update

task/search_tractate_ctr.py

@@ -73,7 +73,7 @@ spark.sql("CREATE TEMPORARY FUNCTION is_json AS 'com.gmei.hive.common.udf.UDFJso
 spark.sql("CREATE TEMPORARY FUNCTION arrayMerge AS 'com.gmei.hive.common.udf.UDFArryMerge'")
 
 task_list = []
-task_days = 60
+task_days = 3
 for t in range(1, task_days):
     day_num = 0 - t
     now = (datetime.datetime.now() + datetime.timedelta(days=day_num))
@@ -116,6 +116,17 @@ for t in range(1, task_days):
               )a
               group by partition_day,card_content_type,device_id
             )t1
+            left join 
+            (
+                SELECT DISTINCT device_id
+                FROM ml.ml_d_ct_dv_devicespam_d  --去除机构刷单设备，即作弊设备（浏览和曝光事件去除）
+                WHERE partition_day='{partition_day}'
+            
+                UNION ALL 
+                SELECT DISTINCT device_id
+                FROM dim.dim_device_user_staff   --去除内网用户
+            )spam_pv
+            on spam_pv.device_id=t1.device_id
             LEFT JOIN
             (
                 SELECT partition_date,device_id
@@ -245,7 +256,7 @@ for t in range(1, task_days):
         partition_date = yesterday_str
         pid = hashlib.md5((partition_date + device_os_type + active_type).encode("utf8")).hexdigest()
         click_num = res.neirong_click_pv
-        exposure = res.neirong_exp_pv
+        exposure = res.exposure
         try:
             search_ctr = round(click_num / exposure, 5)
         except: