Commit 65c955fd authored by 高雅喆's avatar 高雅喆

update

parent 375e7c50
......@@ -75,7 +75,7 @@ def get_device_order_info(start_timestamp):
# data
start_timestamp = 1572969600
device_info = get_device_order_info(1575594645)
device_info = get_device_order_info(start_timestamp)
# 获取搜索词及其近义词对应的tag
......@@ -105,6 +105,6 @@ device_ids_lst_rdd = spark.sparkContext.parallelize(device_info)
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, size=None)).filter(lambda x: x is not None)
print(result.count())
print(result.take(10))
df = spark.createDataFrame(result).na.drop().toDF("device", "search_words", "user_portrait").na.drop().toPandas()
df = spark.createDataFrame(result).na.drop().toDF("pay_time", "cl_id", "order_tag_id", "order_tag_id_score").na.drop().toPandas()
df.to_csv("~/gyz/log/stat_device_order_portrait_score_1106_1206.csv", index=False)
spark.stop()
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