update

new_user_analysis/user_behavior_path.py

@@ -87,18 +87,19 @@ spark.sql("CREATE TEMPORARY FUNCTION arrayMerge AS 'com.gmei.hive.common.udf.UDF
 
 
 task_list = []
-task_days = 3
+task_days = 2
 
-for t in range(2, task_days):
+for t in range(1, task_days):
     day_num = 0 - t
     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")
+    today_str_format = 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")
     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
+    (select first_device as device_id from online.ml_user_history_detail where partition_date = '{today_str}' and date_joined >= '{yesterday_str}' and date_joined <= '{today_str_format}') t2
     LEFT JOIN
     (
         select distinct device_id
@@ -164,7 +165,7 @@ for t in range(2, task_days):
     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)
+    """.format(today_str=today_str,yesterday_str=yesterday_str,today_str_format=today_str_format)
 
     print(new_urser_device_id_sql)
     new_urser_device_id_df = spark.sql(new_urser_device_id_sql)