计算匹配度的时候，用户log限制在该用户下单之前

eda/smart_rank/evaluation_metrics.py

@@ -31,7 +31,7 @@ def setup_logger(logger_name, log_file, level=logging.INFO):
     my_log.addHandler(stream_handler)
 
 
-def get_user_service_portrait_not_alipay(cl_id, all_word_tags, all_tag_tag_type, all_3tag_2tag, size=10):
+def get_user_service_portrait_not_alipay(cl_id, all_word_tags, all_tag_tag_type, pay_time, all_3tag_2tag, size=10):
     """
     :param cl_id:
     :param all_word_tags:
@@ -44,11 +44,10 @@ def get_user_service_portrait_not_alipay(cl_id, all_word_tags, all_tag_tag_type,
         db_jerry_test = pymysql.connect(host='172.16.40.158', port=4000, user='root', passwd='3SYz54LS9#^9sBvC',
                                         db='jerry_test', charset='utf8')
         cur_jerry_test = db_jerry_test.cursor()
-        yesterday = get_yesterday_start_timestamp()
         # 用户的非搜索、支付的行为
         user_df_service_sql = "select time,cl_id,score_type,tag_id,tag_referrer,action from user_new_tag_log " \
-                              "where cl_id ='{cl_id}' and time < {yesterday} and action not in " \
-                              "('api/settlement/alipay_callback','do_search')".format(cl_id=cl_id, yesterday=yesterday)
+                              "where cl_id ='{cl_id}' and time < {pay_time} and action not in " \
+                              "('api/settlement/alipay_callback','do_search')".format(cl_id=cl_id, pay_time=pay_time)
         cur_jerry_test.execute(user_df_service_sql)
         data = list(cur_jerry_test.fetchall())
         if data:
@@ -58,8 +57,8 @@ def get_user_service_portrait_not_alipay(cl_id, all_word_tags, all_tag_tag_type,
             user_df_service = pd.DataFrame(columns=["time", "cl_id", "score_type", "tag_id", "tag_referrer", "action"])
         # 用户的搜索行为
         user_df_search_sql = "select time,cl_id,score_type,tag_id,tag_referrer,action from user_new_tag_log " \
-                             "where cl_id ='{cl_id}' and time < {yesterday} and " \
-                             "action = 'do_search'".format(cl_id=cl_id, yesterday=yesterday)
+                             "where cl_id ='{cl_id}' and time < {pay_time} and " \
+                             "action = 'do_search'".format(cl_id=cl_id, pay_time=pay_time)
         cur_jerry_test.execute(user_df_search_sql)
         data_search = list(cur_jerry_test.fetchall())
         db_jerry_test.close()
@@ -120,7 +119,7 @@ def get_user_service_portrait_not_alipay(cl_id, all_word_tags, all_tag_tag_type,
         return list(), dict()
 
