Selaa lähdekoodia

generate label for mysql

罗俊辉 1 vuosi sitten
vanhempi
commit
65da77c002
1 muutettua tiedostoa jossa 2 lisäystä ja 4 poistoa
  1. 2 4
      process_data.py

+ 2 - 4
process_data.py

@@ -11,7 +11,6 @@ import time
 
 from tqdm import tqdm
 import jieba.analyse
-from concurrent.futures.thread import ThreadPoolExecutor
 
 sys.path.append(os.getcwd())
 
@@ -141,7 +140,7 @@ class DataProcessor(object):
             label_obj = label_info.get(label_dt, {}).get(video_id)
             if label_obj:
                 label = int(label_obj["total_return"]) if label_obj["total_return"] else 0
-                print(label)
+                # print(label)
             else:
                 label = 0
             return label, label_dt
@@ -161,11 +160,10 @@ class DataProcessor(object):
             # print(insert_sql)
             self.client_spider.update(insert_sql)
 
-        select_sql = "SELECT video_id, hour_dt_str FROM lightgbm_data where label = 0 and hour_dt_str < '20240327';"
+        select_sql = "SELECT video_id, hour_dt_str FROM lightgbm_data where label is NULL and hour_dt_str < '20240327';"
         init_data_tuple = self.client_spider.select(select_sql)
         init_list = list(init_data_tuple)
         for item in tqdm(init_list):
-            # print(item)
             process_info(item)
         #     time.sleep(0.5)
         # with ThreadPoolExecutor(max_workers=8) as Pool: