{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "import numpy as np\n",
    "import pandas as pd\n",
    "import matplotlib.pyplot as plt\n",
    "from matplotlib.pylab import rcParams\n",
    "from sklearn.datasets import make_blobs\n",
    "from sklearn.linear_model import LogisticRegression\n",
    "from sklearn.metrics import accuracy_score, confusion_matrix\n",
    "from sklearn.svm import SVC\n",
    "\n",
    "%matplotlib inline\n",
    "rcParams['figure.figsize'] = 9, 6"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Generate Imbalanced Datasets"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "# make 3-class dataset for classification\n",
    "center1 = [[0, 0]]\n",
    "X1, y1 = make_blobs(n_samples=800, centers=center1, random_state=42)\n",
    "center2 = [[0, 0], [1, 1]]\n",
    "X2, y2 = make_blobs(n_samples=200,\n",
    "                    centers=center2,\n",
    "                    random_state=42,\n",
    "                    cluster_std=0.3)\n",
    "X = np.vstack((X1, X2))\n",
    "y = np.hstack((y1, y2))"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "* 在圖上紅色點表示為壞人(1)，藍色點是好人(0)\n",
    "* 今天身為一位警察該如何透過兩個 feature 從好人中去抓出壞人呢？\n",
    "* 這邊產生的資料只有 20% 是壞人，80% 是好人"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "color = \"br\"\n",
    "color = [color[y[i]] for i in range(len(y))]\n",
    "plt.scatter(X[:, 0], X[:, 1], c=color, alpha=.5)\n",
    "plt.xlabel('Feature1')\n",
    "plt.ylabel('Feature2')"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Predict with Logistic Regression \n",
    "* 試試看預測結果 accuracy 有沒有辦法超過 90%?"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Print F1_Score, Precision, Recall"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# 如何讓F1_Score更好？\n",
    "* 大家可以試著 print 出 logistic regression 預測的 probability\n",
    "* 試著去調整 threshold 看看如何把 f1_score 做得更好。"
   ]
  },
  {
   "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": "3.7.4"
  },
  "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
}