breast_cancer_classification.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [],
   "source": [
    "import numpy as np\n",
    "import pandas as pd\n",
    "import sklearn\n",
    "from sklearn.model_selection import train_test_split\n",
    "from sklearn.linear_model import LinearRegression\n",
    "from sklearn.linear_model import Ridge\n",
    "from sklearn.pipeline import Pipeline\n",
    "from sklearn.feature_selection import SelectKBest\n",
    "from sklearn.decomposition import PCA\n",
    "from sklearn.model_selection import GridSearchCV, RandomizedSearchCV\n",
    "from sklearn.ensemble import AdaBoostClassifier,RandomForestClassifier\n",
    "from sklearn.feature_selection import f_regression, chi2\n",
    "from sklearn.feature_selection import mutual_info_regression\n",
    "from scipy.stats import randint as sp_randint\n",
    "from sklearn import preprocessing\n",
    "from sklearn.metrics import log_loss,accuracy_score,precision_score,recall_score\n",
    "from sklearn.feature_extraction import FeatureHasher\n",
    "from sklearn.svm import SVC"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [],
   "source": [
    "columns_name=['class','age','menopause','tumor-size','inv-nodes','node-caps','deg-malig','breast','breast-quad','irradiat']"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [],
   "source": [
    "data_df=pd.read_csv('breast-cancer.data',names=columns_name,header=None)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(286, 10)"
      ]
     },
     "execution_count": 4,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "data_df.shape"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "278\n"
     ]
    }
   ],
   "source": [
    "data1=data_df['node-caps'] != '?'\n",
    "print(data1.sum())"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [],
   "source": [
    "#data_df=pd.to_numeric(data_df['node-caps'])\n",
    "data_df = data_df[data_df['node-caps'] != '?']\n",
    "data_df = data_df[data_df['breast-quad'] != '?']"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [],
   "source": [
    "data_df.reset_index(drop=True,inplace=True)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(277, 10)"
      ]
     },
     "execution_count": 8,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "data_df.shape"
   ]
  },
  {
   "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>deg-malig</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>count</th>\n",
       "      <td>277.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>mean</th>\n",
       "      <td>2.057762</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>std</th>\n",
       "      <td>0.729989</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>min</th>\n",
       "      <td>1.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>25%</th>\n",
       "      <td>2.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>50%</th>\n",
       "      <td>2.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>75%</th>\n",
       "      <td>3.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>max</th>\n",
       "      <td>3.000000</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "        deg-malig\n",
       "count  277.000000\n",
       "mean     2.057762\n",
       "std      0.729989\n",
       "min      1.000000\n",
       "25%      2.000000\n",
       "50%      2.000000\n",
       "75%      3.000000\n",
       "max      3.000000"
      ]
     },
     "execution_count": 9,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "data_df.describe()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "class          object\n",
       "age            object\n",
       "menopause      object\n",
       "tumor-size     object\n",
       "inv-nodes      object\n",
       "node-caps      object\n",
       "deg-malig       int64\n",
       "breast         object\n",
       "breast-quad    object\n",
       "irradiat       object\n",
       "dtype: object"
      ]
     },
     "execution_count": 10,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "data_df.dtypes"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "/anaconda3/envs/fm1/lib/python3.7/site-packages/ipykernel_launcher.py:2: DeprecationWarning: \n",
      ".ix is deprecated. Please use\n",
      ".loc for label based indexing or\n",
      ".iloc for positional indexing\n",
      "\n",
      "See the documentation here:\n",
      "http://pandas.pydata.org/pandas-docs/stable/indexing.html#ix-indexer-is-deprecated\n",
      "  \n"
     ]
    }
   ],
   "source": [
    "labels=np.array(data_df['class'])\n",
    "X=data_df.ix[:,'age':]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "metadata": {},
   "outputs": [],
   "source": [
    "labels=data_df['class']"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "metadata": {},
   "outputs": [],
   "source": [
    "RSEED=50\n",
    "train, test, train_labels, test_labels = train_test_split(X,\n",
    "                                         labels, \n",
    "                                         stratify = labels,\n",
    "                                         test_size = 0.3, \n",
    "                                         random_state = RSEED)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "metadata": {},
   "outputs": [],
   "source": [
    "X_train_hash = pd.DataFrame.copy(train)\n",
    "X_test_hash = pd.DataFrame.copy(test)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>age</th>\n",
       "      <th>menopause</th>\n",
       "      <th>tumor-size</th>\n",
       "      <th>inv-nodes</th>\n",
       "      <th>node-caps</th>\n",
       "      <th>deg-malig</th>\n",
       "      <th>breast</th>\n",
       "      <th>breast-quad</th>\n",
       "      <th>irradiat</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>221</th>\n",
       "      <td>50-59</td>\n",
       "      <td>premeno</td>\n",
       "      <td>30-34</td>\n",
       "      <td>0-2</td>\n",
       "      <td>no</td>\n",
       "      <td>3</td>\n",
       "      <td>right</td>\n",
       "      <td>left_up</td>\n",
       "      <td>yes</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>153</th>\n",
       "      <td>30-39</td>\n",
       "      <td>lt40</td>\n",
       "      <td>15-19</td>\n",
       "      <td>0-2</td>\n",
       "      <td>no</td>\n",
       "      <td>3</td>\n",
       "      <td>right</td>\n",
       "      <td>left_up</td>\n",
       "      <td>no</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>84</th>\n",
       "      <td>40-49</td>\n",
       "      <td>premeno</td>\n",
       "      <td>20-24</td>\n",
       "      <td>0-2</td>\n",
       "      <td>no</td>\n",
       "      <td>1</td>\n",
       "      <td>left</td>\n",
       "      <td>right_low</td>\n",
       "      <td>no</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>240</th>\n",
       "      <td>50-59</td>\n",
       "      <td>ge40</td>\n",
       "      <td>30-34</td>\n",
       "      <td>9-11</td>\n",
       "      <td>yes</td>\n",
       "      <td>3</td>\n",
       "      <td>left</td>\n",
       "      <td>right_low</td>\n",
       "      <td>yes</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>183</th>\n",
       "      <td>40-49</td>\n",
       "      <td>premeno</td>\n",
       "      <td>10-14</td>\n",
       "      <td>0-2</td>\n",
       "      <td>no</td>\n",
       "      <td>2</td>\n",
       "      <td>right</td>\n",
       "      <td>left_up</td>\n",
       "      <td>no</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "       age menopause tumor-size inv-nodes node-caps  deg-malig breast  \\\n",
       "221  50-59   premeno      30-34       0-2        no          3  right   \n",
       "153  30-39      lt40      15-19       0-2        no          3  right   \n",
       "84   40-49   premeno      20-24       0-2        no          1   left   \n",
       "240  50-59      ge40      30-34      9-11       yes          3   left   \n",
       "183  40-49   premeno      10-14       0-2        no          2  right   \n",
       "\n",
       "    breast-quad irradiat  \n",
       "221     left_up      yes  \n",
       "153     left_up       no  \n",
       "84    right_low       no  \n",
       "240   right_low      yes  \n",
       "183     left_up       no  "
      ]
     },
     "execution_count": 15,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "X_train_hash.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "metadata": {},
   "outputs": [],
   "source": [
    "h = FeatureHasher(n_features=100,input_type=\"string\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "metadata": {},
   "outputs": [],
   "source": [
    "for i in range(X_train_hash.shape[1]):\n",
    "    X_train_hash.iloc[:,i]=X_train_hash.iloc[:,i].astype('str')\n",
    "for i in range(X_test_hash.shape[1]):\n",
    "    X_test_hash.iloc[:,i]=X_test_hash.iloc[:,i].astype('str')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "metadata": {},
   "outputs": [],
   "source": [
    "X_train_hash = h.transform(X_train_hash.values)\n",
    "X_test_hash = h.transform(X_test_hash.values)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 19,
   "metadata": {},
   "outputs": [],
   "source": [
    "#print(X_train_hash.head())"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 20,
   "metadata": {},
   "outputs": [],
   "source": [
    "r = RandomForestClassifier(n_estimators=100000,max_depth=20)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 21,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "RandomForestClassifier(bootstrap=True, class_weight=None, criterion='gini',\n",
       "                       max_depth=20, max_features='auto', max_leaf_nodes=None,\n",
       "                       min_impurity_decrease=0.0, min_impurity_split=None,\n",
       "                       min_samples_leaf=1, min_samples_split=2,\n",
       "                       min_weight_fraction_leaf=0.0, n_estimators=100000,\n",
       "                       n_jobs=None, oob_score=False, random_state=None,\n",
       "                       verbose=0, warm_start=False)"
      ]
     },
     "execution_count": 21,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "r.fit(X_train_hash,train_labels)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": 24,
   "metadata": {},
   "outputs": [],
   "source": [
    "y_pred = r.predict_proba(X_test_hash)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 25,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "0.5034557445251281\n"
     ]
    }
   ],
   "source": [
    "print(log_loss(test_labels,y_pred))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": 26,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "0.75\n",
      "0.7794117647058824\n"
     ]
    }
   ],
   "source": [
    "y_pred1 = r.predict(X_test_hash)\n",
    "print(accuracy_score(test_labels,y_pred1))\n",
    "#print(recall_score(test_labels,y_pred1))\n",
    "print(precision_score(test_labels,y_pred1,pos_label=\"no-recurrence-events\"))\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 27,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "0.75\n",
      "0.7794117647058824\n",
      "0.625\n"
     ]
    }
   ],
   "source": [
    "print(accuracy_score(test_labels,y_pred1))\n",
    "#print(recall_score(test_labels,y_pred1))\n",
    "print(precision_score(test_labels,y_pred1,pos_label=\"no-recurrence-events\"))\n",
    "print(precision_score(test_labels,y_pred1,pos_label=\"recurrence-events\"))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 28,
   "metadata": {},
   "outputs": [],
   "source": [
    "svc=SVC(probability=True, kernel='sigmoid')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 29,
   "metadata": {},
   "outputs": [],
   "source": [
    "adabc =AdaBoostClassifier(n_estimators=1000, base_estimator=svc,learning_rate=1)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 30,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "/anaconda3/envs/fm1/lib/python3.7/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"
     ]
    },
    {
     "data": {
      "text/plain": [
       "AdaBoostClassifier(algorithm='SAMME.R',\n",
       "                   base_estimator=SVC(C=1.0, cache_size=200, class_weight=None,\n",
       "                                      coef0=0.0, decision_function_shape='ovr',\n",
       "                                      degree=3, gamma='auto_deprecated',\n",
       "                                      kernel='sigmoid', max_iter=-1,\n",
       "                                      probability=True, random_state=None,\n",
       "                                      shrinking=True, tol=0.001,\n",
       "                                      verbose=False),\n",
       "                   learning_rate=1, n_estimators=1000, random_state=None)"
      ]
     },
     "execution_count": 30,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "adabc.fit(X_train_hash,train_labels)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 31,
   "metadata": {},
   "outputs": [],
   "source": [
    "y_pred_adab = adabc.predict(X_test_hash)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 32,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "0.7023809523809523\n",
      "0.7023809523809523\n"
     ]
    }
   ],
   "source": [
    "print(accuracy_score(test_labels,y_pred_adab))\n",
    "#print(recall_score(test_labels,y_pred1))\n",
    "print(precision_score(test_labels,y_pred_adab,pos_label=\"no-recurrence-events\"))"
   ]
  },
  {
   "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
}