Cancer Classification.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "id": "dfcd2208",
   "metadata": {},
   "source": [
    "# Importing Libraries"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "id": "0edd298a",
   "metadata": {},
   "outputs": [],
   "source": [
    "import numpy as np\n",
    "import pandas as pd\n",
    "import matplotlib.pyplot as plt\n",
    "import seaborn as sns\n",
    "%matplotlib inline\n",
    "import warnings\n",
    "warnings.filterwarnings('ignore')"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "d57c5fd4",
   "metadata": {},
   "source": [
    "# Loading and Studying dataset"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "id": "a7e7e0c9",
   "metadata": {},
   "outputs": [],
   "source": [
    "data = pd.read_csv('cell_samples.csv')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "id": "9c5d00a8",
   "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>Clump</th>\n",
       "      <th>UnifSize</th>\n",
       "      <th>UnifShape</th>\n",
       "      <th>MargAdh</th>\n",
       "      <th>SingEpiSize</th>\n",
       "      <th>BareNuc</th>\n",
       "      <th>BlandChrom</th>\n",
       "      <th>NormNucl</th>\n",
       "      <th>Mit</th>\n",
       "      <th>Class</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>1000025</td>\n",
       "      <td>5</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>2</td>\n",
       "      <td>1</td>\n",
       "      <td>3</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>1002945</td>\n",
       "      <td>5</td>\n",
       "      <td>4</td>\n",
       "      <td>4</td>\n",
       "      <td>5</td>\n",
       "      <td>7</td>\n",
       "      <td>10</td>\n",
       "      <td>3</td>\n",
       "      <td>2</td>\n",
       "      <td>1</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>1015425</td>\n",
       "      <td>3</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>2</td>\n",
       "      <td>2</td>\n",
       "      <td>3</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>1016277</td>\n",
       "      <td>6</td>\n",
       "      <td>8</td>\n",
       "      <td>8</td>\n",
       "      <td>1</td>\n",
       "      <td>3</td>\n",
       "      <td>4</td>\n",
       "      <td>3</td>\n",
       "      <td>7</td>\n",
       "      <td>1</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>1017023</td>\n",
       "      <td>4</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>3</td>\n",
       "      <td>2</td>\n",
       "      <td>1</td>\n",
       "      <td>3</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "        ID  Clump  UnifSize  UnifShape  MargAdh  SingEpiSize BareNuc  \\\n",
       "0  1000025      5         1          1        1            2       1   \n",
       "1  1002945      5         4          4        5            7      10   \n",
       "2  1015425      3         1          1        1            2       2   \n",
       "3  1016277      6         8          8        1            3       4   \n",
       "4  1017023      4         1          1        3            2       1   \n",
       "\n",
       "   BlandChrom  NormNucl  Mit  Class  \n",
       "0           3         1    1      2  \n",
       "1           3         2    1      2  \n",
       "2           3         1    1      2  \n",
       "3           3         7    1      2  \n",
       "4           3         1    1      2  "
      ]
     },
     "execution_count": 3,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "data.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "id": "55c82714",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(699, 11)"
      ]
     },
     "execution_count": 4,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "data.shape"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "id": "7bc17642",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "2    458\n",
       "4    241\n",
       "Name: Class, dtype: int64"
      ]
     },
     "execution_count": 5,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "data['Class'].value_counts()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "b3f09699",
   "metadata": {},
   "source": [
    "# Feature Transformation"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "id": "56b9a987",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "<class 'pandas.core.frame.DataFrame'>\n",
      "RangeIndex: 699 entries, 0 to 698\n",
      "Data columns (total 11 columns):\n",
      " #   Column       Non-Null Count  Dtype \n",
      "---  ------       --------------  ----- \n",
      " 0   ID           699 non-null    int64 \n",
      " 1   Clump        699 non-null    int64 \n",
      " 2   UnifSize     699 non-null    int64 \n",
      " 3   UnifShape    699 non-null    int64 \n",
      " 4   MargAdh      699 non-null    int64 \n",
      " 5   SingEpiSize  699 non-null    int64 \n",
      " 6   BareNuc      699 non-null    object\n",
      " 7   BlandChrom   699 non-null    int64 \n",
      " 8   NormNucl     699 non-null    int64 \n",
      " 9   Mit          699 non-null    int64 \n",
      " 10  Class        699 non-null    int64 \n",
      "dtypes: int64(10), object(1)\n",
      "memory usage: 60.2+ KB\n"
     ]
    }
   ],
   "source": [
    "data.info()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "id": "1240b66e",
   "metadata": {},
   "outputs": [],
   "source": [
    "data = data[pd.to_numeric(data['BareNuc'], errors='coerce').notnull()]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "id": "b2fa4468",
   "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>Clump</th>\n",
       "      <th>UnifSize</th>\n",
       "      <th>UnifShape</th>\n",
       "      <th>MargAdh</th>\n",
