|
|
@@ -104,8 +104,7 @@ class DataHandler(object):
|
|
|
|
|
|
def fill_pre_data(self, unite):
|
|
|
unite = unite.interpolate(method='linear') # nwp先进行线性填充
|
|
|
- unite = unite.fillna(method='ffill') # 再对超过采样边缘无法填充的点进行二次填充
|
|
|
- unite = unite.fillna(method='bfill')
|
|
|
+ unite = unite.ffill().bfill() # 再对超过采样边缘无法填充的点进行二次填充
|
|
|
return unite
|
|
|
|
|
|
def missing_time_splite(self, df, dt_short, dt_long, col_time):
|
|
|
@@ -197,7 +196,7 @@ class DataHandler(object):
|
|
|
# 标准化特征和目标
|
|
|
scaled_train_data = train_scaler.fit_transform(train_data_cleaned[self.opt.features])
|
|
|
scaled_target = target_scaler.fit_transform(train_data_cleaned[[target]])
|
|
|
- scaled_cap = target_scaler.transform(np.array([[self.opt.cap]]))[0,0]
|
|
|
+ scaled_cap = target_scaler.transform(np.array([[float(self.opt.cap)]]))[0,0]
|
|
|
train_data_cleaned[self.opt.features] = scaled_train_data
|
|
|
train_data_cleaned[[target]] = scaled_target
|
|
|
# 3.缺值补值
|
|
|
@@ -233,13 +232,12 @@ class DataHandler(object):
|
|
|
# features, time_steps, col_time, model_name, col_reserve = str_to_list(args['features']), int(
|
|
|
# args['time_steps']), args['col_time'], args['model_name'], str_to_list(args['col_reserve'])
|
|
|
col_time, features = self.opt.col_time, self.opt.features
|
|
|
- data = data.applymap(lambda x: float(x.to_decimal()) if isinstance(x, Decimal128) else float(x) if isinstance(x, numbers.Number) else x)
|
|
|
+ data = data.map(lambda x: float(x.to_decimal()) if isinstance(x, Decimal128) else float(x) if isinstance(x, numbers.Number) else x)
|
|
|
data = data.sort_values(by=col_time).reset_index(drop=True, inplace=False)
|
|
|
+ pre_data = data[features].copy()
|
|
|
if self.opt.Model['predict_data_fill']:
|
|
|
- data = self.fill_pre_data(data)
|
|
|
- pre_data = data[features]
|
|
|
- scaled_features = feature_scaler.transform(data[features])
|
|
|
- pre_data.loc[:, features] = scaled_features
|
|
|
+ pre_data = self.fill_pre_data(pre_data)
|
|
|
+ pre_data.loc[:, features] = feature_scaler.transform(pre_data)
|
|
|
if bp_data:
|
|
|
pre_x = np.array(pre_data)
|
|
|
else:
|
David