# -*- coding:utf-8 -*-
# 數據集成

import csv
import numpy as np
import pandas as pd
import matplotlib.pyplot as plt  

#客戶信息
basicInfo = pd.DataFrame.from_csv(‘datas/basicInfo_train.csv‘, header=0, sep=‘,‘, index_col=0, parse_dates=True, encoding=None, tupleize_cols=False, infer_datetime_format=False)
 
#歷史還款記錄
historyInfo = pd.DataFrame.from_csv(‘datas/history_train.csv‘, header=0, sep=‘,‘, index_col=0, parse_dates=True, encoding=None, tupleize_cols=False, infer_datetime_format=False)
#歷史逾期情況
defaultInfo = pd.DataFrame.from_csv(‘datas/default_train.csv‘, header=0, sep=‘,‘, index_col=0, parse_dates=True, encoding=None, tupleize_cols=False, infer_datetime_format=False)
combineInfo 
 
= pd.concat([basicInfo,historyInfo,defaultInfo],axis=1)

#查看前10條數據
combineInfo[:10]

#性別分析
gender = combineInfo.groupby(‘SEX‘)[‘Default‘].mean().reset_index()
plt.xticks((0,1),(u"Male",u"Female"))
plt.xlabel(u"Gender")
plt.ylabel(u"Counts")
plt.bar(gender.SEX,gender.Default,0.1,color=‘green
 
‘)
plt.show()

#教育程度與default值的相關性分析
edu = combineInfo.groupby(‘EDUCATION‘)[‘Default‘].mean()
plt.plot(edu)
plt.show()

#婚姻狀況分析
marriage = combineInfo.groupby(‘MARRIAGE‘)[‘Default‘].mean().reset_index()
plt.bar(marriage.MARRIAGE,marriage.Default,0.5,color=‘green‘)
plt.show()

Python大數據：信用卡逾期分析