{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "클래스 레이블: [0 1 2]\n"
     ]
    }
   ],
   "source": [
    "from sklearn import datasets\n",
    "import numpy as np\n",
    "\n",
    "iris = datasets.load_iris()\n",
    "X = iris.data[:, [2, 3]]\n",
    "y = iris.target\n",
    "\n",
    "print('클래스 레이블:', np.unique(y))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [],
   "source": [
    "from sklearn.model_selection import train_test_split\n",
    "\n",
    "X_train, X_test, y_train, y_test = train_test_split(\n",
    "    X, y, test_size=0.3, random_state=1, stratify=y)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [],
   "source": [
    "from sklearn.preprocessing import StandardScaler\n",
    "\n",
    "sc = StandardScaler()\n",
    "sc.fit(X_train)\n",
    "X_train_std = sc.transform(X_train)\n",
    "X_test_std = sc.transform(X_test)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [],
   "source": [
    "X_combined_std = np.vstack((X_train_std, X_test_std))\n",
    "y_combined = np.hstack((y_train, y_test))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [],
   "source": [
    "class LogisticRegressionGD(object):\n",
    "    \"\"\"경사 하강법을 사용한 로지스틱 회귀 분류기\n",
    "\n",
    "    매개변수\n",
    "    ------------\n",
    "    eta : float\n",
    "      학습률 (0.0과 1.0 사이)\n",
    "    n_iter : int\n",
    "      훈련 데이터셋 반복 횟수\n",
    "    random_state : int\n",
    "      가중치 무작위 초기화를 위한 난수 생성기 시드\n",
    "\n",
    "    속성\n",
    "    -----------\n",
    "    w_ : 1d-array\n",
    "      학습된 가중치\n",
    "    cost_ : list\n",
    "      에포크마다 누적된 로지스틱 비용 함수 값\n",
    "\n",
    "    \"\"\"\n",
    "    def __init__(self, eta=0.05, n_iter=100, random_state=1):\n",
    "        self.eta = eta\n",
    "        self.n_iter = n_iter\n",
    "        self.random_state = random_state\n",
    "\n",
    "    def fit(self, X, y):\n",
    "        \"\"\"훈련 데이터 학습\n",
    "\n",
    "        매개변수\n",
    "        ----------\n",
    "        X : {array-like}, shape = [n_samples, n_features]\n",
    "          n_samples 개의 샘플과 n_features 개의 특성으로 이루어진 훈련 데이터\n",
    "        y : array-like, shape = [n_samples]\n",
    "          타깃값\n",
    "\n",
    "        반환값\n",
    "        -------\n",
    "        self : object\n",
    "\n",
    "        \"\"\"\n",
    "        rgen = np.random.RandomState(self.random_state)\n",
    "        self.w_ = rgen.normal(loc=0.0, scale=0.01, size=1 + X.shape[1])\n",
    "        self.cost_ = []\n",
    "\n",
    "        for i in range(self.n_iter):\n",
    "            net_input = self.net_input(X)\n",
    "            output = self.activation(net_input)\n",
    "            errors = (y - output)\n",
    "            self.w_[1:] += self.eta * X.T.dot(errors)\n",
    "            self.w_[0] += self.eta * errors.sum()\n",
    "            \n",
    "            # 오차 제곱합 대신 로지스틱 비용을 계산합니다.\n",
    "            cost = -y.dot(np.log(output)) - ((1 - y).dot(np.log(1 - output)))\n",
    "            self.cost_.append(cost)\n",
    "        return self\n",
    "    \n",
    "    def net_input(self, X):\n",
    "        \"\"\"최종 입력 계산\"\"\"\n",
    "        return np.dot(X, self.w_[1:]) + self.w_[0]\n",
    "\n",
    "    def activation(self, z):\n",
    "        \"\"\"로지스틱 시그모이드 활성화 계산\"\"\"\n",
    "        return 1. / (1. + np.exp(-np.clip(z, -250, 250)))\n",
    "\n",
    "    def predict(self, X):\n",
    "        \"\"\"단위 계단 함수를 사용하여 클래스 레이블을 반환합니다\"\"\"\n",
    "        return np.where(self.net_input(X) >= 0.0, 1, 0)\n",
    "        # 다음과 동일합니다.\n",
    "        # return np.where(self.activation(self.net_input(X)) >= 0.5, 1, 0)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [],
   "source": [
    "from matplotlib.colors import ListedColormap\n",
    "import matplotlib.pyplot as plt\n",
    "\n",
    "\n",
    "def plot_decision_regions(X, y, classifier, test_idx=None, resolution=0.02):\n",
    "\n",
    "    # 마커와 컬러맵을 설정합니다.\n",
    "    markers = ('s', 'x', 'o', '^', 'v')\n",
    "    colors = ('red', 'blue', 'lightgreen', 'gray', 'cyan')\n",
    "    cmap = ListedColormap(colors[:len(np.unique(y))])\n",
    "\n",
    "    # 결정 경계를 그립니다.\n",
    "    x1_min, x1_max = X[:, 0].min() - 1, X[:, 0].max() + 1\n",
    "    x2_min, x2_max = X[:, 1].min() - 1, X[:, 1].max() + 1\n",
    "    xx1, xx2 = np.meshgrid(np.arange(x1_min, x1_max, resolution),\n",
    "                           np.arange(x2_min, x2_max, resolution))\n",
    "    Z = classifier.predict(np.array([xx1.ravel(), xx2.ravel()]).T)\n",
    "    Z = Z.reshape(xx1.shape)\n",
    "    plt.contourf(xx1, xx2, Z, alpha=0.3, cmap=cmap)\n",
    "    plt.xlim(xx1.min(), xx1.max())\n",
    "    plt.ylim(xx2.min(), xx2.max())\n",
    "\n",
    "    for idx, cl in enumerate(np.unique(y)):\n",
    "        plt.scatter(x=X[y == cl, 0], \n",
    "                    y=X[y == cl, 1],\n",
    "                    alpha=0.8, \n",
    "                    c=colors[idx],\n",
    "                    marker=markers[idx], \n",
    "                    label=cl, \n",
    "                    edgecolor='black')\n",
    "\n",
    "    # 테스트 샘플을 부각하여 그립니다.\n",
    "    if test_idx:\n",
    "        # 모든 샘플을 그립니다.\n",
    "        X_test, y_test = X[test_idx, :], y[test_idx]\n",
    "\n",
    "        plt.scatter(X_test[:, 0],\n",
    "                    X_test[:, 1],\n",
    "                    facecolor='none',\n",
    "                    edgecolor='black',\n",
    "                    alpha=1.0,\n",
    "                    linewidth=1,\n",
    "                    marker='o',\n",
    "                    s=100, \n",
    "                    label='test set')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "C:\\Users\\jihun\\AppData\\Local\\Temp\\ipykernel_13336\\477685992.py:24: UserWarning: You passed a edgecolor/edgecolors ('black') for an unfilled marker ('x').  Matplotlib is ignoring the edgecolor in favor of the facecolor.  This behavior may change in the future.\n",
      "  plt.scatter(x=X[y == cl, 0],\n"
     ]
    },
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 640x480 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "X_train_01_subset = X_train_std[(y_train == 0) | (y_train == 1)]\n",
    "y_train_01_subset = y_train[(y_train == 0) | (y_train == 1)]\n",
    "\n",
    "lrgd = LogisticRegressionGD(eta=0.05, n_iter=1000, random_state=1)\n",
    "lrgd.fit(X_train_01_subset,\n",
    "         y_train_01_subset)\n",
    "\n",
    "plot_decision_regions(X=X_train_01_subset, \n",
    "                      y=y_train_01_subset,\n",
    "                      classifier=lrgd)\n",
    "\n",
    "plt.xlabel('petal length [standardized]')\n",
    "plt.ylabel('petal width [standardized]')\n",
    "plt.legend(loc='upper left')\n",
    "\n",
    "plt.tight_layout()\n",
    "# plt.savefig('images/03_05.png', dpi=300)\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### 사이킷런을 사용해 로지스틱 회귀 모델 훈련하기"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "C:\\Users\\jihun\\AppData\\Local\\Temp\\ipykernel_13336\\477685992.py:24: UserWarning: You passed a edgecolor/edgecolors ('black') for an unfilled marker ('x').  Matplotlib is ignoring the edgecolor in favor of the facecolor.  This behavior may change in the future.\n",
      "  plt.scatter(x=X[y == cl, 0],\n"
     ]
    },
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 640x480 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "from sklearn.linear_model import LogisticRegression\n",
    "\n",
    "lr = LogisticRegression(C=100.0, random_state=1)\n",
    "lr.fit(X_train_std, y_train)\n",
    "\n",
    "plot_decision_regions(X_combined_std, y_combined,\n",
    "                      classifier=lr, test_idx=range(105, 150))\n",
    "plt.xlabel('petal length [standardized]')\n",
    "plt.ylabel('petal width [standardized]')\n",
    "plt.legend(loc='upper left')\n",
    "plt.tight_layout()\n",
    "# plt.savefig('images/03_06.png', dpi=300)\n",
    "plt.show()"
   ]
  }
 ],
 "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": "3.11.4"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}