用户画像冷启动

eda/smart_rank/dist_update_user_portrait_service.py

@@ -20,6 +20,26 @@ from pyspark.sql.functions import concat_ws
 from tool import *
 
 
+def get_hot_search_words_tag():
+    try:
+        hot_search = """
+                        SELECT a.keywords,
+                               b.id,
+                               b.tag_type
+                        FROM api_hot_search_words a
+                        LEFT JOIN api_tag b ON a.keywords=b.name
+                        WHERE a.is_delete=0
+                          AND b.tag_type+0<'4'+0
+                          AND b.is_online=1
+                        ORDER BY a.sorted DESC LIMIT 10
+                        """
+        mysql_results = get_data_by_mysql('172.16.30.141', 3306, 'work', 'BJQaT9VzDcuPBqkd', 'zhengxing', hot_search)
+        return mysql_results
+    except Exception as e:
+        print(e)
+        return []
+
+
 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',
@@ -140,6 +160,21 @@ if __name__ == '__main__':
         # 3级tag对应的2级tag
         all_3tag_2tag = get_all_3tag_2tag()
 
+        # 画像冷启动
+        hot_search_words = get_hot_search_words_tag()
+        hot_search_words_portrait = list()
+        for tag_info in hot_search_words:
+            tmp = dict()
+            tmp["tag_score"] = 10
+            tmp["weight"] = 10
+            tmp["tag2"] = tag_info["id"]
+            hot_search_words_portrait.append(tmp)
+        gm_kv_cli = redis.Redis(host="172.16.40.135", port=5379, db=2, socket_timeout=2000)
+        hot_search_words_portrait_portrait_key = "user:service_coldstart_tags:cl_id:"
+        hot_search_words_portrait_json = json.dumps(hot_search_words_portrait)
+        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)
+
         # rdd
         sparkConf = SparkConf().set("spark.hive.mapred.supports.subdirectories", "true") \
             .set("spark.hadoop.mapreduce.input.fileinputformat.input.dir.recursive", "true") \