update

eda/smart_rank/dist_update_user_portrait.py

@@ -118,7 +118,8 @@ if __name__ == '__main__':
         # 获取所有用户的设备id
         sql_device_ids = "select distinct cl_id from user_new_tag_log"
         cur_jerry_test.execute(sql_device_ids)
-        device_ids_lst = [i[0] for i in cur_jerry_test.fetchall()]
+        # todo 放开用户量
+        device_ids_lst = [i[0] for i in cur_jerry_test.fetchall()][:10]
 
         # 获取所有用户的行为日志
         sql_all_log = "select time,cl_id,score_type,tag_id,tag_referrer,action from user_new_tag_log"
@@ -145,6 +146,7 @@ if __name__ == '__main__':
         result_rename = result.selectExpr("_1 as cl_id", "_2 as tag_list")
         stat_date = datetime.datetime.today().strftime('%Y-%m-%d')
         result_last = result_rename.withColumn("stat_date", lit(stat_date))
+        result_last.show()
         df = result_last.select("stat_date", "cl_id", concat_ws(',', 'tag_list').alias("tag_list"))
         df.show()
         df.write.jdbc(