泰迪—020优惠券使用预测未完成版本

import pandas as pd
import numpy as np
df_train=pd.read_csv(open('G:/o2o商家优惠券使用预测/训练数据.csv',encoding='utf-8'))
#df_test=pd.read_csv(open('G:/o2o商家优惠券使用预测/测试数据.csv',encoding='utf-8'))

print(df_train.info())
print(df_train.head())
df_train.columns = ['User_id','Merchant_id','Coupon_id','Discount_rate','Distance','Date_received','Date']

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 1754884 entries, 0 to 1754883
Data columns (total 7 columns):
User_id          int64
Merchant_id      int64
Coupon_id        object
Discount_rate    object
Distance         object
Date_received    object
Date             object
dtypes: int64(2), object(5)
memory usage: 93.7+ MB
None
   User_id  Merchant_id Coupon_id Discount_rate Distance Date_received  \
0  1439408         2632      null          null        0          null   
1  1439408         4663     11002        150:20        1      20160528   
2  1439408         2632      8591          20:1        0      20160217   
3  1439408         2632      1078          20:1        0      20160319   
4  1439408         2632      8591          20:1        0      20160613   

       Date  
0  20160217  
1      null  
2      null  
3      null  
4      null  

#新增列并初始化
df_train['t_discount']='-1'
df_train['t_litPrice']='-1'
df_train['consumeType']='-1'
df_train['t_days']=int(-1)
df_train = df_train[['User_id','Merchant_id','Coupon_id','Discount_rate','t_litPrice','t_discount','Distance','Date_received','Date','t_days','consumeType']]

print('有优惠券，购买商品条数', df_train[(df_train['Date_received'] != 'null') & (df_train['Date'] != 'null')].shape[0])
print