1

auto-spread/auto_manage/candidate_set_temp.py

@@ -12,7 +12,7 @@ from dingtalkchatbot.chatbot import DingtalkChatbot
 # WebHook地址
 webhook = 'https://oapi.dingtalk.com/robot/send?access_token=4f28ce996ab4f2601c0362fbfd0d48f58b0250a76953ff117ca41e9f1ec8e565'
 # 初始化机器人小丁
-xiaoding = DtalkChatbot(webhook)
+xiaoding = DingtalkChatbot(webhook)
 at_mobiles = ['18668032242']
 
 os.chdir('/home/db_dlp/mengxiangxuan/auto_spread')
@@ -54,7 +54,7 @@ try:
     pre_slotad_stat_cvr['slotid'] = bb[:, 0]
     pre_slotad_stat_cvr['advert_id'] = bb[:, 1]
     pre_slotad_stat_cvr['cvr'] = ll[:, 1]
-    # pre_slotad_stat_cvr.head()
+    pre_slotad_stat_cvr['cvr'] = pre_slotad_stat_cvr['cvr'].map(lambda x: x.replace('E-', 'E-5'))
     pre_slotad_stat_cvr['cvr'] = pre_slotad_stat_cvr['cvr'].astype('float')
 
     # 匹配广告行业
@@ -184,7 +184,7 @@ try:
     for i in pre_slotad_cvr_good_old.index:
         key = pre_slotad_cvr_good_old.ix[i, 'key']
         value = pre_slotad_cvr_good_old.ix[i, 'value']
-        pipe.set(key, value, ex=200)
+        pipe.set(key, value, ex=600)
         if i % 5000 == 0:
             pipe.execute()
             print(i)

auto-spread/auto_manage/effect_eva.py

+import os
+import pandas as pd
+import numpy as np
+from pyhive import hive
+from sqlalchemy import create_engine
+import pymysql
+import redis
+import datetime
+import time
+
+os.chdir('/home/db_dlp/mengxiangxuan/auto_spread')
+cursor = hive.connect(host='10.50.10.11', port=10000, username='mengxiangxuan', database='default').cursor()
+now = datetime.datetime.now()
+today = now.strftime('%Y-%m-%d')
+delta1 = datetime.timedelta(days=1)
+delta3 = datetime.timedelta(days=3)
+delta5 = datetime.timedelta(days=5)
+delta7 = datetime.timedelta(days=7)
+delta10 = datetime.timedelta(days=10)
+delta15 = datetime.timedelta(days=15)
+yestoday1 = (now - delta1).strftime('%Y-%m-%d')
+yestoday3 = (now - delta3).strftime('%Y-%m-%d')
+yestoday5 = (now - delta5).strftime('%Y-%m-%d')
+yestoday7 = (now - delta7).strftime('%Y-%m-%d')
+yestoday10 = (now - delta10).strftime('%Y-%m-%d')
+yestoday15 = (now - delta15).strftime('%Y-%m-%d')
+
+#按照偏差找价格切分点不可行
+sql='''select advert_id,
+fee_level,
+avg(fee) fee,
+sum(charge_fees) cost,
+sum(act_click_cnt) convert,
+avg(ad_costconvert) ad_costconvert
+from
+(select a.advert_id,
+   a.charge_fees,a.act_click_cnt,a.fee,
+   b.min_fee,b.max_fee,
+   floor((a.fee-b.min_fee)*100/(b.max_fee-b.min_fee)) fee_level,
+   b.ad_costconvert  
+   from (select * from advert.dws_advert_order_wide_v4_level_3_di 
+   where dt>='{0}' and dt<='{1}' and fee>0 and charge_fees>0) a
+   left outer join
+   (select 
+	advert_id,min(fee) min_fee,max(fee) max_fee,
+	sum(charge_fees)/sum(act_click_cnt) ad_costconvert
+	from advert.dws_advert_order_wide_v4_level_3_di 
+	where dt>='{0}' and dt<='{1}' and fee>0 and charge_fees>0
+	group by advert_id) b
+	on a.advert_id=b.advert_id) t
+group by advert_id,fee_level'''.format(yestoday3, yestoday1)
+
+cursor.execute(sql)
+fee_level_data = pd.DataFrame(cursor.fetchall())
+fee_level_data.columns=['advert_id','fee_level','fee','cost','convert','ad_costconvert']
+fee_level_data['convert']=fee_level_data['convert'].fillna(value=0)
+fee_level_data['cost_cumsum']=fee_level_data['cost'].groupby(fee_level_data['advert_id']).cumsum()
+fee_level_data['convert_cumsum']=fee_level_data['convert'].groupby(fee_level_data['advert_id']).cumsum()
+fee_level_data['costconvert']=fee_level_data['cost_cumsum']/fee_level_data['convert_cumsum']
+fee_level_data['costconvert_bias']=fee_level_data['costconvert']/fee_level_data['ad_costconvert']
+fee_level_data.to_csv('fee_level_data.csv',index=False)
+
+#按分位数找切分点--效果评估
+
+nolunch_pre_cvr = pd.read_table(r'slot_ad_cvr.txt',sep=',')
+nolunch_pre_cvr.columns = ['slotad','ctr','cvr']
+nolunch_pre_cvr[['slotid','advert_id']]=nolunch_pre_cvr['slotad'].str.split('_',expand=True)
+nolunch_pre_cvr['w_sum_cvr']=nolunch_pre_cvr['ctr']*nolunch_pre_cvr['cvr']
+nolunch_ad_cvr=pd.DataFrame(nolunch_pre_cvr.groupby(['advert_id']).sum())
+nolunch_ad_cvr['pre_ad_cvr']=nolunch_ad_cvr['w_sum_cvr']/nolunch_ad_cvr['ctr']
+nolunch_ad_cvr['advert_id']=nolunch_ad_cvr.index
+
+
+sql = '''
+select advert_id,avg(stat_cvr)
+from logs.dwd_nezha_result_log_di
+where dt>='{0}' and dt<='{1}' and order_id is not null
+group by advert_id
+'''.format(yestoday15,yestoday1)
+cursor.execute(sql)
+ad_pre_eva = pd.DataFrame(cursor.fetchall())
+ad_pre_eva.columns = ['advert_id','ad_cvr']
+ad_pre_eva['advert_id'] = ad_pre_eva['advert_id'].astype('str')
+
+ad_pre_cvr_eva = pd.merge(nolunch_ad_cvr, ad_pre_eva, how='left', on=['advert_id'])
+ad_pre_cvr_eva['ad_pre_diff']=ad_pre_cvr_eva['pre_ad_cvr']/ad_pre_cvr_eva['ad_cvr']
+ad_pre_cvr_eva.ix[ad_pre_cvr_eva['ad_pre_diff']>1.5].shape[0]/ad_pre_cvr_eva.shape[0]#85%的准确率
+
+
+
+
+
+
+
+
+
+
+