Commit 637fd6ce authored by 高雅喆's avatar 高雅喆

test

parent a594fcd6
...@@ -77,14 +77,8 @@ def get_user_service_portrait(cl_id, all_word_tags, all_tag_tag_type, all_3tag_2 ...@@ -77,14 +77,8 @@ def get_user_service_portrait(cl_id, all_word_tags, all_tag_tag_type, all_3tag_2
gmkv_tag_score_sum = tag_score_sum[["tag2", "tag_score", "weight"]][:size].to_dict('record') gmkv_tag_score_sum = tag_score_sum[["tag2", "tag_score", "weight"]][:size].to_dict('record')
gmkv_tag_score2_sum = tag_score_sum[["tag2", "tag_score"]][:size].to_dict('record') gmkv_tag_score2_sum = tag_score_sum[["tag2", "tag_score"]][:size].to_dict('record')
gmkv_tag_score2_sum_dict = {i["tag2"]: i["tag_score"] for i in gmkv_tag_score2_sum} gmkv_tag_score2_sum_dict = {i["tag2"]: i["tag_score"] for i in gmkv_tag_score2_sum}
# 写gmkv
gm_kv_cli = redis.Redis(host="172.16.40.135", port=5379, db=2, socket_timeout=2000) # 写redis
cl_id_portrait_key = "user:service_portrait_tags:cl_id:" + str(cl_id)
tag_id_list_json = json.dumps(gmkv_tag_score_sum)
gm_kv_cli.set(cl_id_portrait_key, tag_id_list_json)
gm_kv_cli.expire(cl_id_portrait_key, time=30 * 24 * 60 * 60)
redis
redis_client = redis.StrictRedis.from_url('redis://:ReDis!GmTx*0aN9@172.16.40.173:6379') redis_client = redis.StrictRedis.from_url('redis://:ReDis!GmTx*0aN9@172.16.40.173:6379')
cl_id_portrait_key2 = "user:service_portrait_tags2:cl_id:" + str(cl_id) cl_id_portrait_key2 = "user:service_portrait_tags2:cl_id:" + str(cl_id)
# 如果画像的tag个数小于5,则补充热搜词 # 如果画像的tag个数小于5,则补充热搜词
...@@ -137,7 +131,6 @@ def get_user_service_portrait(cl_id, all_word_tags, all_tag_tag_type, all_3tag_2 ...@@ -137,7 +131,6 @@ def get_user_service_portrait(cl_id, all_word_tags, all_tag_tag_type, all_3tag_2
if __name__ == '__main__': if __name__ == '__main__':
try:
db_jerry_test = pymysql.connect(host='172.16.40.170', port=4000, user='root', passwd='3SYz54LS9#^9sBvC', db_jerry_test = pymysql.connect(host='172.16.40.170', port=4000, user='root', passwd='3SYz54LS9#^9sBvC',
db='jerry_test', charset='utf8') db='jerry_test', charset='utf8')
cur_jerry_test = db_jerry_test.cursor() cur_jerry_test = db_jerry_test.cursor()
...@@ -218,6 +211,3 @@ if __name__ == '__main__': ...@@ -218,6 +211,3 @@ if __name__ == '__main__':
device_ids_lst_rdd = spark.sparkContext.parallelize(device_ids_lst, numSlices=1000) 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 = 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() result.collect()
except Exception as e:
send_email("dist_update_user_portrait_service", "dist_update_user_portrait_service", "dist_update_user_portrait_service")
\ No newline at end of file
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