改变画像的数据存储格式

eda/smart_rank/dist_update_user_portrait_service.py

@@ -109,12 +109,20 @@ def get_user_service_portrait(cl_id, all_word_tags, all_tag_tag_type, all_3tag_2
                 ), axis=1
             )
             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_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)
             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)
+
+            cl_id_portrait_key2 = "user:service_portrait_tags2:cl_id:" + str(cl_id)
+            tag_id_list_json2 = json.dumps(gmkv_tag_score2_sum_dict)
+            gm_kv_cli.set(cl_id_portrait_key2, tag_id_list_json2)
+            gm_kv_cli.expire(cl_id_portrait_key2, time=30 * 24 * 60 * 60)
+
             # 写tidb，redis同步
             stat_date = datetime.datetime.today().strftime('%Y-%m-%d')
             replace_sql = """replace into user_service_portrait_tags (stat_date, cl_id, tag_list) values("{stat_date}","{cl_id}","{tag_list}")"""\
@@ -175,6 +183,13 @@ if __name__ == '__main__':
         gm_kv_cli.set(hot_search_words_portrait_portrait_key, hot_search_words_portrait_json)
         gm_kv_cli.expire(hot_search_words_portrait_portrait_key, time=30 * 24 * 60 * 60)
 
+        hot_search_words_portrait_portrait_key2 = "user:service_coldstart_tags2"
+        hot_search_words_portrait_dict = {i["id"]: 10 for i in hot_search_words}
+        hot_search_words_portrait_json2 = json.dumps(hot_search_words_portrait_dict)
+        gm_kv_cli.set(hot_search_words_portrait_portrait_key2, hot_search_words_portrait_json2)
+        gm_kv_cli.expire(hot_search_words_portrait_portrait_key2, time=30 * 24 * 60 * 60)
+
+
         # rdd
         sparkConf = SparkConf().set("spark.hive.mapred.supports.subdirectories", "true") \
             .set("spark.hadoop.mapreduce.input.fileinputformat.input.dir.recursive", "true") \