0s\n",
      "[CV] C=0.1, gamma=0.0001 .............................................\n",
      "[CV] ................. C=0.1, gamma=0.0001, score=0.962, total=   0.0s\n",
      "[CV] C=0.1, gamma=0.0001 .............................................\n",
      "[CV] ................. C=0.1, gamma=0.0001, score=0.917, total=   0.0s\n",
      "[CV] C=0.1, gamma=0.1 ................................................\n",
      "[CV] .................... C=0.1, gamma=0.1, score=0.632, total=   0.0s\n",
      "[CV] C=0.1, gamma=0.1 ................................................\n",
      "[CV] .................... C=0.1, gamma=0.1, score=0.632, total=   0.0s\n",
      "[CV] C=0.1, gamma=0.1 ................................................\n",
      "[CV] .................... C=0.1, gamma=0.1, score=0.636, total=   0.0s\n",
      "[CV] C=1, gamma=1 ....................................................\n",
      "[CV] ........................ C=1, gamma=1, score=0.632, total=   0.0s\n",
      "[CV] C=1, gamma=1 ....................................................\n",
      "[CV] ........................ C=1, gamma=1, score=0.632, total=   0.0s\n",
      "[CV] C=1, gamma=1 ....................................................\n",
      "[CV] ........................ C=1, gamma=1, score=0.636, total=   0.0s\n",
      "[CV] C=1, gamma=0.1 ..................................................\n",
      "[CV] ...................... C=1, gamma=0.1, score=0.632, total=   0.0s\n",
      "[CV] C=1, gamma=0.1 ..................................................\n",
      "[CV] ...................... C=1, gamma=0.1, score=0.632, total=   0.0s\n",
      "[CV] C=1, gamma=0.1 ..................................................\n",
      "[CV] ...................... C=1, gamma=0.1, score=0.636, total=   0.0s\n",
      "[CV] C=1, gamma=0.001 ................................................\n",
      "[CV] .................... C=1, gamma=0.001, score=0.902, total=   0.0s\n",
      "[CV] C=1, gamma=0.001 ................................................\n",
      "[CV] .................... C=1, gamma=0.001, score=0.940, total=   0.0s\n",
      "[CV] C=1, gamma=0.001 ................................................\n",
      "[CV] .................... C=1, gamma=0.001, score=0.955, total=   0.0s\n",
      "[CV] C=1, gamma=0.0001 ...............................................\n",
      "[CV] ................... C=1, gamma=0.0001, score=0.940, total=   0.0s\n",
      "[CV] C=1, gamma=0.0001 ...............................................\n",
      "[CV] ................... C=1, gamma=0.0001, score=0.970, total=   0.0s\n",
      "[CV] C=1, gamma=0.0001 ...............................................\n",
      "[CV] ................... C=1, gamma=0.0001, score=0.947, total=   0.0s\n",
      "[CV] C=1, gamma=0.1 ..................................................\n",
      "[CV] ...................... C=1, gamma=0.1, score=0.632, total=   0.0s\n",
      "[CV] C=1, gamma=0.1 ..................................................\n",
      "[CV] ...................... C=1, gamma=0.1, score=0.632, total=   0.0s\n",
      "[CV] C=1, gamma=0.1 ..................................................\n",
      "[CV] ...................... C=1, gamma=0.1, score=0.636, total=   0.0s\n",
      "[CV] C=10, gamma=1 ...................................................\n",
      "[CV] ....................... C=10, gamma=1, score=0.632, total=   0.0s\n",
      "[CV] C=10, gamma=1 ...................................................\n",
      "[CV] ....................... C=10, gamma=1, score=0.632, total=   0.0s\n",
      "[CV] C=10, gamma=1 ...................................................\n",
      "[CV] ....................... C=10, gamma=1, score=0.636, total=   0.0s\n",
      "[CV] C=10, gamma=0.1 .................................................\n",
      "[CV] ..................... C=10, gamma=0.1, score=0.632, total=   0.0s\n",
      "[CV] C=10, gamma=0.1 .................................................\n",
      "[CV] ..................... C=10, gamma=0.1, score=0.632, total=   0.0s\n",
      "[CV] C=10, gamma=0.1 .................................................\n",
      "[CV] ..................... C=10, gamma=0.1, score=0.636, total=   0.0s\n",
      "[CV] C=10, gamma=0.001 ...............................................\n",
      "[CV] ................... C=10, gamma=0.001, score=0.895, total=   0.0s\n",
      "[CV] C=10, gamma=0.001 ...............................................\n",
      "[CV] ................... C=10, gamma=0.001, score=0.932, total=   0.0s\n",
