用户画像重排增加if判断

eda/esmm/Model_pipline/rerank_esmm.py

@@ -170,33 +170,35 @@ def to_data_base(df):
 
 
 if __name__ == "__main__":
-    users_list = get_esmm_users()[:2000]
-    # TODO 删除上面的2000
+    users_list = get_esmm_users()
     print("user number")
     print(len(users_list))
 
-    name_tag = get_searchworlds_to_tagid()
-    n = 500
-    split_users_list = [users_list[i:i + n] for i in range(0, len(users_list), n)]
-    for child_users_list in split_users_list:
-        total_samples = list()
-        for uid_city in child_users_list:
-            tag_list = get_user_profile(uid_city[0])
-            queues = get_queues(uid_city[0], uid_city[1])
-            if len(queues) > 0 and len(tag_list) > 0:
-                new_native = tag_boost(queues[0], tag_list)
-                new_nearby = tag_boost(queues[1], tag_list)
-
-                insert_time = str(datetime.datetime.now().strftime('%Y%m%d%H%M'))
-                sample = [uid_city[0], uid_city[1], new_native, new_nearby, queues[2], queues[3], insert_time]
-                total_samples.append(sample)
-
-        if len(total_samples) > 0:
-            df = pd.DataFrame(total_samples)
-            df = df.rename(columns={0: "device_id", 1: "city_id",2:"native_queue",
-                                    3:"nearby_queue",4:"nation_queue",5:"megacity_queue",6:"time"})
-
-            to_data_base(df)
+    if len(users_list) > 0:
+        name_tag = get_searchworlds_to_tagid()
+        n = 500
+        split_users_list = [users_list[i:i + n] for i in range(0, len(users_list), n)]
+        for child_users_list in split_users_list:
+            total_samples = list()
+            for uid_city in child_users_list:
+                tag_list = get_user_profile(uid_city[0])
+                queues = get_queues(uid_city[0], uid_city[1])
+                if len(queues) > 0 and len(tag_list) > 0:
+                    new_native = tag_boost(queues[0], tag_list)
+                    new_nearby = tag_boost(queues[1], tag_list)
+
+                    insert_time = str(datetime.datetime.now().strftime('%Y%m%d%H%M'))
+                    sample = [uid_city[0], uid_city[1], new_native, new_nearby, queues[2], queues[3], insert_time]
+                    total_samples.append(sample)
+
+            if len(total_samples) > 0:
+                df = pd.DataFrame(total_samples)
+                df = df.rename(columns={0: "device_id", 1: "city_id",2:"native_queue",
+                                        3:"nearby_queue",4:"nation_queue",5:"megacity_queue",6:"time"})
+
+                to_data_base(df)
+    else:
+        print("没有获取到用户")