{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "from sklearn import preprocessing\n",
    "import numpy as np\n",
    "from sklearn.model_selection import train_test_split\n",
    "from sklearn.datasets import make_classification\n",
    "import matplotlib.pyplot as plt\n",
    "from matplotlib.pylab import rcParams\n",
    "rcParams['figure.figsize'] = 8, 5"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "# 製作兩個feature的分類資料\n",
    "X, y = make_classification(n_samples=300,\n",
    "                           n_features=2,\n",
    "                           n_redundant=0,\n",
    "                           n_informative=2,\n",
    "                           random_state=22,\n",
    "                           n_clusters_per_class=1,\n",
    "                           scale=100)\n",
    "# 將資料可視化\n",
    "plt.scatter(X[:, 0], X[:, 1], c=y)\n",
    "plt.xlabel('X1')\n",
    "plt.ylabel('X2')\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Prediction before normalization"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "from sklearn.svm import SVC\n",
    "\n",
    "# 將資料分成訓練及測試集\n",
    "X_train, X_test, y_train, y_test = train_test_split(X,\n",
    "                                                    y,\n",
    "                                                    test_size=0.3,\n",
    "                                                    random_state=42)\n",
    "# import svm classifier\n",
    "model = SVC()\n",
    "model.fit(X_train, y_train)\n",
    "prediction = model.predict(X)\n",
    "print('accuracy before normalization:%.2f' % model.score(X_test, y_test))"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# 可視化結果"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "# 畫出原始資料\n",
    "plt.subplot(121)\n",
    "plt.scatter(X[:, 0], X[:, 1], c=y)\n",
    "plt.title('Actual')\n",
    "plt.xlabel('X1')\n",
    "plt.ylabel('X2')\n",
    "# 畫出預測結果\n",
    "plt.subplot(122)\n",
    "plt.scatter(X[:, 0], X[:, 1], c=prediction)\n",
    "plt.title('Prediction')\n",
    "plt.xlabel('X1')\n",
    "plt.ylabel('X2')\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Predictino after normalization"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "from sklearn.svm import SVC\n",
    "\n",
    "# 將資料做z-score normalization\n",
    "X = preprocessing.scale(X)\n",
    "# 將資料分成訓練及測試集\n",
    "X_train, X_test, y_train, y_test = train_test_split(X,\n",
    "                                                    y,\n",
    "                                                    test_size=0.3,\n",
    "                                                    random_state=42)\n",
    "# import svm classifier\n",
    "model = SVC()\n",
    "model.fit(X_train, y_train)\n",
    "prediction = model.predict(X)\n",
    "print('accuracy after normalization:%.2f' % model.score(X_test, y_test))"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# 將結果可視化"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "# 畫出原始資料\n",
    "plt.subplot(121)\n",
    "plt.scatter(X[:, 0], X[:, 1], c=y)\n",
    "plt.title('Actual')\n",
    "plt.xlabel('X1')\n",
    "plt.ylabel('X2')\n",
    "# 畫出預測結果\n",
    "plt.subplot(122)\n",
    "plt.scatter(X[:, 0], X[:, 1], c=prediction)\n",
    "plt.title('Prediction')\n",
    "plt.xlabel('X1')\n",
    "plt.ylabel('X2')\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "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": "3.10.2"
  },
  "toc": {
   "base_numbering": 1,
   "nav_menu": {},
   "number_sections": true,
   "sideBar": true,
   "skip_h1_title": false,
   "title_cell": "Table of Contents",
   "title_sidebar": "Contents",
   "toc_cell": false,
   "toc_position": {},
   "toc_section_display": true,
   "toc_window_display": false
  }
 },
 "nbformat": 4,
 "nbformat_minor": 4
}