task5.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [],
   "source": [
    "import pandas as pd\n",
    "import numpy as np\n",
    "import matplotlib.pyplot as plt\n",
    "train=pd.read_csv('train1.csv',encoding='gbk')\n",
    "test=pd.read_csv('test1.csv',encoding='gbk')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [],
   "source": [
    "X_train=train.drop('status',axis=1)\n",
    "X_test=test.drop('status',axis=1)\n",
    "y_train=train['status']\n",
    "y_test=test['status']"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [],
   "source": [
    "from sklearn.preprocessing import minmax_scale\n",
    "X_train = minmax_scale(X_train)\n",
    "X_test =  minmax_scale(X_test)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [],
   "source": [
    "from sklearn.svm import SVC\n",
    "from sklearn.model_selection import GridSearchCV"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    " class sklearn.svm.SVC(C=1.0, kernel=’rbf’, degree=3, gamma=’auto_deprecated’, coef0=0.0, shrinking=True, probability=False, tol=0.001, cache_size=200, class_weight=None, verbose=False, max_iter=-1, decision_function_shape=’ovr’, random_state=None)[source]¶\n",
    " 主要调节的参数有：C、kernel、degree、gamma、coef0。\n",
    " kernel : string, optional (default=’rbf’)\n",
    "Specifies the kernel type to be used in the algorithm. It must be one of ‘linear’, ‘poly’, ‘rbf’, ‘sigmoid’, ‘precomputed’ or a callable."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "GridSearchCV(cv=5, error_score='raise',\n",
       "       estimator=SVC(C=1.0, cache_size=200, class_weight=None, coef0=0.0,\n",
       "  decision_function_shape='ovr', degree=3, gamma='auto', kernel='rbf',\n",
       "  max_iter=-1, probability=True, random_state=2018, shrinking=True,\n",
       "  tol=1e-06, verbose=False),\n",
       "       fit_params=None, iid=True, n_jobs=1,\n",
       "       param_grid=[{'kernel': ['linear', 'poly', 'rbf', 'sigmoid'], 'C': [0.1, 0.3, 1, 3, 10]}],\n",
       "       pre_dispatch='2*n_jobs', refit=True, return_train_score='warn',\n",
       "       scoring='roc_auc', verbose=0)"
      ]
     },
     "execution_count": 10,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "#因为对svm的核函数选用比较好奇，所以选择对SVM的参数进行寻优\n",
    "svc = SVC(kernel='sigmoid',probability=True,random_state=2018,tol=1e-6)\n",
    "param_grid=[{'kernel':['linear','poly','rbf','sigmoid'],'C':[0.1,0.3,1,3,10]}]\n",
    "svc = SVC(probability=True,random_state=2018,tol=1e-6)\n",
    "grid_search=GridSearchCV(svc,param_grid,cv=5,scoring='roc_auc')\n",
    "grid_search.fit(X_train,y_train)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "{'C': 3, 'kernel': 'linear'}"
      ]
     },
     "execution_count": 11,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "grid_search.best_params_"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "最佳参数： {'C': 3, 'kernel': 'linear'}\n",
      "训练集的最佳分数： 0.7920355176643208\n",
      "测试集的最佳分数： 0.7731643433473377\n"
     ]
    }
   ],
   "source": [
    "print('最佳参数：',grid_search.best_params_)\n",
    "print('训练集的最佳分数：', grid_search.best_score_)\n",
    "print('测试集的最佳分数：', grid_search.score(X_test, y_test))"
   ]
  },
  {
   "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": "3.6.5"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}