update

task/search_strategy_d.py

@@ -71,6 +71,60 @@ for t in range(0, task_days):
     today_str = now.strftime("%Y%m%d")
     yesterday_str = (now + datetime.timedelta(days=-1)).strftime("%Y%m%d")
     one_week_age_str = (now + datetime.timedelta(days=-7)).strftime("%Y%m%d")
+    sql_distinct_device_id = r"""
+	SELECT partition_date,device_id
+	FROM 
+	(
+	    SELECT user_id,partition_date,
+	            if(size(device_list) > 0, device_list [ 0 ], '') AS device_id
+	      FROM online.ml_user_updates
+	      WHERE partition_date>='{yesterday_str}' AND partition_date<'{today_str}'
+	)t1
+	JOIN
+	(  
+	    SELECT distinct user_id
+	    FROM online.tl_hdfs_doctor_view
+	    WHERE partition_date = '{yesterday_str}'
+
+	    UNION ALL
+	    SELECT user_id
+	    FROM ml.ml_c_ct_ui_user_dimen_d
+	    WHERE partition_day = '{yesterday_str}'
+	    AND (is_puppet = 'true' or is_classifyuser = 'true')
+
+	    UNION ALL
+	    select distinct user_id
+	    from dim.dim_device_user_staff
+	    UNION ALL
+	    
+	    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 = '{yesterday_str}'
+	    )t1
+	    JOIN
+	    (
+	        SELECT device_id
+	        FROM online.ml_device_history_detail
+	        WHERE partition_date = '{yesterday_str}'
+	        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
+""".format(today_str=today_str, yesterday_str=yesterday_str, )
+    distinct_device_id_df = spark.sql(sql_distinct_device_id)
+    distinct_device_id_df.show(1, False)
+    sql_res = distinct_device_id_df.collect()
+    for res in sql_res:
+        print(res)
+
+    print("-------------------------------")
+
     sql = r"""SELECT
             ,t3.device_os_type as device_type
             ,t3.active_type as active_type
@@ -162,56 +216,6 @@ for t in range(0, task_days):
                 LATERAL VIEW explode(mas.active_type) t2 AS active_type
             )t2
             on t1.cl_id=t2.device_id AND t1.partition_date = t2.partition_date
-            LEFT JOIN
-(
-	SELECT partition_date,device_id
-	FROM 
-	(
-	    SELECT user_id,partition_date,
-	            if(size(device_list) > 0, device_list [ 0 ], '') AS device_id
-	      FROM online.ml_user_updates
-	      WHERE partition_date>='{yesterday_str}' AND partition_date<'{today_str}'
-	)t1
-	JOIN
-	(  
-	    SELECT distinct user_id
-	    FROM online.tl_hdfs_doctor_view
-	    WHERE partition_date = '{yesterday_str}'
-
-	    UNION ALL
-	    SELECT user_id
-	    FROM ml.ml_c_ct_ui_user_dimen_d
-	    WHERE partition_day = '{yesterday_str}'
-	    AND (is_puppet = 'true' or is_classifyuser = 'true')
-
-	    UNION ALL
-	    select distinct user_id
-	    from dim.dim_device_user_staff
-	    UNION ALL
-	    
-	    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 = '{yesterday_str}'
-	    )t1
-	    JOIN
-	    (
-	        SELECT device_id
-	        FROM online.ml_device_history_detail
-	        WHERE partition_date = '{yesterday_str}'
-	        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 t1.partition_date=dev.partition_date and t1.cl_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 active_type,device_os_type,channel
         )t
     )t3