Home Credit信贷逾期风险预测

一、引入基础包及文件

#-*- coding:utf-8 –*-
import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
import seaborn as sns
import warnings
from sklearn.preprocessing import LabelEncoder, MinMaxScaler, Imputer
pd.set_option("display.max_columns", None)
warnings.filterwarnings("ignore")
df_train = pd.read_csv('F:\credit\\application_train.csv')
df_test  = pd.read_csv('F:\credit\\application_test.csv')

二、探索清洗数据
查看train文件基本信息，由于特征列数太多，这里就不详细列出了。重要的特征包括姓名、性别、收入、工作形式、工作年限等

print df_train.shape

(307511, 122)

print df_train.head()
print df_train.describe()

查看test文件基本信息，同样不列出详细列

print df_test.shape

(48744, 121)

train中，TARGET值为1的，说明未按时归还贷款，值为0的，说明按时归还贷款

print df_train['TARGET'].value_counts()

0    282686
1     24825

df_train['TARGET'].plot.hist()
plt.show()

显示只有8%左右的人群是未能按时归还贷款的。

# 遍历所有特征，查看特征中的空值
def mis_val_counts(df):
    mis_val = df.isnull().sum()
    mis_val_pec = 100*df.isnull().sum()/len(df)
    missing_val_counts = pd.concat([mis_val,mis_val_pec],axis=1)
    missing_val_counts_colnums = missing_val_counts.rename(columns={0: 'Missing Values', 1: '% of Total Values'})
    missing_val_counts_colnums = missing_val_counts_colnums[missing_val_counts_colnums.iloc[:,1]!=0].sort_values('% of Total Values').round(1)
    return missing_val_counts_colnums
    
print mis_val_counts(df_train)

DAYS_LAST_PHONE_CHANGE                     1                0.0
CNT_FAM_MEMBERS                            2                0.0
AMT_ANNUITY                               12                0.0
AMT_GOODS_PRICE                          278                0.1
EXT_SOURCE_2                             660                0.2
DEF_60_CNT_SOCIAL_CIRCLE                1021                0.3
OBS_60_CNT_SOCIAL_CIRCLE                1021                0.3
DEF_30_CNT_SOCIAL_CIRCLE                1021                0.3
OBS_30_CNT_SOCIAL_CIRCLE                1021                0.3
NAME_TYPE_SUITE                         1292                0.4
AMT_REQ_CREDIT_BUREAU_MON              41519               13.5
AMT_REQ_CREDIT_BUREAU_WEEK             41519               13.5
AM