Breast-Cancer-Classification.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "id": "1e1f51a4",
   "metadata": {},
   "outputs": [],
   "source": [
    "import numpy as np\n",
    "import pandas as pd\n",
    "import matplotlib.pyplot as plt\n",
    "%matplotlib inline\n",
    "import seaborn as sns\n",
    "import plotly.express as px\n",
    "from ydata_profiling import ProfileReport\n",
    "\n",
    "from sklearn.preprocessing import LabelEncoder, StandardScaler\n",
    "from sklearn.model_selection import train_test_split, StratifiedKFold\n",
    "from sklearn.model_selection import cross_val_score\n",
    "from sklearn.metrics import accuracy_score\n",
    "\n",
    "from sklearn.linear_model import LogisticRegression\n",
    "from sklearn.svm import SVC\n",
    "from sklearn.neighbors import KNeighborsClassifier\n",
    "from sklearn.ensemble import RandomForestClassifier\n",
    "from xgboost import XGBClassifier\n",
    "\n",
    "import warnings\n",
    "import os\n",
    "warnings.filterwarnings(\"ignore\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "id": "dedeb6f4",
   "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": 2,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df = pd.read_csv(r\"data.csv\")\n",
    "df.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "id": "0503e1af",
   "metadata": {},
   "outputs": [],
   "source": [
    "df = df.drop(\"Unnamed: 32\", axis = 1)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "id": "b6cd2007",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "B    357\n",
       "M    212\n",
       "Name: diagnosis, dtype: int64"
      ]
     },
     "execution_count": 4,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.diagnosis.value_counts()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "id": "ea9a52cd",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0    357\n",
       "1    212\n",
       "Name: diagnosis, dtype: int64"
      ]
     },
     "execution_count": 5,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df[\"diagnosis\"] = LabelEncoder().fit_transform(df[\"diagnosis\"])\n",
    "df.diagnosis.value_counts()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "id": "7b08d565",
   "metadata": {},
   "outputs": [],
   "source": [
    "import scipy.stats as stats\n",
    "df[df.columns[2:]] = df[df.columns[2:]].apply(stats.zscore)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "id": "8744ab52",
   "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>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>842302</td>\n",
       "      <td>1</td>\n",
       "      <td>1.097064</td>\n",
       "      <td>-2.073335</td>\n",
       "      <td>1.269934</td>\n",
       "      <td>0.984375</td>\n",
       "      <td>1.568466</td>\n",
       "      <td>3.283515</td>\n",
       "      <td>2.652874</td>\n",
       "      <td>2.532475</td>\n",
       "      <td>...</td>\n",
       "      <td>1.886690</td>\n",
       "      <td>-1.359293</td>\n",
       "      <td>2.303601</td>\n",
       "      <td>2.001237</td>\n",
       "      <td>1.307686</td>\n",
       "      <td>2.616665</td>\n",
       "      <td>2.109526</td>\n",
       "      <td>2.296076</td>\n",
       "      <td>2.750622</td>\n",
       "      <td>1.937015</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>842517</td>\n",
       "      <td>1</td>\n",
       "      <td>1.829821</td>\n",
       "      <td>-0.353632</td>\n",
       "      <td>1.685955</td>\n",
       "      <td>1.908708</td>\n",
       "      <td>-0.826962</td>\n",
       "      <td>-0.487072</td>\n",
       "      <td>-0.023846</td>\n",
       "      <td>0.548144</td>\n",
       "      <td>...</td>\n",
       "      <td>1.805927</td>\n",
       "      <td>-0.369203</td>\n",
       "      <td>1.535126</td>\n",
       "      <td>1.890489</td>\n",
       "      <td>-0.375612</td>\n",
       "      <td>-0.430444</td>\n",
       "      <td>-0.146749</td>\n",
       "      <td>1.087084</td>\n",
       "      <td>-0.243890</td>\n",
       "      <td>0.281190</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>84300903</td>\n",
       "      <td>1</td>\n",
       "      <td>1.579888</td>\n",
       "      <td>0.456187</td>\n",
       "      <td>1.566503</td>\n",
       "      <td>1.558884</td>\n",
       "      <td>0.942210</td>\n",
       "      <td>1.052926</td>\n",
       "      <td>1.363478</td>\n",
       "      <td>2.037231</td>\n",
       "      <td>...</td>\n",
       "      <td>1.511870</td>\n",
       "      <td>-0.023974</td>\n",
       "      <td>1.347475</td>\n",
       "      <td>1.456285</td>\n",
       "      <td>0.527407</td>\n",
       "      <td>1.082932</td>\n",
       "      <td>0.854974</td>\n",
       "      <td>1.955000</td>\n",
       "      <td>1.152255</td>\n",
       "      <td>0.201391</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>84348301</td>\n",
       "      <td>1</td>\n",
       "      <td>-0.768909</td>\n",
       "      <td>0.253732</td>\n",
       "      <td>-0.592687</td>\n",
       "      <td>-0.764464</td>\n",
       "      <td>3.283553</td>\n",
       "      <td>3.402909</td>\n",
       "      <td>1.915897</td>\n",
       "      <td>1.451707</td>\n",
       "      <td>...</td>\n",
       "      <td>-0.281464</td>\n",
       "      <td>0.133984</td>\n",
       "      <td>-0.249939</td>\n",
       "      <td>-0.550021</td>\n",
       "      <td>3.394275</td>\n",
       "      <td>3.893397</td>\n",
       "      <td>1.989588</td>\n",
       "      <td>2.175786</td>\n",
       "      <td>6.046041</td>\n",
       "      <td>4.935010</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>84358402</td>\n",
       "      <td>1</td>\n",
       "      <td>1.750297</td>\n",
       "      <td>-1.151816</td>\n",
       "      <td>1.776573</td>\n",
       "      <td>1.826229</td>\n",
       "      <td>0.280372</td>\n",
       "      <td>0.539340</td>\n",
       "      <td>1.371011</td>\n",
       "      <td>1.428493</td>\n",
       "      <td>...</td>\n",
       "      <td>1.298575</td>\n",
       "      <td>-1.466770</td>\n",
       "      <td>1.338539</td>\n",
       "      <td>1.220724</td>\n",
       "      <td>0.220556</td>\n",
       "      <td>-0.313395</td>\n",
       "      <td>0.613179</td>\n",
       "      <td>0.729259</td>\n",
       "      <td>-0.868353</td>\n",
       "      <td>-0.397100</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>5 rows × 32 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "         id  diagnosis  radius_mean  texture_mean  perimeter_mean  area_mean  \\\n",
       "0    842302          1     1.097064     -2.073335        1.269934   0.984375   \n",
       "1    842517          1     1.829821     -0.353632        1.685955   1.908708   \n",
       "2  84300903          1     1.579888      0.456187        1.566503   1.558884   \n",
       "3  84348301          1    -0.768909      0.253732       -0.592687  -0.764464   \n",
       "4  84358402          1     1.750297     -1.151816        1.776573   1.826229   \n",
       "\n",
       "   smoothness_mean  compactness_mean  concavity_mean  concave points_mean  \\\n",
       "0         1.568466          3.283515        2.652874             2.532475   \n",
       "1        -0.826962         -0.487072       -0.023846             0.548144   \n",
       "2         0.942210          1.052926        1.363478             2.037231   \n",
       "3         3.283553          3.402909        1.915897             1.451707   \n",
       "4         0.280372          0.539340        1.371011             1.428493   \n",
       "\n",
       "   ...  radius_worst  texture_worst  perimeter_worst  area_worst  \\\n",
       "0  ...      1.886690      -1.359293         2.303601    2.001237   \n",
       "1  ...      1.805927      -0.369203         1.535126    1.890489   \n",
       "2  ...      1.511870      -0.023974         1.347475    1.456285   \n",
       "3  ...     -0.281464       0.133984        -0.249939   -0.550021   \n",
       "4  ...      1.298575      -1.466770         1.338539    1.220724   \n",
       "\n",
       "   smoothness_worst  compactness_worst  concavity_worst  concave points_worst  \\\n",
       "0          1.307686           2.616665         2.109526              2.296076   \n",
       "1         -0.375612          -0.430444        -0.146749              1.087084   \n",
       "2          0.527407           1.082932         0.854974              1.955000   \n",
       "3          3.394275           3.893397         1.989588              2.175786   \n",
       "4          0.220556          -0.313395         0.613179              0.729259   \n",
       "\n",
       "   symmetry_worst  fractal_dimension_worst  \n",
       "0        2.750622                 1.937015  \n",
       "1       -0.243890                 0.281190  \n",
       "2        1.152255                 0.201391  \n",
       "3        6.046041                 4.935010  \n",
       "4       -0.868353                -0.397100  \n",
       "\n",
       "[5 rows x 32 columns]"
      ]
     },
     "execution_count": 7,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "id": "ab929ea2",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "smoothness_se             -0.067016\n",
       "fractal_dimension_mean    -0.012838\n",
       "texture_se                -0.008303\n",
       "symmetry_se               -0.006522\n",
       "id                         0.039769\n",
       "fractal_dimension_se       0.077972\n",
       "concavity_se               0.253730\n",
       "compactness_se             0.292999\n",
       "fractal_dimension_worst    0.323872\n",
       "symmetry_mean              0.330499\n",
       "smoothness_mean            0.358560\n",
       "concave points_se          0.408042\n",
       "texture_mean               0.415185\n",
       "symmetry_worst             0.416294\n",
       "smoothness_worst           0.421465\n",
       "texture_worst              0.456903\n",
       "area_se                    0.548236\n",
       "perimeter_se               0.556141\n",
       "radius_se                  0.567134\n",
       "compactness_worst          0.590998\n",
       "compactness_mean           0.596534\n",
       "concavity_worst            0.659610\n",
       "concavity_mean             0.696360\n",
       "area_mean                  0.708984\n",
       "radius_mean                0.730029\n",
       "area_worst                 0.733825\n",
       "perimeter_mean             0.742636\n",
       "radius_worst               0.776454\n",
       "concave points_mean        0.776614\n",
       "perimeter_worst            0.782914\n",
       "concave points_worst       0.793566\n",
       "diagnosis                  1.000000\n",
       "dtype: float64"
      ]
     },
     "execution_count": 8,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "corrValues = df.corrwith(df[\"diagnosis\"])\n",
    "corrValues.sort_values()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "id": "5bb98695",
   "metadata": {},
   "outputs": [],
   "source": [
    "features = [\"area_se\",\n",
    "            \"perimeter_se\",\n",
    "            \"radius_se\",\n",
    "            \"compactness_worst\",\n",
    "            \"compactness_mean\",\n",
    "            \"concavity_worst\",\n",
    "            \"concavity_mean\",\n",
    "            \"area_mean\",\n",
    "            \"radius_mean\",\n",
    "            \"area_worst\",\n",
    "            \"perimeter_mean\",\n",
    "            \"radius_worst\",\n",
    "            \"concave points_mean\",\n",
    "            \"perimeter_worst\",\n",
    "            \"concave points_worst\",\n",
    "            \"diagnosis\"\n",
    "           ]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "id": "0efeb826",
   "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>area_se</th>\n",
       "      <th>perimeter_se</th>\n",
       "      <th>radius_se</th>\n",
       "      <th>compactness_worst</th>\n",
       "      <th>compactness_mean</th>\n",
       "      <th>concavity_worst</th>\n",
       "      <th>concavity_mean</th>\n",
       "      <th>area_mean</th>\n",
       "      <th>radius_mean</th>\n",
       "      <th>area_worst</th>\n",
       "      <th>perimeter_mean</th>\n",
       "      <th>radius_worst</th>\n",
       "      <th>concave points_mean</th>\n",
       "      <th>perimeter_worst</th>\n",
       "      <th>concave points_worst</th>\n",
       "      <th>diagnosis</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>2.487578</td>\n",
       "      <td>2.833031</td>\n",
       "      <td>2.489734</td>\n",
       "      <td>2.616665</td>\n",
       "      <td>3.283515</td>\n",
       "      <td>2.109526</td>\n",
       "      <td>2.652874</td>\n",
       "      <td>0.984375</td>\n",
       "      <td>1.097064</td>\n",
       "      <td>2.001237</td>\n",
       "      <td>1.269934</td>\n",
       "      <td>1.886690</td>\n",
       "      <td>2.532475</td>\n",
       "      <td>2.303601</td>\n",
       "      <td>2.296076</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>0.742402</td>\n",
       "      <td>0.263327</td>\n",
       "      <td>0.499255</td>\n",
       "      <td>-0.430444</td>\n",
       "      <td>-0.487072</td>\n",
       "      <td>-0.146749</td>\n",
       "      <td>-0.023846</td>\n",
       "      <td>1.908708</td>\n",
       "      <td>1.829821</td>\n",
       "      <td>1.890489</td>\n",
       "      <td>1.685955</td>\n",
       "      <td>1.805927</td>\n",
       "      <td>0.548144</td>\n",
       "      <td>1.535126</td>\n",
       "      <td>1.087084</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>1.181336</td>\n",
       "      <td>0.850928</td>\n",
       "      <td>1.228676</td>\n",
       "      <td>1.082932</td>\n",
       "      <td>1.052926</td>\n",
       "      <td>0.854974</td>\n",
       "      <td>1.363478</td>\n",
       "      <td>1.558884</td>\n",
       "      <td>1.579888</td>\n",
       "      <td>1.456285</td>\n",
       "      <td>1.566503</td>\n",
       "      <td>1.511870</td>\n",
       "      <td>2.037231</td>\n",
       "      <td>1.347475</td>\n",
       "      <td>1.955000</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>-0.288378</td>\n",
       "      <td>0.286593</td>\n",
       "      <td>0.326373</td>\n",
       "      <td>3.893397</td>\n",
       "      <td>3.402909</td>\n",
       "      <td>1.989588</td>\n",
       "      <td>1.915897</td>\n",
       "      <td>-0.764464</td>\n",
       "      <td>-0.768909</td>\n",
       "      <td>-0.550021</td>\n",
       "      <td>-0.592687</td>\n",
       "      <td>-0.281464</td>\n",
       "      <td>1.451707</td>\n",
       "      <td>-0.249939</td>\n",
       "      <td>2.175786</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>1.190357</td>\n",
       "      <td>1.273189</td>\n",
       "      <td>1.270543</td>\n",
       "      <td>-0.313395</td>\n",
       "      <td>0.539340</td>\n",
       "      <td>0.613179</td>\n",
       "      <td>1.371011</td>\n",
       "      <td>1.826229</td>\n",
       "      <td>1.750297</td>\n",
       "      <td>1.220724</td>\n",
       "      <td>1.776573</td>\n",
       "      <td>1.298575</td>\n",
       "      <td>1.428493</td>\n",
       "      <td>1.338539</td>\n",
       "      <td>0.729259</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>564</th>\n",
       "      <td>2.604187</td>\n",
       "      <td>2.379583</td>\n",
       "      <td>2.782080</td>\n",
       "      <td>-0.273318</td>\n",
       "      <td>0.219060</td>\n",
       "      <td>0.664512</td>\n",
       "      <td>1.947285</td>\n",
       "      <td>2.343856</td>\n",
       "      <td>2.110995</td>\n",
       "      <td>2.015301</td>\n",
       "      <td>2.060786</td>\n",
       "      <td>1.901185</td>\n",
       "      <td>2.320965</td>\n",
       "      <td>1.752563</td>\n",
       "      <td>1.629151</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>565</th>\n",
       "      <td>1.291565</td>\n",
       "      <td>1.156857</td>\n",
       "      <td>1.300499</td>\n",
       "      <td>-0.394820</td>\n",
       "      <td>-0.017833</td>\n",
       "      <td>0.236573</td>\n",
       "      <td>0.693043</td>\n",
       "      <td>1.723842</td>\n",
       "      <td>1.704854</td>\n",
       "      <td>1.494959</td>\n",
       "      <td>1.615931</td>\n",
       "      <td>1.536720</td>\n",
       "      <td>1.263669</td>\n",
       "      <td>1.421940</td>\n",
       "      <td>0.733827</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>566</th>\n",
       "      <td>0.180698</td>\n",
       "      <td>0.276693</td>\n",
       "      <td>0.184892</td>\n",
       "      <td>0.350735</td>\n",
       "      <td>-0.038680</td>\n",
       "      <td>0.326767</td>\n",
       "      <td>0.046588</td>\n",
       "      <td>0.577953</td>\n",
       "      <td>0.702284</td>\n",
       "      <td>0.427906</td>\n",
       "      <td>0.672676</td>\n",
       "      <td>0.561361</td>\n",
       "      <td>0.105777</td>\n",
       "      <td>0.579001</td>\n",
       "      <td>0.414069</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>567</th>\n",
       "      <td>1.009503</td>\n",
       "      <td>1.438530</td>\n",
       "      <td>1.157935</td>\n",
       "      <td>3.904848</td>\n",
       "      <td>3.272144</td>\n",
       "      <td>3.197605</td>\n",
       "      <td>3.296944</td>\n",
       "      <td>1.735218</td>\n",
       "      <td>1.838341</td>\n",
       "      <td>1.653171</td>\n",
       "      <td>1.982524</td>\n",
       "      <td>1.961239</td>\n",
       "      <td>2.658866</td>\n",
       "      <td>2.303601</td>\n",
       "      <td>2.289985</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>568</th>\n",
       "      <td>-0.466152</td>\n",
       "      <td>-0.157449</td>\n",
       "      <td>-0.070279</td>\n",
       "      <td>-1.207552</td>\n",
       "      <td>-1.150752</td>\n",
       "      <td>-1.305831</td>\n",
       "      <td>-1.114873</td>\n",
       "      <td>-1.347789</td>\n",
       "      <td>-1.808401</td>\n",
       "      <td>-1.075813</td>\n",
       "      <td>-1.814389</td>\n",
       "      <td>-1.410893</td>\n",
       "      <td>-1.261820</td>\n",
       "      <td>-1.432735</td>\n",
       "      <td>-1.745063</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>569 rows × 16 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "      area_se  perimeter_se  radius_se  compactness_worst  compactness_mean  \\\n",
       "0    2.487578      2.833031   2.489734           2.616665          3.283515   \n",
       "1    0.742402      0.263327   0.499255          -0.430444         -0.487072   \n",
       "2    1.181336      0.850928   1.228676           1.082932          1.052926   \n",
       "3   -0.288378      0.286593   0.326373           3.893397          3.402909   \n",
       "4    1.190357      1.273189   1.270543          -0.313395          0.539340   \n",
       "..        ...           ...        ...                ...               ...   \n",
       "564  2.604187      2.379583   2.782080          -0.273318          0.219060   \n",
       "565  1.291565      1.156857   1.300499          -0.394820         -0.017833   \n",
       "566  0.180698      0.276693   0.184892           0.350735         -0.038680   \n",
       "567  1.009503      1.438530   1.157935           3.904848          3.272144   \n",
       "568 -0.466152     -0.157449  -0.070279          -1.207552         -1.150752   \n",
       "\n",
       "     concavity_worst  concavity_mean  area_mean  radius_mean  area_worst  \\\n",
       "0           2.109526        2.652874   0.984375     1.097064    2.001237   \n",
       "1          -0.146749       -0.023846   1.908708     1.829821    1.890489   \n",
       "2           0.854974        1.363478   1.558884     1.579888    1.456285   \n",
       "3           1.989588        1.915897  -0.764464    -0.768909   -0.550021   \n",
       "4           0.613179        1.371011   1.826229     1.750297    1.220724   \n",
       "..               ...             ...        ...          ...         ...   \n",
       "564         0.664512        1.947285   2.343856     2.110995    2.015301   \n",
       "565         0.236573        0.693043   1.723842     1.704854    1.494959   \n",
       "566         0.326767        0.046588   0.577953     0.702284    0.427906   \n",
       "567         3.197605        3.296944   1.735218     1.838341    1.653171   \n",
       "568        -1.305831       -1.114873  -1.347789    -1.808401   -1.075813   \n",
       "\n",
       "     perimeter_mean  radius_worst  concave points_mean  perimeter_worst  \\\n",
       "0          1.269934      1.886690             2.532475         2.303601   \n",
       "1          1.685955      1.805927             0.548144         1.535126   \n",
       "2          1.566503      1.511870             2.037231         1.347475   \n",
       "3         -0.592687     -0.281464             1.451707        -0.249939   \n",
       "4          1.776573      1.298575             1.428493         1.338539   \n",
       "..              ...           ...                  ...              ...   \n",
       "564        2.060786      1.901185             2.320965         1.752563   \n",
       "565        1.615931      1.536720             1.263669         1.421940   \n",
       "566        0.672676      0.561361             0.105777         0.579001   \n",
       "567        1.982524      1.961239             2.658866         2.303601   \n",
       "568       -1.814389     -1.410893            -1.261820        -1.432735   \n",
       "\n",
       "     concave points_worst  diagnosis  \n",
       "0                2.296076          1  \n",
       "1                1.087084          1  \n",
