Commit 6829f21a authored by 高雅喆's avatar 高雅喆

更新新用户的轻医美标签词

parent d475ced6
......@@ -117,7 +117,6 @@ if __name__ == '__main__':
redis_client.hmset(hot_search_words_portrait_portrait_key3, hot_search_words_portrait3_dict)
# rdd
spark.sparkContext.addPyFile("/srv/apps/ffm-baseline_git/eda/smart_rank/tool.py")
sparkConf = SparkConf().set("spark.hive.mapred.supports.subdirectories", "true") \
.set("spark.hadoop.mapreduce.input.fileinputformat.input.dir.recursive", "true") \
.set("spark.tispark.plan.allow_index_double_read", "false") \
......@@ -128,7 +127,7 @@ 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)
result = device_ids_lst_rdd.repartition(100).map(lambda x: get_user_history_order_service_tag(x))
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