09장_앙상블_5절_스태킹.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# 개별코드"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [],
   "source": [
    "# 데이터 불러오기\n",
    "from sklearn import datasets\n",
    "raw_breast_cancer = datasets.load_breast_cancer()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [],
   "source": [
    "# 피쳐, 타겟 데이터 지정\n",
    "X = raw_breast_cancer.data\n",
    "y = raw_breast_cancer.target"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [],
   "source": [
    "# 트레이닝/테스트 데이터 분할\n",
    "from sklearn.model_selection import train_test_split\n",
    "X_tn, X_te, y_tn, y_te=train_test_split(X,y,random_state=0)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [],
   "source": [
    "# 데이터 표준화\n",
    "from sklearn.preprocessing import StandardScaler\n",
    "std_scale = StandardScaler()\n",
    "std_scale.fit(X_tn)\n",
    "X_tn_std = std_scale.transform(X_tn)\n",
    "X_te_std  = std_scale.transform(X_te)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "StackingClassifier(cv=None,\n",
       "                   estimators=[('svm',\n",
       "                                SVC(C=1.0, break_ties=False, cache_size=200,\n",
       "                                    class_weight=None, coef0=0.0,\n",
       "                                    decision_function_shape='ovr', degree=3,\n",
       "                                    gamma='scale', kernel='linear', max_iter=-1,\n",
       "                                    probability=False, random_state=1,\n",
       "                                    shrinking=True, tol=0.001, verbose=False)),\n",
       "                               ('gnb',\n",
       "                                GaussianNB(priors=None, var_smoothing=1e-09))],\n",
       "                   final_estimator=LogisticRegression(C=1.0, class_weight=None,\n",
       "                                                      dual=False,\n",
       "                                                      fit_intercept=True,\n",
       "                                                      intercept_scaling=1,\n",
       "                                                      l1_ratio=None,\n",
       "                                                      max_iter=100,\n",
       "                                                      multi_class='auto',\n",
       "                                                      n_jobs=None, penalty='l2',\n",
       "                                                      random_state=None,\n",
       "                                                      solver='lbfgs',\n",
       "                                                      tol=0.0001, verbose=0,\n",
       "                                                      warm_start=False),\n",
       "                   n_jobs=None, passthrough=False, stack_method='auto',\n",
       "                   verbose=0)"
      ]
     },
     "execution_count": 5,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# 스태킹 학습\n",
    "from sklearn import svm\n",
    "from sklearn.naive_bayes import GaussianNB\n",
    "from sklearn.linear_model import LogisticRegression\n",
    "from sklearn.ensemble import StackingClassifier\n",
    "\n",
    "clf1 = svm.SVC(kernel='linear', random_state=1) \n",
    "clf2 = GaussianNB()\n",
    "\n",
    "clf_stkg = StackingClassifier(\n",
    "            estimators=[\n",
    "                ('svm', clf1), \n",
    "                ('gnb', clf2)\n",
    "            ],\n",
    "            final_estimator=LogisticRegression())\n",
    "clf_stkg.fit(X_tn_std, y_tn)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "[0 1 1 1 1 1 1 1 1 1 1 1 1 1 1 0 1 0 0 0 0 0 1 1 0 1 1 0 1 0 1 0 1 0 1 0 1\n",
      " 0 1 0 0 1 0 1 1 0 1 1 1 0 0 0 0 1 1 1 1 1 1 0 0 0 1 1 0 1 0 0 0 1 1 0 1 0\n",
      " 0 1 1 1 1 1 0 0 0 1 0 1 1 1 0 0 1 0 0 0 1 1 0 1 1 1 1 1 1 1 0 1 0 1 1 0 1\n",
      " 0 0 1 1 1 1 1 1 1 1 1 1 1 0 1 0 1 1 1 0 1 1 1 1 1 1 1 0 1 1 1 0]\n"
     ]
    }
   ],
   "source": [
    "# 예측\n",
    "pred_stkg = clf_stkg.predict(X_te_std)\n",
    "print(pred_stkg)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "0.965034965034965\n"
     ]
    }
   ],
   "source": [
    "# 정확도\n",
    "from sklearn.metrics import accuracy_score\n",
    "accuracy = accuracy_score(y_te, pred_stkg)\n",
    "print(accuracy)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "[[50  3]\n",
      " [ 2 88]]\n"
     ]
    }
   ],
   "source": [
    "# confusion matrix 확인 \n",
    "from sklearn.metrics import confusion_matrix\n",
    "conf_matrix = confusion_matrix(y_te, pred_stkg)\n",
    "print(conf_matrix)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "              precision    recall  f1-score   support\n",
      "\n",
      "           0       0.96      0.94      0.95        53\n",
      "           1       0.97      0.98      0.97        90\n",
      "\n",
      "    accuracy                           0.97       143\n",
      "   macro avg       0.96      0.96      0.96       143\n",
      "weighted avg       0.96      0.97      0.96       143\n",
      "\n"
     ]
    }
   ],
   "source": [
    "# 분류 레포트 확인\n",
    "from sklearn.metrics import classification_report\n",
    "class_report = classification_report(y_te, pred_stkg)\n",
    "print(class_report)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# 통합코드"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "[0 1 1 1 1 1 1 1 1 1 1 1 1 1 1 0 1 0 0 0 0 0 1 1 0 1 1 0 1 0 1 0 1 0 1 0 1\n",
      " 0 1 0 0 1 0 1 1 0 1 1 1 0 0 0 0 1 1 1 1 1 1 0 0 0 1 1 0 1 0 0 0 1 1 0 1 0\n",
      " 0 1 1 1 1 1 0 0 0 1 0 1 1 1 0 0 1 0 0 0 1 1 0 1 1 1 1 1 1 1 0 1 0 1 1 0 1\n",
      " 0 0 1 1 1 1 1 1 1 1 1 1 1 0 1 0 1 1 1 0 1 1 1 1 1 1 1 0 1 1 1 0]\n",
      "0.965034965034965\n",
      "[[50  3]\n",
      " [ 2 88]]\n",
      "              precision    recall  f1-score   support\n",
      "\n",
      "           0       0.96      0.94      0.95        53\n",
      "           1       0.97      0.98      0.97        90\n",
      "\n",
      "    accuracy                           0.97       143\n",
      "   macro avg       0.96      0.96      0.96       143\n",
      "weighted avg       0.96      0.97      0.96       143\n",
      "\n"
     ]
    }
   ],
   "source": [
    "from sklearn import datasets\n",
    "from sklearn.model_selection import train_test_split\n",
    "from sklearn.preprocessing import StandardScaler\n",
    "\n",
    "from sklearn import svm\n",
    "from sklearn.naive_bayes import GaussianNB\n",
    "from sklearn.linear_model import LogisticRegression\n",
    "from sklearn.ensemble import StackingClassifier\n",
    "\n",
    "from sklearn.metrics import accuracy_score\n",
    "from sklearn.metrics import confusion_matrix\n",
    "from sklearn.metrics import classification_report\n",
    "\n",
    "\n",
    "# 데이터 불러오기\n",
    "raw_breast_cancer = datasets.load_breast_cancer()\n",
    "\n",
    "# 피쳐, 타겟 데이터 지정\n",
    "X = raw_breast_cancer.data\n",
    "y = raw_breast_cancer.target\n",
    "\n",
    "# 트레이닝/테스트 데이터 분할\n",
    "X_tn, X_te, y_tn, y_te=train_test_split(X,y,random_state=0)\n",
    "\n",
    "# 데이터 표준화\n",
    "std_scale = StandardScaler()\n",
    "std_scale.fit(X_tn)\n",
    "X_tn_std = std_scale.transform(X_tn)\n",
    "X_te_std  = std_scale.transform(X_te)\n",
    "\n",
    "# 스태킹 학습\n",
    "clf1 = svm.SVC(kernel='linear', random_state=1) \n",
    "clf2 = GaussianNB()\n",
    "\n",
    "clf_stkg = StackingClassifier(\n",
    "            estimators=[\n",
    "                ('svm', clf1), \n",
    "                ('gnb', clf2)\n",
    "            ],\n",
    "            final_estimator=LogisticRegression())\n",
    "clf_stkg.fit(X_tn_std, y_tn)\n",
    "\n",
    "# 예측\n",
    "pred_stkg = clf_stkg.predict(X_te_std)\n",
    "print(pred_stkg)\n",
    "\n",
    "# 정확도\n",
    "accuracy = accuracy_score(y_te, pred_stkg)\n",
    "print(accuracy)\n",
    "\n",
    "# confusion matrix 확인 \n",
    "conf_matrix = confusion_matrix(y_te, pred_stkg)\n",
    "print(conf_matrix)\n",
    "\n",
    "# 분류 레포트 확인\n",
    "class_report = classification_report(y_te, pred_stkg)\n",
    "print(class_report)"
   ]
  },
  {
   "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": "3.7.6"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 4
}