update

task/search_strategy_d.py

@@ -71,8 +71,7 @@ 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 
-        (  
+    sql_distinct_device_id = r"""
             SELECT distinct user_id
             FROM online.tl_hdfs_doctor_view
             WHERE partition_date = '{yesterday_str}'
@@ -86,25 +85,7 @@ for t in range(0, task_days):
             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
-                )
 """.format(today_str=today_str, yesterday_str=yesterday_str)
     print(sql_distinct_device_id)
     distinct_device_id_df = spark.sql(sql_distinct_device_id)