天池大赛o2o优惠券第一名代码解读(4)

每天惯例感激

#4.user_merchant:
      #times_user_buy_merchant_before. 

all_user_merchant = feature3[['user_id','merchant_id']]
all_user_merchant.drop_duplicates(inplace=True)
#只保留销售了商品的商户id
t = feature3[['user_id','merchant_id','date']]
t = t[t.date!='null'][['user_id','merchant_id']]
#用户一共买了这家商户的多少商品
t['user_merchant_buy_total'] = 1
t = t.groupby(['user_id','merchant_id']).agg('sum').reset_index()
t.drop_duplicates(inplace=True)

t1 = feature3[['user_id','merchant_id','coupon_id']]
t1 = t1[t1.coupon_id!='null'][['user_id','merchant_id']]
#用户一共收到一个商户的多少优惠券
t1['user_merchant_received'] = 1
t1 = t1.groupby(['user_id','merchant_id']).agg('sum').reset_index()
t1.drop_duplicates(inplace = True)


t2 = feature3[['user_id','merchant_id','date','date_received']]
t2 = t2[(t2.date!='null')&(t2.date_received!='null')][['user_id','merchant_id']]
#用户在一家商户中使用优惠券购买的商品的数目
t2['user_merchant_buy_use_coupon'] = 1
t2 = t2.groupby(['user_id','merchant_id']).agg('sum').reset_index()
t2.drop_duplicates(inplace = True)

#用户在一家商家的所有记录总数
t3 = feature3[['user_id','merchant_id']]
t3['user_merchant_any'] = 1
t3 = t3.groupby(['user_id','merchant_id']).agg('sum').reset_index()
t3.drop_duplicates(inplace = True)

t4 = feature3[['user_id','merchant_id','date','coupon_id']]
t4 = t4[(t4.date!='null')&(t4.coupon_id=='null')][['user_id','merchant_id']]
#用户没有使用优惠券购买的商品的数目
t4['user_merchant_buy_common'] = 1
t4 = t4.groupby(['user_id','merchant_id']).agg('sum').reset_index()
t4.drop_duplicates(inplace = True)

user_merchant3 = pd.merge(all_user_merchant,t,on=['user_id','merchant_id'],how='left')
user_merchant3 = pd.merge(user_merchant3,t1,on=['user_id','merchant_id'],how='left')
user_merchant3 = pd.merge(user_merchant3,t2,on=['user_id','merchant_id'],how='left')
user_merchant3 = pd.merge(user_merchant3,t3,on=['user_id','merchant_id'],how='left')
user_merchant3 = pd.merge(user_merchant3,t4,on=['user_id','merchant_id'],how='left')
#都是针对一家商户和一个用户
user_merchant3.user_merchant_buy_use_coupon = user_merchant3.user_merchant_buy_use_coupon.replace(np.nan,0)
user_merchant3.user_merchant_buy_common = user_merchant3.user_merchant_buy_common.replace(np.nan,0)
#y优惠券的转换率，用户使用了的优惠券/一共收到的优惠券
user_merchant3['user_merchant_coupon_transfer_rate'] = user_merchant3.user_merchant_buy_use_coupon.astype('float') / user_merchant3.user_merchant_received.astype('float')
#用户使用优惠券的概率，在一家商户使用优惠券购买的商品/在一家商户购买商品的总数
user_merchant3['user_merchant_coupon_buy_rate'] = user_merchant3.user_merchant_buy_use_coupon.astype('float') / user_merchant3.user_merchant_buy_total.astype('float')
#用户在商户消费的概率 用户在商户购买的总数/在一家商户浏览的总次数
user_merchant3['user_merchant_rate'] = user_merchant3.user_merchant_buy_total.astype('float') / user_merchant3.user_merchant_any.astype('float')
#用户在一家商户不适用优惠券购买的概率 普通购买的商品数/购买商品的总数
user_merchant3['user_merchant_common_buy_rate'] = user_merchant3.user_merchant_buy_common.astype('float') / user_merchant3.user_merchant_buy_total.astype('float')
user_merchant3.to_csv('data/user_merchant3.csv',index=None)

#对于数据集2
all_user_merchant = feature2[['user_id','merchant_id']]
all_user_merchant.drop_duplicates(inplace=True)

t = feature2[['user_id','merchant_id','date']]
t = t[t.date!='null'][['user_id','merchant_id']]
t['user_merchant_buy_total'] = 1
t = t.groupby(['user_id','merchant_id']).agg('sum').reset_index()
t.drop_duplicates(inplace = True)

t1 = feature2[['user_id','merchant_id','coupon_id']]
t1 = t1[t1.coupon_id != 'null'][['user_id','merchant_id']]
t1['user_merchant_received'] = 1
t1 = t1.groupby(['user_id','merchant_id']).agg('sum').reset_index()
t1.drop_duplicates(inplace = True)

t2 = feature2[['user_id','merchant_id','date','date_received']]
t2 = t2[(t2.date!='null')&(t2.date_received !='null')][['user_id','merchant_id']]
t2['user_merchant_buy_use_coupon'] = 1
t2 = t2.groupby(['user_id','merchant_id']).agg('sum').reset_index()
t2.drop_duplicates(inplace= True)

t3 = feature2[['user_id','merchant_id']]
t3['user_merchant_any'] = 1
t3 = t3.groupby(['user_id','merchant_id']).agg('sum').reset_index()
t3.drop_duplicates(inplace=True)

t4 = feature2[['user_id','merchant_id','date','coupon_id']]
t4 = t4[(t4.date !='null')&(t4.coupon_id == 'null')][['user_id','merchant_id']]
t4['user_merchant_buy_common'] = 1
t4 = t4.groupby(['user_id','merchant_id']).agg('sum').reset_index()
t4.drop_duplicates(inplace=True)

user_merchant2 = pd.merge(all_user_merchant,t,on=['user_id','merchant_id'],how='left')
user_merchant2 = pd.merge(user_merchant2,t1,on=['user_id','merchant_id'],how='left')
user_merchant2 = pd.merge(user_merchant2,t2,on=['user_id','merchant_id'],how='left')
user_merchant2 = pd.merge(user_merchant2,t3,on=['user_id','merchant_id'],how='left')
user_merchant2 = pd.merge(user_merchant2,t4,on=['user_id','merchant_id'],how='left')

user_merchant2.user_merchant_buy_use_coupon = user_merchant2.user_merchant_buy_use_coupon.replace(np.nan,0)
user_merchant2.user_merchant_buy_common = user_merchant2.user_merchant_buy_common.replace(np.nan,0)

user_merchant2['user_merchant_coupon_transfer_rate'] = user_merchant2.user_merchant_buy_use_coupon.astype('float') / user_merchant2.user_merchant_received.astype('float')
user_merchant2['user_merchant_coupon_buy_rate'] = user_merchant2.user_merchant_buy_use_coupon.astype('float') / user_merchant2.user_merchant_buy_total.astype('float')
user_merchant2['user_merchant_rate'] = user_merchant2.user_merchant_buy_total.astype('float') / user_merchant2.user_merchant_any.astype('float')
user_merchant2['user_merchant_common_buy_rate'] = user_merchant2.user_merchant_buy_common.astype('float') / user_merchant2.user_merchant_buy_total.astype('float')
user_merchant2.to_csv('data/user_merchant2.csv',index=None)