update

new_user_analysis/new_user_has_protratit_rate.py

@@ -105,7 +105,7 @@ for t in range(1, task_days):
     one_week_age_str = (now + datetime.timedelta(days=-7)).strftime("%Y%m%d")
     new_urser_device_id_sql = r"""
     select t2.device_id as device_id from 
-    (select device_id from online.ml_device_day_active_status where partition_date = '${today_str}' and active_type in (1,2)) t2
+    (select device_id from online.ml_device_day_active_status where partition_date = '{today_str}' and active_type in (1,2)) t2
     LEFT JOIN
     (
         select distinct device_id
@@ -195,7 +195,6 @@ WHERE spam_pv.device_id IS NULL
     for count_user_count, res in enumerate(sql_res):
         # print(count, res)
         portratit_res = get_user_portrait_tag3_from_redis(res.device_id)
-        portratit_res
 
         # print(count_user_count, res, portratit_res)
         temp_count = 0

new_user_analysis/user_behavior_path.py

@@ -86,7 +86,7 @@ spark.sql("CREATE TEMPORARY FUNCTION is_json AS 'com.gmei.hive.common.udf.UDFJso
 spark.sql("CREATE TEMPORARY FUNCTION arrayMerge AS 'com.gmei.hive.common.udf.UDFArryMerge'")
 
 task_list = []
-task_days = 30
+task_days = 8
 
 name_dict = {
     "/api/my_order/recommend/service/list": "我的订单页推荐美购列表",
@@ -870,7 +870,7 @@ for t in range(1, task_days):
     one_week_age_str = (now + datetime.timedelta(days=-7)).strftime("%Y%m%d")
     new_urser_device_id_sql = r"""
     select t2.device_id as device_id from 
-    (select device_id from online.ml_device_day_active_status where partition_date = '${today_str}' and active_type in (1,2)) t2
+    (select device_id from online.ml_device_day_active_status where partition_date = '{today_str}' and active_type in (1,2)) t2
     LEFT JOIN
     (
         select distinct device_id
@@ -954,7 +954,7 @@ WHERE spam_pv.device_id IS NULL
     left join 
     (select cl_id, concat_ws(',', collect_list(action)) as track from
 (select * from online.bl_hdfs_maidian_updates where partition_date = {partition_date} and cl_id is not null ) group by cl_id) t2 
-on t1.device_id = t2.cl_id""".format(partition_date=yesterday_str)
+on t1.device_id = t2.cl_id""".format(partition_date=today_str)
     print(maidian_sql)
     track_df = spark.sql(maidian_sql)
     # track_df.createOrReplaceTempView("device_id_view")