修改rerank文件每次写入的数量

eda/esmm/Model_pipline/rerank_esmm.py

@@ -204,9 +204,6 @@ if __name__ == "__main__":
             df = df.rename(columns={0: "device_id", 1: "city_id",2:"native_queue",
                                     3:"nearby_queue",4:"nation_queue",5:"megacity_queue",6:"time"})
 
-
-            print("df numbers")
-            print(df.shape[0])
             to_data_base(df)
 
 

monitor.py

@@ -200,8 +200,6 @@ def make_data(device_id,city_id,key_head):
     r.hset(name=key, key="nation_queue", value=nation)
     r.hset(name=key, key="megacity_queue", value=megacity)
     print(r.hgetall(key))
-
-if __name__ == "__main__":
     native = ",".join([str(i) for i in (range(100, 102))])
     nearby = ",".join([str(i) for i in (range(102, 106))])
     nation = ",".join([str(i) for i in (range(106, 110))])
@@ -209,10 +207,35 @@ if __name__ == "__main__":
     key_head = "device_diary_queue_rerank:device_id:"
     # key_head = "device_diary_queue:device_id:"
     device_id = "868663038800471"
-    make_data(device_id, "beijing", key_head)
+    # make_data(device_id, "beijing", key_head)
     # device_id = "868663038800476"
     city_id = "beijing"
 
+if __name__ == "__main__":
+    users_list = list(range(1,90))
+    n = 3
+    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(uid_city)
+
+        if len(total_samples) > 0:
+            df = pd.DataFrame(total_samples)
+            df = df.rename(columns={0: "device_id"})
+
+            print("df numbers")
+            print(df.shape[0])
+            # to_data_base(df)
+