update

eda/smart_rank/dist_update_user_portrait_service.py

@@ -200,7 +200,7 @@ def get_action_tag_count(df, action_time):
         print(e)
 
 
-def get_user_service_portrait(cl_id, all_word_tags, all_tag_tag_type, all_3tag_2tag):
+def get_user_service_portrait(cl_id, all_word_tags, all_tag_tag_type, all_3tag_2tag, size=10):
     try:
         db_jerry_test = pymysql.connect(host='172.16.40.158', port=4000, user='root', passwd='3SYz54LS9#^9sBvC',
                                         db='jerry_test', charset='utf8')
@@ -248,7 +248,7 @@ def get_user_service_portrait(cl_id, all_word_tags, all_tag_tag_type, all_3tag_2
                         compute_validate(x.days_diff_now)/get_action_tag_count(user_df_service, x.time)))), axis=1)
             tag_score_sum = user_df_service.groupby(by=["tag2", "tag2_type"]).agg({'tag_score': sum}).reset_index().sort_values(by=["tag_score"],ascending=False)
             tag_score_sum['weight'] = 100 * tag_score_sum['tag_score'] / tag_score_sum['tag_score'].sum()
-            gmkv_tag_score_sum = tag_score_sum[["tag2", "tag_score", "weight"]].to_dict('record')
+            gmkv_tag_score_sum = tag_score_sum[["tag2", "tag_score", "weight"]][:size].to_dict('record')
             # 写gmkv
             gm_kv_cli = redis.Redis(host="172.16.40.135", port=5379, db=2, socket_timeout=2000)
             cl_id_portrait_key = "user:service_portrait_tags:cl_id:" + str(cl_id)