客户贷款逾期预测[4]-记录评分、绘制roc曲线

任务

       记录五个模型（逻辑回归、svm、决策树、xgboost、lightgbm）关于precision、recall score、f1 score、roc、aoc的评分表格。

实现

# -*- coding: utf-8 -*-
"""
Created on Thu Nov 15 13:02:11 2018

@author: keepi
"""

import pandas as pd
from sklearn.model_selection import train_test_split
from sklearn.preprocessing import StandardScaler
import warnings
warnings.filterwarnings('ignore')

#导入数据
data = pd.read_csv('data.csv',encoding='gb18030')
print("data.shape:",data.shape)
#数据处理
miss_rate = data.isnull().sum() / len(data)
#print("缺失率：",miss_rate.sort_values(ascending=False))
X_num = data.select_dtypes('number').copy()
X_num.fillna(X_num.mean(),inplace=True)
print("数值型特征的shape：",X_num.shape)
print(X_num.columns)
X_num.drop(['Unnamed: 0','status'],axis=1,inplace=True)

X_str = data.select_dtypes(exclude='number').copy()
X_str.fillna(0,inplace=True)
print("非数值型特征：",X_str.columns)
print(X_str.head())

X_dummy = pd.get_dummies(X_str['reg_preference_for_trad'])
X = pd.concat([X_num,X_dummy],axis=1,sort=False)
y = data['status']

#划分训练集、测试集
X_train,X_test,y_train,y_test = train_test_split(X,y,test_size=0.3,random_state=1117)

#归一化
ss = StandardScaler()
X_train_std = ss.fit_transform(X_train)
X_test_std = ss.transf