update

new_user_analysis/user_behavior_path.py

@@ -94,12 +94,76 @@ for t in range(2, task_days):
     now = (datetime.datetime.now() + datetime.timedelta(days=day_num))
     last_30_day_str = (now + datetime.timedelta(days=-30)).strftime("%Y%m%d")
     today_str = now.strftime("%Y%m%d")
-    yesterday_str = (now + datetime.timedelta(days=-1)).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")
     new_urser_device_id_sql = r"""
     select t2.device_id from 
     (select first_device as device_id from online.ml_user_history_detail where partition_date = '{today_str}' and date_joined >= '{yesterday_str}') t2
- 
+    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='{today_str}'
+
+        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=t2.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='{today_str}'
+        )t1
+                JOIN
+            (  --医生账号
+          SELECT distinct user_id
+          FROM online.tl_hdfs_doctor_view
+          WHERE partition_date = '{today_str}'
+
+          --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 = '{today_str}'
+          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 = '{today_str}'
+            ) t1
+            JOIN
+            (
+                SELECT device_id
+                FROM online.ml_device_history_detail
+                WHERE partition_date = '{today_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
+    on t2.device_id=dev.device_id
+WHERE spam_pv.device_id IS NULL
+  and dev.device_id is null
     """.format(today_str=today_str,yesterday_str=yesterday_str)
 
     print(new_urser_device_id_sql)