       "      <th>SingEpiSize</th>\n",
       "      <th>BareNuc</th>\n",
       "      <th>BlandChrom</th>\n",
       "      <th>NormNucl</th>\n",
       "      <th>Mit</th>\n",
       "      <th>Class</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>1000025</td>\n",
       "      <td>5</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>2</td>\n",
       "      <td>1</td>\n",
       "      <td>3</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>1002945</td>\n",
       "      <td>5</td>\n",
       "      <td>4</td>\n",
       "      <td>4</td>\n",
       "      <td>5</td>\n",
       "      <td>7</td>\n",
       "      <td>10</td>\n",
       "      <td>3</td>\n",
       "      <td>2</td>\n",
       "      <td>1</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>1015425</td>\n",
       "      <td>3</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>2</td>\n",
       "      <td>2</td>\n",
       "      <td>3</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>1016277</td>\n",
       "      <td>6</td>\n",
       "      <td>8</td>\n",
       "      <td>8</td>\n",
       "      <td>1</td>\n",
       "      <td>3</td>\n",
       "      <td>4</td>\n",
       "      <td>3</td>\n",
       "      <td>7</td>\n",
       "      <td>1</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>1017023</td>\n",
       "      <td>4</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>3</td>\n",
       "      <td>2</td>\n",
       "      <td>1</td>\n",
       "      <td>3</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "        ID  Clump  UnifSize  UnifShape  MargAdh  SingEpiSize BareNuc  \\\n",
       "0  1000025      5         1          1        1            2       1   \n",
       "1  1002945      5         4          4        5            7      10   \n",
       "2  1015425      3         1          1        1            2       2   \n",
       "3  1016277      6         8          8        1            3       4   \n",
       "4  1017023      4         1          1        3            2       1   \n",
       "\n",
       "   BlandChrom  NormNucl  Mit  Class  \n",
       "0           3         1    1      2  \n",
       "1           3         2    1      2  \n",
       "2           3         1    1      2  \n",
       "3           3         7    1      2  \n",
       "4           3         1    1      2  "
      ]
     },
     "execution_count": 8,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "data.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "id": "5ae052f9",
   "metadata": {},
   "outputs": [],
   "source": [
    "data['BareNuc'] = data['BareNuc'].astype('int64')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "id": "f86da823",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "ID             int64\n",
       "Clump          int64\n",
       "UnifSize       int64\n",
       "UnifShape      int64\n",
       "MargAdh        int64\n",
       "SingEpiSize    int64\n",
       "BareNuc        int64\n",
       "BlandChrom     int64\n",
       "NormNucl       int64\n",
       "Mit            int64\n",
       "Class          int64\n",
       "dtype: object"
      ]
     },
     "execution_count": 10,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "data.dtypes"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "8c683e5e",
   "metadata": {},
   "source": [
    "# X and y matrix"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "id": "36ff3339",
   "metadata": {},
   "outputs": [],
   "source": [
    "X = data.drop(['ID','Class'],axis=1)\n",
    "y = data.Class"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "id": "8194c338",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "X Shape: (683, 9)\n",
      "y Shape: (683,)\n"
     ]
    }
   ],
   "source": [
    "print(\"X Shape:\",X.shape)\n",
    "print(\"y Shape:\",y.shape)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "1955dd3b",
   "metadata": {},
   "source": [
    "# Splitting into train and test datasets"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "id": "010997a7",
   "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=0.2,random_state=43)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "ae1467d8",
   "metadata": {},
   "source": [
    "# Support Vector Classification Model"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "3c2cab03",
   "metadata": {},
   "source": [
    "### Instantiating and fitting the model"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "id": "7cde6b79",
   "metadata": {},
   "outputs": [],
   "source": [
    "from sklearn.svm import SVC\n",
    "svc = SVC()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "id": "e40cec21",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<style>#sk-container-id-1 {color: black;background-color: white;}#sk-container-id-1 pre{padding: 0;}#sk-container-id-1 div.sk-toggleable {background-color: white;}#sk-container-id-1 label.sk-toggleable__label {cursor: pointer;display: block;width: 100%;margin-bottom: 0;padding: 0.3em;box-sizing: border-box;text-align: center;}#sk-container-id-1 label.sk-toggleable__label-arrow:before {content: \"▸\";float: left;margin-right: 0.25em;color: #696969;}#sk-container-id-1 label.sk-toggleable__label-arrow:hover:before {color: black;}#sk-container-id-1 div.sk-estimator:hover label.sk-toggleable__label-arrow:before {color: black;}#sk-container-id-1 div.sk-toggleable__content {max-height: 0;max-width: 0;overflow: hidden;text-align: left;background-color: #f0f8ff;}#sk-container-id-1 div.sk-toggleable__content pre {margin: 0.2em;color: black;border-radius: 0.25em;background-color: #f0f8ff;}#sk-container-id-1 input.sk-toggleable__control:checked~div.sk-toggleable__content {max-height: 