debug

ad_feature_process.py

@@ -7,7 +7,7 @@ features = [
     'mid',
     'videoid',
     'ad_mid',
-    'share_videoid'
+    'share_videoid',
     'mid_preview_count_30day',
     'mid_view_count_30day',
     'mid_view_count_pv_30day',
@@ -60,7 +60,7 @@ train_feature = [
     'video_share_rate_pv_30day',
     'video_return_rate_30day',
     'ad_status',
-    'share_status'
+    'share_status',
 ]
 
 
@@ -79,7 +79,10 @@ def get_feature_data(project, table, features, dt):
 
 def daily_data_process(project, table, features, dt, app_type):
     """每日特征处理"""
+    print('step 1: get feature data')
     feature_initial_df = get_feature_data(project=project, table=table, features=features, dt=dt)
+    print(f"feature_initial_df shape: {feature_initial_df.shape}")
+    print('step 2: process')
     feature_initial_df['apptype'] = feature_initial_df['apptype'].astype(int)
     feature_df = feature_initial_df[feature_initial_df['apptype'] == app_type]
     # 增加此次是否有广告字段 'ad_status' 1: 有广告, 0: 无广告
@@ -124,11 +127,23 @@ def daily_data_process(project, table, features, dt, app_type):
     ]
     for column_name in type_float_columns:
         feature_df[column_name].astype(float)
+    print(f"feature_df shape: {feature_df.shape}")
     # 获取所需的字段
+    print('step 3: get train_df')
     train_df = feature_df[train_feature]
+    print(f"train_df shape: {train_df.shape}")
     return train_df
 
 
+if __name__ == '__main__':
+    project = 'loghubods'
+    table = 'admodel_data_train'
+    dt = '20230725'
+    df = daily_data_process(project=project, table=table, features=features, dt=dt, app_type=0)
+    print(df.shape)
+    print(df.columns)
+    df.to_csv(f'./data/{dt}.csv')
+
 
 
 

config.py

@@ -2301,8 +2301,8 @@ class ProductionConfig(BaseConfig):
 
 def set_config():
     # 获取环境变量 ROV_OFFLINE_ENV
-    env = os.environ.get('ROV_OFFLINE_ENV')
-    # env = 'dev'
+    # env = os.environ.get('ROV_OFFLINE_ENV')
+    env = 'dev'
     if env is None:
         # log_.error('ENV ERROR: is None!')
         return