python_两个数据集拼接join操作 t3 = dataset3 [[ 'user_id' , 'coupon_id' , 'date_received' ]] t3 = pd . merge ( t3 , t2 , on = [ 'user_id' , 'coupon_id' ], how = 'left' ) t3 [ 'this_month_user_receive_same_coupon_lastone' ] = t3 . ma
python_两个数据集拼接&join操作
t3 = dataset3[['user_id','coupon_id','date_received']]t3 = pd.merge(t3,t2,on=['user_id','coupon_id'],how='left')
t3['this_month_user_receive_same_coupon_lastone'] = t3.max_date_received - t3.date_received
t3['this_month_user_receive_same_coupon_firstone'] = t3.date_received - t3.min_date_received
#根据多个字段就进行merge
other_feature3 = pd.merge(t1,t,on='user_id')
other_feature3 = pd.merge(other_feature3,t3,on=['user_id','coupon_id'])
other_feature3 = pd.merge(other_feature3,t4,on=['user_id','date_received'])
other_feature3 = pd.merge(other_feature3,t5,on=['user_id','coupon_id','date_received'])
other_feature3 = pd.merge(other_feature3,t7,on=['user_id','coupon_id','date_received'])
other_feature3.to_csv('data/other_feature3.csv',index=None)
#拼接数据集
#两个数据框合并为一个
df_train_stmt = pd.concat([df_train_stmt,df_train_stmt_test],axis = 0)