update

task/spark_test.py

@@ -80,8 +80,33 @@ spark.sql("CREATE TEMPORARY FUNCTION arrayMerge AS 'com.gmei.hive.common.udf.UDF
 
 
 sql_search_ctr = r"""
-select * from online.bl_hdfs_maidian_updates where partition_date = '20200915' and cl_id is not null
-"""
+SELECT
+        cl_id,
+        card_id,
+        count(distinct app_session_id) as session_pv
+        from
+        (
+           SELECT 
+                  cl_id,
+                  card_id,
+                  app_session_id
+           from online.ml_community_precise_exposure_detail
+           WHERE partition_date>='{today_str}'
+           AND action in ('page_precise_exposure','home_choiceness_card_exposure') --7745版本action改为page_precise_exposure
+           AND is_exposure = '1'  ----精准曝光
+           AND page_name ='home'
+           AND tab_name = '精选'
+           AND (transaction_type in ('-1','smr','hotspot','pgc','newdata','hotspot_feed','aistragegy','excestragegy','FIXEDSTRATEGY','FIXEDSTRATEGY_VIDEO')
+                or transaction_type like '%ctr' or transaction_type like '%cvr' or transaction_type like 'deeplink%')
+           AND card_content_type in ('user_post')
+           AND transaction_type in ('high_quality_fmctr')
+           group by 
+                  cl_id,
+                  transaction_type,
+                  card_id,
+                  app_session_id
+        ) a  group by cl_id,card_id order by app_session_id desc
+""".format(today_str='20200922')
 
 print(sql_search_ctr)
 search_ctr_df = spark.sql(sql_search_ctr)