200px;max-width: 100%;overflow: auto;}#sk-container-id-1 input.sk-toggleable__control:checked~label.sk-toggleable__label-arrow:before {content: \"▾\";}#sk-container-id-1 div.sk-estimator input.sk-toggleable__control:checked~label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-1 div.sk-label input.sk-toggleable__control:checked~label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-1 input.sk-hidden--visually {border: 0;clip: rect(1px 1px 1px 1px);clip: rect(1px, 1px, 1px, 1px);height: 1px;margin: -1px;overflow: hidden;padding: 0;position: absolute;width: 1px;}#sk-container-id-1 div.sk-estimator {font-family: monospace;background-color: #f0f8ff;border: 1px dotted black;border-radius: 0.25em;box-sizing: border-box;margin-bottom: 0.5em;}#sk-container-id-1 div.sk-estimator:hover {background-color: #d4ebff;}#sk-container-id-1 div.sk-parallel-item::after {content: \"\";width: 100%;border-bottom: 1px solid gray;flex-grow: 1;}#sk-container-id-1 div.sk-label:hover label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-1 div.sk-serial::before {content: \"\";position: absolute;border-left: 1px solid gray;box-sizing: border-box;top: 0;bottom: 0;left: 50%;z-index: 0;}#sk-container-id-1 div.sk-serial {display: flex;flex-direction: column;align-items: center;background-color: white;padding-right: 0.2em;padding-left: 0.2em;position: relative;}#sk-container-id-1 div.sk-item {position: relative;z-index: 1;}#sk-container-id-1 div.sk-parallel {display: flex;align-items: stretch;justify-content: center;background-color: white;position: relative;}#sk-container-id-1 div.sk-item::before, #sk-container-id-1 div.sk-parallel-item::before {content: \"\";position: absolute;border-left: 1px solid gray;box-sizing: border-box;top: 0;bottom: 0;left: 50%;z-index: -1;}#sk-container-id-1 div.sk-parallel-item {display: flex;flex-direction: column;z-index: 1;position: relative;background-color: white;}#sk-container-id-1 div.sk-parallel-item:first-child::after {align-self: flex-end;width: 50%;}#sk-container-id-1 div.sk-parallel-item:last-child::after {align-self: flex-start;width: 50%;}#sk-container-id-1 div.sk-parallel-item:only-child::after {width: 0;}#sk-container-id-1 div.sk-dashed-wrapped {border: 1px dashed gray;margin: 0 0.4em 0.5em 0.4em;box-sizing: border-box;padding-bottom: 0.4em;background-color: white;}#sk-container-id-1 div.sk-label label {font-family: monospace;font-weight: bold;display: inline-block;line-height: 1.2em;}#sk-container-id-1 div.sk-label-container {text-align: center;}#sk-container-id-1 div.sk-container {/* jupyter's `normalize.less` sets `[hidden] { display: none; }` but bootstrap.min.css set `[hidden] { display: none !important; }` so we also need the `!important` here to be able to override the default hidden behavior on the sphinx rendered scikit-learn.org. See: https://github.com/scikit-learn/scikit-learn/issues/21755 */display: inline-block !important;position: relative;}#sk-container-id-1 div.sk-text-repr-fallback {display: none;}</style><div id=\"sk-container-id-1\" class=\"sk-top-container\"><div class=\"sk-text-repr-fallback\"><pre>SVC()</pre><b>In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook. <br />On GitHub, the HTML representation is unable to render, please try loading this page with nbviewer.org.</b></div><div class=\"sk-container\" hidden><div class=\"sk-item\"><div class=\"sk-estimator sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-1\" type=\"checkbox\" checked><label for=\"sk-estimator-id-1\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">SVC</label><div class=\"sk-toggleable__content\"><pre>SVC()</pre></div></div></div></div></div>"
      ],
      "text/plain": [
       "SVC()"
      ]
     },
     "execution_count": 16,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "svc.fit(X_train,y_train)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "440b0802",
   "metadata": {},
   "source": [
    "### Evaluating the model"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "id": "f4c5643b",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Accuracy Score:97.08%\n"
     ]
    }
   ],
   "source": [
    "from sklearn.metrics import accuracy_score,f1_score\n",
    "y_pred = svc.predict(X_test)\n",
    "print(\"Accuracy Score:{:.2f}%\".format(accuracy_score(y_test,y_pred)*100))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 19,
   "id": "c6fa954c",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "F1 Score: 0.9708029197080292\n"
     ]
    }
   ],
   "source": [
    "print(\"F1 Score:\",f1_score(y_test,y_pred,average='weighted'))"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "015e3ff7",
   "metadata": {},
   "source": [
    "# Predicting the result"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 23,
   "id": "4a6190ab",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "Clump          3\n",
       "UnifSize       1\n",
       "UnifShape      1\n",
       "MargAdh        1\n",
       "SingEpiSize    2\n",
       "BareNuc        2\n",
       "BlandChrom     3\n",
       "NormNucl       1\n",
       "Mit            1\n",
       "Name: 2, dtype: int64"
      ]
     },
     "execution_count": 23,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "test = data.iloc[2]\n",
    "test = test[1:10]\n",
    "test"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 24,
   "id": "d2adef2e",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([2], dtype=int64)"
      ]
     },
     "execution_count": 24,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "svc.predict([test])"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "test",
   "language": "python",
   "name": "test"
  },
  "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
}