update

task/search_meigou_ctr.py

@@ -230,13 +230,74 @@ left join
  WHERE T.PARTITION_DAY = '{partition_day}'
    AND T.ACTIVE_TYPE IN ('1', '2', '4'))
     D on T.DEVICE_ID =  D.DEVICE_ID 
-    LEFT JOIN spam_pv on spam_pv.device_id= T.DEVICE_ID
-    LEFT JOIN dev_view on dev_view.device_id= T.DEVICE_ID
-    WHERE (spam_pv.device_id IS NULL or spam_pv.device_id = '')
-and (dev_view.device_id is null or dev_view.device_id='')
+        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=T.DEVICE_ID
+LEFT JOIN
+(
+	SELECT partition_date,device_id
+	FROM 
+	(--找出user_id当天活跃的第一个设备id
+	    SELECT user_id,partition_date,
+	            if(size(device_list) > 0, device_list [ 0 ], '') AS device_id
+	      FROM online.ml_user_updates
+	      WHERE partition_date>='{partition_day}' AND partition_date<'{end_date}'
+	)t1
+	JOIN
+	(  --医生账号
+	    SELECT distinct user_id
+	    FROM online.tl_hdfs_doctor_view
+	    WHERE partition_date = '{partition_day}'
+
+	    --马甲账号/模特用户
+	    UNION ALL
+	    SELECT user_id
+	    FROM ml.ml_c_ct_ui_user_dimen_d
+	    WHERE partition_day = '{partition_day}'
+	    AND (is_puppet = 'true' or is_classifyuser = 'true')
+
+	    UNION ALL
+	    --公司内网覆盖用户
+	    select distinct user_id
+	    from dim.dim_device_user_staff
+
+	    UNION ALL
+	    --登陆过医生设备
+	    SELECT distinct t1.user_id
+	    FROM
+	    (
+	        SELECT user_id, v.device_id as device_id
+	        FROM online.ml_user_history_detail
+	            LATERAL VIEW EXPLODE(device_history_list) v AS device_id
+	        WHERE partition_date = '{partition_day}'
+	    )t1
+	    JOIN
+	    (
+	        SELECT device_id
+	        FROM online.ml_device_history_detail
+	        WHERE partition_date = '{partition_day}'
+	        AND is_login_doctor = '1'
+	    )t2
+	        ON t1.device_id = t2.device_id
+	)t2
+	on t1.user_id=t2.user_id
+	group by partition_date,device_id
+)dev 
+on T.DEVICE_ID=dev.device_id
+WHERE (spam_pv.device_id IS NULL or spam_pv.device_id = '')
+and (dev.device_id is null or dev.device_id='')
+
     GROUP by D.DEVICE_OS_TYPE,
         D.ACTIVE_TYPE
-    """.format(partition_day=yesterday_str, )
+    """.format(partition_day=yesterday_str,end_date=today_str )
 
     print(sql_search_ctr)
     search_ctr_df = spark.sql(sql_search_ctr)