13-ROC曲线的实现.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [],
   "source": [
    "import numpy as np\n",
    "import matplotlib.pyplot as plt"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [],
   "source": [
    "from sklearn import datasets\n",
    "\n",
    "# 进行数据的预处理，解决是二分类的问题\n",
    "digits = datasets.load_digits()\n",
    "X = digits.data\n",
    "y = digits.target.copy()\n",
    "\n",
    "y[digits.target==9] = 1\n",
    "y[digits.target!=9] = 0"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [],
   "source": [
    "from sklearn import datasets\n",
    "from sklearn.model_selection import train_test_split\n",
    "\n",
    "# 进行数据的预处理，解决是二分类的问题\n",
    "digits = datasets.load_digits()\n",
    "X = digits.data\n",
    "y = digits.target.copy()\n",
    "\n",
    "y[digits.target==9] = 1\n",
    "y[digits.target!=9] = 0\n",
    "\n",
    "# 进行数据集的划分\n",
    "train_x, test_x, train_y, test_y = train_test_split(X, y)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [],
   "source": [
    "from Scripts.Logistic import Logistic\n",
    "\n",
    "log_reg = Logistic()\n",
    "log_reg.fit(train_x, train_y)\n",
    "\n",
    "# 每个点到划分超平面的举例，在我们自己实现逻辑回归中有讲到过\n",
    "decision_scores = log_reg.decision_function(test_x)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [],
   "source": [
    "# 实现我们的TP\n",
    "def TP(y_true, y_predict):\n",
    "    assert len(y_true) == len(y_predict)\n",
    "    return np.sum((y_true == 1) & (y_predict == 1))\n",
    "\n",
    "def FN(y_true, y_predict):\n",
    "    assert len(y_true) == len(y_predict)\n",
    "    return np.sum((y_true == 1) & (y_predict == 0))\n",
    "\n",
    "def FP(y_true, y_predict):\n",
    "    assert len(y_true) == len(y_predict)\n",
    "    return np.sum((y_true == 0) & (y_predict == 1))\n",
    "\n",
    "def TN(y_true, y_predict):\n",
    "    assert len(y_true) == len(y_predict)\n",
    "    return np.sum((y_true == 0) & (y_predict == 0))\n",
    "\n",
    "def TPR(y_true, y_predict):\n",
    "    return TP(y_true, y_predict) / (TP(y_true, y_predict) + FN(y_true, y_predict))\n",
    "\n",
    "def FPR(y_true, y_predict):\n",
    "    return FP(y_true, y_predict) / (FP(y_true, y_predict) + TN(y_true, y_predict))\n",
    "\n",
    "fprs = []\n",
    "tprs = []\n",
    "thresholds = np.arange(np.min(decision_scores), np.max(decision_scores), 0.1)\n",
    "for threshold in thresholds:\n",
    "    y_predict = np.array(decision_scores >= threshold, dtype='int')\n",
    "    fprs.append(FPR(test_y, y_predict))\n",
    "    tprs.append(TPR(test_y, y_predict))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "plt.plot(fprs, tprs)\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "END"
   ]
  }
 ],
 "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": "3.7.1"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}