       "2                1.955000          1  \n",
       "3                2.175786          1  \n",
       "4                0.729259          1  \n",
       "..                    ...        ...  \n",
       "564              1.629151          1  \n",
       "565              0.733827          1  \n",
       "566              0.414069          1  \n",
       "567              2.289985          1  \n",
       "568             -1.745063          0  \n",
       "\n",
       "[569 rows x 16 columns]"
      ]
     },
     "execution_count": 10,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "new_df = df[features]\n",
    "new_df"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "id": "8725dce1",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0    357\n",
       "1    212\n",
       "Name: diagnosis, dtype: int64"
      ]
     },
     "execution_count": 11,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "new_df.diagnosis.value_counts()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "id": "c9bf9309",
   "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>area_se</th>\n",
       "      <th>perimeter_se</th>\n",
       "      <th>radius_se</th>\n",
       "      <th>compactness_worst</th>\n",
       "      <th>compactness_mean</th>\n",
       "      <th>concavity_worst</th>\n",
       "      <th>concavity_mean</th>\n",
       "      <th>area_mean</th>\n",
       "      <th>radius_mean</th>\n",
       "      <th>area_worst</th>\n",
       "      <th>perimeter_mean</th>\n",
       "      <th>radius_worst</th>\n",
       "      <th>concave points_mean</th>\n",
       "      <th>perimeter_worst</th>\n",
       "      <th>concave points_worst</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>2.487578</td>\n",
       "      <td>2.833031</td>\n",
       "      <td>2.489734</td>\n",
       "      <td>2.616665</td>\n",
       "      <td>3.283515</td>\n",
       "      <td>2.109526</td>\n",
       "      <td>2.652874</td>\n",
       "      <td>0.984375</td>\n",
       "      <td>1.097064</td>\n",
       "      <td>2.001237</td>\n",
       "      <td>1.269934</td>\n",
       "      <td>1.886690</td>\n",
       "      <td>2.532475</td>\n",
       "      <td>2.303601</td>\n",
       "      <td>2.296076</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>0.742402</td>\n",
       "      <td>0.263327</td>\n",
       "      <td>0.499255</td>\n",
       "      <td>-0.430444</td>\n",
       "      <td>-0.487072</td>\n",
       "      <td>-0.146749</td>\n",
       "      <td>-0.023846</td>\n",
       "      <td>1.908708</td>\n",
       "      <td>1.829821</td>\n",
       "      <td>1.890489</td>\n",
       "      <td>1.685955</td>\n",
       "      <td>1.805927</td>\n",
       "      <td>0.548144</td>\n",
       "      <td>1.535126</td>\n",
       "      <td>1.087084</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>1.181336</td>\n",
       "      <td>0.850928</td>\n",
       "      <td>1.228676</td>\n",
       "      <td>1.082932</td>\n",
       "      <td>1.052926</td>\n",
       "      <td>0.854974</td>\n",
       "      <td>1.363478</td>\n",
       "      <td>1.558884</td>\n",
       "      <td>1.579888</td>\n",
       "      <td>1.456285</td>\n",
       "      <td>1.566503</td>\n",
       "      <td>1.511870</td>\n",
       "      <td>2.037231</td>\n",
       "      <td>1.347475</td>\n",
       "      <td>1.955000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>-0.288378</td>\n",
       "      <td>0.286593</td>\n",
       "      <td>0.326373</td>\n",
       "      <td>3.893397</td>\n",
       "      <td>3.402909</td>\n",
       "      <td>1.989588</td>\n",
       "      <td>1.915897</td>\n",
       "      <td>-0.764464</td>\n",
       "      <td>-0.768909</td>\n",
       "      <td>-0.550021</td>\n",
       "      <td>-0.592687</td>\n",
       "      <td>-0.281464</td>\n",
       "      <td>1.451707</td>\n",
       "      <td>-0.249939</td>\n",
       "      <td>2.175786</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>1.190357</td>\n",
       "      <td>1.273189</td>\n",
       "      <td>1.270543</td>\n",
       "      <td>-0.313395</td>\n",
       "      <td>0.539340</td>\n",
       "      <td>0.613179</td>\n",
       "      <td>1.371011</td>\n",
       "      <td>1.826229</td>\n",
       "      <td>1.750297</td>\n",
       "      <td>1.220724</td>\n",