      "[CV] C=10, gamma=0.001 ...............................................\n",
      "[CV] ................... C=10, gamma=0.001, score=0.917, total=   0.0s\n",
      "[CV] C=10, gamma=0.0001 ..............................................\n",
      "[CV] .................. C=10, gamma=0.0001, score=0.932, total=   0.0s\n",
      "[CV] C=10, gamma=0.0001 ..............................................\n",
      "[CV] .................. C=10, gamma=0.0001, score=0.970, total=   0.0s\n",
      "[CV] C=10, gamma=0.0001 ..............................................\n",
      "[CV] .................. C=10, gamma=0.0001, score=0.962, total=   0.0s\n",
      "[CV] C=10, gamma=0.1 .................................................\n",
      "[CV] ..................... C=10, gamma=0.1, score=0.632, total=   0.0s\n",
      "[CV] C=10, gamma=0.1 .................................................\n",
      "[CV] ..................... C=10, gamma=0.1, score=0.632, total=   0.0s\n",
      "[CV] C=10, gamma=0.1 .................................................\n",
      "[CV] ..................... C=10, gamma=0.1, score=0.636, total=   0.0s\n",
      "[CV] C=100, gamma=1 ..................................................\n",
      "[CV] ...................... C=100, gamma=1, score=0.632, total=   0.0s\n",
      "[CV] C=100, gamma=1 ..................................................\n",
      "[CV] ...................... C=100, gamma=1, score=0.632, total=   0.0s\n",
      "[CV] C=100, gamma=1 ..................................................\n",
      "[CV] ...................... C=100, gamma=1, score=0.636, total=   0.0s\n",
      "[CV] C=100, gamma=0.1 ................................................\n",
      "[CV] .................... C=100, gamma=0.1, score=0.632, total=   0.0s\n",
      "[CV] C=100, gamma=0.1 ................................................\n",
      "[CV] .................... C=100, gamma=0.1, score=0.632, total=   0.0s\n",
      "[CV] C=100, gamma=0.1 ................................................\n",
      "[CV] .................... C=100, gamma=0.1, score=0.636, total=   0.0s\n",
      "[CV] C=100, gamma=0.001 ..............................................\n",
      "[CV] .................. C=100, gamma=0.001, score=0.895, total=   0.0s\n",
      "[CV] C=100, gamma=0.001 ..............................................\n",
      "[CV] .................. C=100, gamma=0.001, score=0.932, total=   0.0s\n",
      "[CV] C=100, gamma=0.001 ..............................................\n",
      "[CV] .................. C=100, gamma=0.001, score=0.917, total=   0.0s\n",
      "[CV] C=100, gamma=0.0001 .............................................\n",
      "[CV] ................. C=100, gamma=0.0001, score=0.917, total=   0.0s\n",
      "[CV] C=100, gamma=0.0001 .............................................\n",
      "[CV] ................. C=100, gamma=0.0001, score=0.977, total=   0.0s\n",
      "[CV] C=100, gamma=0.0001 .............................................\n",
      "[CV] ................. C=100, gamma=0.0001, score=0.939, total=   0.0s\n",
      "[CV] C=100, gamma=0.1 ................................................\n",
      "[CV] .................... C=100, gamma=0.1, score=0.632, total=   0.0s\n",
      "[CV] C=100, gamma=0.1 ................................................\n",
      "[CV] .................... C=100, gamma=0.1, score=0.632, total=   0.0s\n",
      "[CV] C=100, gamma=0.1 ................................................\n",
      "[CV] .................... C=100, gamma=0.1, score=0.636, total=   0.0s\n",
      "[CV] C=1000, gamma=1 .................................................\n",
      "[CV] ..................... C=1000, gamma=1, score=0.632, total=   0.0s\n",
      "[CV] C=1000, gamma=1 .................................................\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "[CV] ..................... C=1000, gamma=1, score=0.632, total=   0.0s\n",
      "[CV] C=1000, gamma=1 .................................................\n",
      "[CV] ..................... C=1000, gamma=1, score=0.636, total=   0.0s\n",
      "[CV] C=1000, gamma=0.1 ...............................................\n",
      "[CV] ................... C=1000, gamma=0.1, score=0.632, total=   0.0s\n",
      "[CV] C=1000, gamma=0.1 ...............................................\n",
      "[CV] ................... C=1000, gamma=0.1, score=0.632, total=   0.0s\n",
      "[CV] C=1000, gamma=0.1 ...............................................\n",
      "[CV] ................... C=1000, gamma=0.1, score=0.636, total=   0.0s\n",