 
-def get_user_service_portrait_not_alipay2(cl_id, all_word_tags, all_tag_tag_type, all_3tag_2tag, size=10):
+def get_user_service_portrait_not_alipay2(cl_id, all_word_tags, all_tag_tag_type, pay_time, all_3tag_2tag, size=10):
     """
     :param cl_id:
     :param all_word_tags:
@@ -136,8 +135,8 @@ def get_user_service_portrait_not_alipay2(cl_id, all_word_tags, all_tag_tag_type
         yesterday = get_yesterday_start_timestamp()
         # 用户的非搜索、支付的行为
         user_df_service_sql = "select time,cl_id,score_type,tag_id,tag_referrer,action from user_new_tag_log " \
-                              "where cl_id ='{cl_id}' and time < {yesterday} and action not in " \
-                              "('api/settlement/alipay_callback','do_search')".format(cl_id=cl_id, yesterday=yesterday)
+                              "where cl_id ='{cl_id}' and time < {pay_time} and action not in " \
+                              "('api/settlement/alipay_callback','do_search')".format(cl_id=cl_id, pay_time=pay_time)
         cur_jerry_test.execute(user_df_service_sql)
         data = list(cur_jerry_test.fetchall())
         if data:
@@ -147,8 +146,8 @@ def get_user_service_portrait_not_alipay2(cl_id, all_word_tags, all_tag_tag_type
             user_df_service = pd.DataFrame(columns=["time", "cl_id", "score_type", "tag_id", "tag_referrer", "action"])
         # 用户的搜索行为
         user_df_search_sql = "select time,cl_id,score_type,tag_id,tag_referrer,action from user_new_tag_log " \
-                             "where cl_id ='{cl_id}' and time < {yesterday} and " \
-                             "action = 'do_search'".format(cl_id=cl_id, yesterday=yesterday)
+                             "where cl_id ='{cl_id}' and time < {pay_time} and " \
+                             "action = 'do_search'".format(cl_id=cl_id, pay_time=pay_time)
         cur_jerry_test.execute(user_df_search_sql)
         data_search = list(cur_jerry_test.fetchall())
         db_jerry_test.close()
@@ -276,44 +275,49 @@ if __name__ == '__main__':
         # api_order只有用户的user_id，一个user_id对应多个device_id
         # 用户一次可以下多个订单(美购)，一个美购对应多个tag
         sql_order_device_info_yesterday = """
-            SELECT tmp1.user_id,
-                   c.device_id,
-                   tmp1.service_ids,
-                   tmp1.tag_ids
-            FROM
-              (SELECT tmp.user_id,
-                      tmp.service_ids,
-                      tmp.tag_ids,
-                      max(tmp.device_id) device_id_id
-               FROM
-                 (SELECT a.user_id,
-                         a.service_ids,
-                         a.tag_ids,
-                         b.device_id
-                  FROM
-                    (SELECT user_id,
-                            group_concat(DISTINCT `service_id` separator ',') service_ids,
-                            group_concat(DISTINCT `tag_id` separator ',') tag_ids
-                     FROM
-                       (SELECT d.user_id,
-                               d.service_id,
-                               e.tag_id
-                        FROM api_order d
-                        LEFT JOIN api_servicetag e ON d.service_id = e.service_id
-                        LEFT JOIN api_tag f ON e.tag_id = f.id
-                        WHERE d.status=1
-                          AND d.pay_time>'{my_yesterday}'
-                          AND d.pay_time<'{today}'
-                          AND f.tag_type+0 <'4'+0) tmp2 
-                     GROUP BY user_id) a
-                  LEFT JOIN statistic_device_user b ON a.user_id = b.user_id) tmp
-               GROUP BY tmp.user_id) tmp1
-            LEFT JOIN statistic_device c ON tmp1.device_id_id = c.id
-            WHERE c.device_id IS NOT NULL
+                SELECT tmp1.user_id,
+                       c.device_id,
+                       tmp1.service_ids,
+                       tmp1.tag_ids,
+                       tmp1.pay_time
+                FROM
+                  (SELECT tmp.user_id,
+                          tmp.service_ids,
+                          tmp.tag_ids,
+                          tmp.pay_time,
+                          max(tmp.device_id) device_id_id
+                   FROM
+                     (SELECT a.user_id,
+                             a.service_ids,
+                             a.tag_ids,
+                             a.pay_time,
+                             b.device_id
+                      FROM
+                        (SELECT user_id,
+                                max(pay_time) AS pay_time,
+                                group_concat(DISTINCT `service_id` separator ',') service_ids,
+                                group_concat(DISTINCT `tag_id` separator ',') tag_ids
+                         FROM
+                           (SELECT d.user_id,
+                                   d.service_id,
+                                   unix_timestamp(d.pay_time) AS pay_time,
+                                   e.tag_id
+                            FROM api_order d
+                            LEFT JOIN api_servicetag e ON d.service_id = e.service_id
+                            LEFT JOIN api_tag f ON e.tag_id = f.id
+                            WHERE d.status=1
+                              AND d.pay_time>'{my_yesterday}'
+                              AND d.pay_time<'{today}'
+                              AND f.tag_type+0 <'4'+0) tmp2
+                         GROUP BY user_id) a
+                      LEFT JOIN statistic_device_user b ON a.user_id = b.user_id) tmp
+                   GROUP BY tmp.user_id) tmp1
+                LEFT JOIN statistic_device c ON tmp1.device_id_id = c.id
+                WHERE c.device_id IS NOT NULL
             """.format(my_yesterday=my_yesterday, today=my_today)
         mysql_results = get_data_by_mysql('172.16.30.141', 3306, 'work', 'BJQaT9VzDcuPBqkd', 'zhengxing',
                                           sql_order_device_info_yesterday)
-        device_ids_lst = [i["device_id"] for i in mysql_results]
+        device_ids_lst = [(i["device_id"], int(i["pay_time"])) for i in mysql_results]
         all_device_order_tags = {i["device_id"]: [int(tag) for tag in i["tag_ids"].split(",")] for i in mysql_results}
 
         # 获取搜索词及其近义词对应的tag
@@ -336,17 +340,23 @@ if __name__ == '__main__':
         all_device_portrait_result = dict()
         debug_all_device_portrait_result = dict()
         if version == 1:
-            for device in device_ids_lst:
+            for order_info in device_ids_lst:
+                device = order_info[0]
+                pay_time = order_info[1]
                 portrait_result, debug_portrait_result = get_user_service_portrait_not_alipay(device, all_word_tags,
                                                                                               all_tag_tag_type,
-                                                                                              all_3tag_2tag, size=-1)
+                                                                                              pay_time, all_3tag_2tag,
+                                                                                              size=-1)
                 all_device_portrait_result[device] = portrait_result
                 debug_all_device_portrait_result[device] = debug_portrait_result
         elif version == 0:
-            for device in device_ids_lst:
+            for order_info in device_ids_lst:
+                device = order_info[0]
+                pay_time = order_info[1]
                 portrait_result, debug_portrait_result = get_user_service_portrait_not_alipay2(device, all_word_tags,
-                                                                                              all_tag_tag_type,
-                                                                                              all_3tag_2tag, size=-1)
+                                                                                               all_tag_tag_type,
+                                                                                               pay_time, all_3tag_2tag,
+                                                                                               size=-1)
                 all_device_portrait_result[device] = portrait_result
                 debug_all_device_portrait_result[device] = debug_portrait_result
         else: