Commit b228de88 authored by 高雅喆's avatar 高雅喆

fix taskSet too large

parent 5c9537eb
......@@ -214,7 +214,7 @@ if __name__ == '__main__':
spark = SparkSession.builder.config(conf=sparkConf).enableHiveSupport().getOrCreate()
spark.sparkContext.setLogLevel("WARN")
spark.sparkContext.addPyFile("/srv/apps/ffm-baseline_git/eda/smart_rank/tool.py")
device_ids_lst_rdd = spark.sparkContext.parallelize(device_ids_lst, numSlices=2)
device_ids_lst_rdd = spark.sparkContext.parallelize(device_ids_lst, numSlices=1000)
result = device_ids_lst_rdd.repartition(100).map(lambda x: get_user_service_portrait(x, all_word_tags, all_tag_tag_type, all_3tag_2tag, all_tags_name))
result.collect()
......
Markdown is supported
0% or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment