Merge branch 'dev_david' of anweiguo/algorithm_platform into dev_awg

models_processing/model_tf/tf_bp_pre.py

@@ -71,7 +71,8 @@ def model_prediction_bp():
         if int(args.get('algorithm_test', 0)):
             pre_data[args['model_name']] = res[:len(pre_data)]
             pre_data.rename(columns={args['col_time']: 'dateTime'}, inplace=True)
-            pre_data = pre_data[['dateTime', 'farm_id', args['target'], args['model_name'], 'dq']]
+            compare_dq = args.get('compare_dq', 'dq').split(',')
+            pre_data = pre_data[['dateTime', 'farm_id', args['target'], args['model_name']] + compare_dq]
             pre_data = pre_data.melt(id_vars=['dateTime', 'farm_id', args['target']], var_name='model', value_name='power_forecast')
             res_cols = ['dateTime', 'power_forecast', 'farm_id', args['target'], 'model']
             if 'howLongAgo' in args:

models_processing/model_tf/tf_cnn_pre.py

@@ -72,7 +72,8 @@ def model_prediction_cnn():
         if int(args.get('algorithm_test', 0)):
             pre_data[args['model_name']] = res[:len(pre_data)]
             pre_data.rename(columns={args['col_time']: 'dateTime'}, inplace=True)
-            pre_data = pre_data[['dateTime', 'farm_id', args['target'], args['model_name'], 'dq']]
+            compare_dq = args.get('compare_dq', 'dq').split(',')
+            pre_data = pre_data[['dateTime', 'farm_id', args['target'], args['model_name']] + compare_dq]
             pre_data = pre_data.melt(id_vars=['dateTime', 'farm_id', args['target']], var_name='model', value_name='power_forecast')
             res_cols = ['dateTime', 'power_forecast', 'farm_id', args['target'], 'model']
             if 'howLongAgo' in args:

models_processing/model_tf/tf_lstm2_pre.py

@@ -70,7 +70,8 @@ def model_prediction_lstm2():
             pre_data = pre_data.iloc[(args['time_series']-1)*dh.opt.Model["time_step"]:]
             pre_data[args['model_name']] = res[:len(pre_data)]
             pre_data.rename(columns={args['col_time']: 'dateTime'}, inplace=True)
-            pre_data = pre_data[['dateTime', 'farm_id', args['target'], args['model_name'], 'dq']]
+            compare_dq = args.get('compare_dq', 'dq').split(',')
+            pre_data = pre_data[['dateTime', 'farm_id', args['target'], args['model_name']] + compare_dq]
             pre_data = pre_data.melt(id_vars=['dateTime', 'farm_id', args['target']], var_name='model', value_name='power_forecast')
             res_cols = ['dateTime', 'power_forecast', 'farm_id', args['target'], 'model']
             if 'howLongAgo' in args:

models_processing/model_tf/tf_lstm3_pre.py

@@ -74,7 +74,8 @@ def model_prediction_lstm3():
             pre_data = pre_data.iloc[dh.opt.Model["time_step"]:]
             pre_data[args['model_name']] = res[:len(pre_data)]
             pre_data.rename(columns={args['col_time']: 'dateTime'}, inplace=True)
-            pre_data = pre_data[['dateTime', 'farm_id', args['target'], args['model_name'], 'dq']]
+            compare_dq = args.get('compare_dq', 'dq').split(',')
+            pre_data = pre_data[['dateTime', 'farm_id', args['target'], args['model_name']] + compare_dq]
             pre_data = pre_data.melt(id_vars=['dateTime', 'farm_id', args['target']], var_name='model', value_name='power_forecast')
             res_cols = ['dateTime', 'power_forecast', 'farm_id', args['target'], 'model']
             if 'howLongAgo' in args:

models_processing/model_tf/tf_lstm_pre.py

@@ -70,7 +70,8 @@ def model_prediction_lstm():
         if int(args.get('algorithm_test', 0)):
             pre_data[args['model_name']] = res[:len(pre_data)]
             pre_data.rename(columns={args['col_time']: 'dateTime'}, inplace=True)
-            pre_data = pre_data[['dateTime', 'farm_id', args['target'], args['model_name'], 'dq']]
+            compare_dq = args.get('compare_dq', 'dq').split(',')
+            pre_data = pre_data[['dateTime', 'farm_id', args['target'], args['model_name']]+compare_dq]
             pre_data = pre_data.melt(id_vars=['dateTime', 'farm_id', args['target']], var_name='model', value_name='power_forecast')
             res_cols = ['dateTime', 'power_forecast', 'farm_id', args['target'], 'model']
             if 'howLongAgo' in args:

models_processing/model_tf/tf_lstm_zone_pre.py

@@ -70,7 +70,8 @@ def model_prediction_lstm():
         if int(args.get('algorithm_test', 0)):
             pre_data[args['model_name']] = res[:len(pre_data)]
             pre_data.rename(columns={args['col_time']: 'dateTime'}, inplace=True)
-            pre_data = pre_data[['dateTime', 'farm_id', args['target'], args['model_name'], 'dq']]
+            compare_dq = args.get('compare_dq', 'dq').split(',')
+            pre_data = pre_data[['dateTime', 'farm_id', args['target'], args['model_name']] + compare_dq]
             pre_data = pre_data.melt(id_vars=['dateTime', 'farm_id', args['target']], var_name='model', value_name='power_forecast')
             res_cols = ['dateTime', 'power_forecast', 'farm_id', args['target'], 'model']
             if 'howLongAgo' in args:

models_processing/model_tf/tf_multi_nwp_pre.py

@@ -70,7 +70,8 @@ def model_prediction_lstm():
         if int(args.get('algorithm_test', 0)):
             pre_data[args['model_name']] = res[:len(pre_data)]
             pre_data.rename(columns={args['col_time']: 'dateTime'}, inplace=True)
-            pre_data = pre_data[['dateTime', 'farm_id', args['target'], args['model_name'], 'dq']]
+            compare_dq = args.get('compare_dq', 'dq').split(',')
+            pre_data = pre_data[['dateTime', 'farm_id', args['target'], args['model_name']] + compare_dq]
             pre_data = pre_data.melt(id_vars=['dateTime', 'farm_id', args['target']], var_name='model', value_name='power_forecast')
             res_cols = ['dateTime', 'power_forecast', 'farm_id', args['target'], 'model']
             if 'howLongAgo' in args:

models_processing/model_tf/tf_test_pre.py

@@ -71,7 +71,8 @@ def model_prediction_test():
         if int(args.get('algorithm_test', 0)):
             pre_data[args['model_name']] = res[:len(pre_data)]
             pre_data.rename(columns={args['col_time']: 'dateTime'}, inplace=True)
-            pre_data = pre_data[['dateTime', 'farm_id', args['target'], args['model_name'], 'dq']]
+            compare_dq = args.get('compare_dq', 'dq').split(',')
+            pre_data = pre_data[['dateTime', 'farm_id', args['target'], args['model_name']] + compare_dq]
             pre_data = pre_data.melt(id_vars=['dateTime', 'farm_id', args['target']], var_name='model', value_name='power_forecast')
             res_cols = ['dateTime', 'power_forecast', 'farm_id', args['target'], 'model']
             if 'howLongAgo' in args:

models_processing/model_tf/tf_transformer_pre.py

@@ -70,7 +70,8 @@ def model_prediction_transformer():
         if int(args.get('algorithm_test', 0)):
             pre_data[args['model_name']] = res[:len(pre_data)]
             pre_data.rename(columns={args['col_time']: 'dateTime'}, inplace=True)
-            pre_data = pre_data[['dateTime', 'farm_id', args['target'], args['model_name'], 'dq']]
+            compare_dq = args.get('compare_dq', 'dq').split(',')
+            pre_data = pre_data[['dateTime', 'farm_id', args['target'], args['model_name']]+compare_dq]
             pre_data = pre_data.melt(id_vars=['dateTime', 'farm_id', args['target']], var_name='model', value_name='power_forecast')
             res_cols = ['dateTime', 'power_forecast', 'farm_id', args['target'], 'model']
             if 'howLongAgo' in args: