update

eda/smart_rank/dist_periodic_update_smart_rank.py

@@ -163,8 +163,8 @@ if __name__ == '__main__':
             device_ids_rdd = spark.sparkContext.parallelize(device_ids)
             result = device_ids_rdd.repartition(40).map(
                 lambda x: update_device_smart_rank(str(x, encoding='utf-8'), result_all_dict,
-                                                   service_detail_view_count_30_dict, result_smart_rank_score_dict))
-            result.foreach(print)
+                                                   service_detail_view_count_30_dict, result_smart_rank_score_dict)).toDF()
+            result.show()
             print(time.time() - start)
     except Exception as e:
         print(e)
\ No newline at end of file

eda/smart_rank/dist_update_user_portrait.py

@@ -139,7 +139,7 @@ if __name__ == '__main__':
         spark = SparkSession.builder.config(conf=sparkConf).enableHiveSupport().getOrCreate()
         spark.sparkContext.setLogLevel("WARN")
 
-        device_ids_lst_rdd = spark.sparkContext.parallelize(device_ids_lst, numSlices=100)
+        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))
         result.take(10).foreach(print)