update

eda/smart_rank/dist_update_user_portrait.py

@@ -142,7 +142,7 @@ if __name__ == '__main__':
 
         device_ids_lst_rdd = spark.sparkContext.parallelize(device_ids_lst)
         gm_kv_cli = redis.Redis(host="172.16.40.135", port=5379, db=6, socket_timeout=2000)
-        result = device_ids_lst_rdd.repartition(100).map(lambda x: get_user_tag_score(x, all_log_df)).toDF()
+        result = device_ids_lst_rdd.repartition(100).map(lambda x: get_user_tag_score(x, all_log_df)).toDF("cl_id","tag_list")
         result.show()
         # stat_date = datetime.datetime.today().strftime('%Y-%m-%d')
         # result_last = result.withColumn("stat_date", lit(stat_date))