       "      <td>1.776573</td>\n",
       "      <td>1.298575</td>\n",
       "      <td>1.428493</td>\n",
       "      <td>1.338539</td>\n",
       "      <td>0.729259</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "    area_se  perimeter_se  radius_se  compactness_worst  compactness_mean  \\\n",
       "0  2.487578      2.833031   2.489734           2.616665          3.283515   \n",
       "1  0.742402      0.263327   0.499255          -0.430444         -0.487072   \n",
       "2  1.181336      0.850928   1.228676           1.082932          1.052926   \n",
       "3 -0.288378      0.286593   0.326373           3.893397          3.402909   \n",
       "4  1.190357      1.273189   1.270543          -0.313395          0.539340   \n",
       "\n",
       "   concavity_worst  concavity_mean  area_mean  radius_mean  area_worst  \\\n",
       "0         2.109526        2.652874   0.984375     1.097064    2.001237   \n",
       "1        -0.146749       -0.023846   1.908708     1.829821    1.890489   \n",
       "2         0.854974        1.363478   1.558884     1.579888    1.456285   \n",
       "3         1.989588        1.915897  -0.764464    -0.768909   -0.550021   \n",
       "4         0.613179        1.371011   1.826229     1.750297    1.220724   \n",
       "\n",
       "   perimeter_mean  radius_worst  concave points_mean  perimeter_worst  \\\n",
       "0        1.269934      1.886690             2.532475         2.303601   \n",
       "1        1.685955      1.805927             0.548144         1.535126   \n",
       "2        1.566503      1.511870             2.037231         1.347475   \n",
       "3       -0.592687     -0.281464             1.451707        -0.249939   \n",
       "4        1.776573      1.298575             1.428493         1.338539   \n",
       "\n",
       "   concave points_worst  \n",
       "0              2.296076  \n",
       "1              1.087084  \n",
       "2              1.955000  \n",
       "3              2.175786  \n",
       "4              0.729259  "
      ]
     },
     "execution_count": 12,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "X = new_df.drop([\"diagnosis\"], axis=1)\n",
    "Y = new_df[\"diagnosis\"]\n",
    "X.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "id": "1174abde",
   "metadata": {},
   "outputs": [],
   "source": [
    "# \"XG Boost\": XGBClassifier(),\n",
    "classifiers = {\n",
    "    \"Random Forest\": RandomForestClassifier(),\n",
    "    \"LogisiticRegression\": LogisticRegression(),\n",
    "    \"KNearest\": KNeighborsClassifier(),\n",
    "    \"Support Vector Classifier\": SVC()\n",
    "}"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "id": "12d1255b",
   "metadata": {},
   "outputs": [],
   "source": [
    "skf = StratifiedKFold(n_splits=10, random_state=None, shuffle = False)\n",
    "\n",
    "for train_index, test_index in skf.split(X, Y):\n",
    "    Xtrain, Xtest = X.iloc[train_index], X.iloc[test_index]\n",
    "    Ytrain, Ytest = Y.iloc[train_index], Y.iloc[test_index]\n",
    "\n",
    "Xtrain = Xtrain.values\n",
    "Xtest = Xtest.values\n",
    "Ytrain = Ytrain.values\n",
    "Ytest = Ytest.values"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "id": "766ffe00",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Classifiers:  RandomForestClassifier has a accuracy score of 0.9821428571428571\n",
      "Classifiers:  LogisticRegression has a accuracy score of 0.9642857142857143\n",
      "Classifiers:  KNeighborsClassifier has a accuracy score of 0.9642857142857143\n",
      "Classifiers:  SVC has a accuracy score of 0.9464285714285714\n"
     ]
    }
   ],
   "source": [
    "for key, classifier in classifiers.items():\n",
    "    classifier.fit(Xtrain, Ytrain)\n",
    "    Ypred = classifier.predict(Xtest)\n",
    "    acc_score = accuracy_score(Ypred, Ytest)\n",
    "    print(\"Classifiers: \", classifier.__class__.__name__, \"has a accuracy score of\", acc_score)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "255cc1cd",
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "7d520250",
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "de5a6c2e",
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3 (ipykernel)",
   "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": "3.9.13"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}