      "[CV] C=1000, gamma=0.001 .............................................\n",
      "[CV] ................. C=1000, gamma=0.001, score=0.895, total=   0.0s\n",
      "[CV] C=1000, gamma=0.001 .............................................\n",
      "[CV] ................. C=1000, gamma=0.001, score=0.932, total=   0.0s\n",
      "[CV] C=1000, gamma=0.001 .............................................\n",
      "[CV] ................. C=1000, gamma=0.001, score=0.917, total=   0.0s\n",
      "[CV] C=1000, gamma=0.0001 ............................................\n",
      "[CV] ................ C=1000, gamma=0.0001, score=0.910, total=   0.0s\n",
      "[CV] C=1000, gamma=0.0001 ............................................\n",
      "[CV] ................ C=1000, gamma=0.0001, score=0.970, total=   0.0s\n",
      "[CV] C=1000, gamma=0.0001 ............................................\n",
      "[CV] ................ C=1000, gamma=0.0001, score=0.932, total=   0.0s\n",
      "[CV] C=1000, gamma=0.1 ...............................................\n",
      "[CV] ................... C=1000, gamma=0.1, score=0.632, total=   0.0s\n",
      "[CV] C=1000, gamma=0.1 ...............................................\n",
      "[CV] ................... C=1000, gamma=0.1, score=0.632, total=   0.0s\n",
      "[CV] C=1000, gamma=0.1 ...............................................\n",
      "[CV] ................... C=1000, gamma=0.1, score=0.636, total=   0.0s\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "[Parallel(n_jobs=1)]: Done  75 out of  75 | elapsed:    1.3s finished\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "GridSearchCV(cv='warn', error_score='raise-deprecating',\n",
       "             estimator=SVC(C=1.0, cache_size=200, class_weight=None, coef0=0.0,\n",
       "                           decision_function_shape='ovr', degree=3,\n",
       "                           gamma='auto_deprecated', kernel='rbf', max_iter=-1,\n",
       "                           probability=False, random_state=None, shrinking=True,\n",
       "                           tol=0.001, verbose=False),\n",
       "             iid='warn', n_jobs=None,\n",
       "             param_grid={'C': [0.1, 1, 10, 100, 1000],\n",
       "                         'gamma': [1, 0.1, 0.001, 0.0001, 0.1]},\n",
       "             pre_dispatch='2*n_jobs', refit=True, return_train_score=False,\n",
       "             scoring=None, verbose=3)"
      ]
     },
     "execution_count": 28,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "grid.fit(X_train, y_train)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 29,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "{'C': 10, 'gamma': 0.0001}"
      ]
     },
     "execution_count": 29,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "grid.best_params_"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 30,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "SVC(C=10, cache_size=200, class_weight=None, coef0=0.0,\n",
       "    decision_function_shape='ovr', degree=3, gamma=0.0001, kernel='rbf',\n",
       "    max_iter=-1, probability=False, random_state=None, shrinking=True,\n",
       "    tol=0.001, verbose=False)"
      ]
     },
     "execution_count": 30,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "grid.best_estimator_"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 31,
   "metadata": {},
   "outputs": [],
   "source": [
    "grid_pred = grid.predict(X_test)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 32,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "[[ 60   6]\n",
      " [  3 102]]\n",
      "\n",
      "\n",
      "              precision    recall  f1-score   support\n",
      "\n",
      "           0       0.95      0.91      0.93        66\n",
      "           1       0.94      0.97      0.96       105\n",
      "\n",
      "    accuracy                           0.95       171\n",
      "   macro avg       0.95      0.94      0.94       171\n",
      "weighted avg       0.95      0.95      0.95       171\n",
      "\n"
     ]
    }
   ],
   "source": [
    "print(confusion_matrix(y_test, grid_pred))\n",
    "print('\\n')\n",
    "print(classification_report(y_test, grid_pred))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 34,
   "metadata": {},
   "outputs": [],
   "source": [
    "#Now we have the classes divided into 0 and 1 \n",
    "#earlier they were into only class 1"
   ]
  },
  {
   "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": "3.7.3"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}