update

new_user_analysis/user_behavior_path.py

@@ -103,7 +103,7 @@ for t in range(1, task_days):
     (
         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}'
+        WHERE partition_day='{today_str}'
 
         union all
 
@@ -119,19 +119,19 @@ for t in range(1, task_days):
           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}'
+            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}'
+          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}'
+          WHERE partition_day = '{today_str}'
           AND (is_puppet = 'true' or is_classifyuser = 'true')
 
           UNION ALL
@@ -147,13 +147,13 @@ for t in range(1, task_days):
                 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}'
+                WHERE partition_date = '{today_str}'
             ) t1
             JOIN
             (
                 SELECT device_id
                 FROM online.ml_device_history_detail
-                WHERE partition_date = -'{today_str}'
+                WHERE partition_date = '{today_str}'
                 AND is_login_doctor = '1'
             ) t2
                 ON t1.device_id = t2.device_id
@@ -173,7 +173,8 @@ WHERE spam_pv.device_id IS NULL
     sql_res = new_urser_device_id_df.collect()
 
 
-print("-------------------------------")
-for count,res in enumerate(sql_res):
-    print(count,res)
+    print("-------------------------------")
+    for count,res in enumerate(sql_res):
+        print(count,res)
 
+    # user_behavior_sql =