|
|
@@ -195,10 +195,10 @@ class DataHandler(object):
|
|
|
train_scaler = MinMaxScaler(feature_range=(0, 1))
|
|
|
target_scaler = MinMaxScaler(feature_range=(0, 1))
|
|
|
# 标准化特征和目标
|
|
|
- scaled_train_data = train_scaler.fit_transform(train_data_cleaned[features])
|
|
|
+ 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]
|
|
|
- train_data_cleaned[features] = scaled_train_data
|
|
|
+ train_data_cleaned[self.opt.features] = scaled_train_data
|
|
|
train_data_cleaned[[target]] = scaled_target
|
|
|
# 3.缺值补值
|
|
|
train_datas = self.fill_train_data(train_data_cleaned, col_time)
|
|
|
@@ -212,10 +212,10 @@ class DataHandler(object):
|
|
|
|
|
|
if bp_data:
|
|
|
train_data = pd.concat(train_datas, axis=0)
|
|
|
- train_x, valid_x, train_y, valid_y = self.train_valid_split(train_data[features].values, train_data[target].values, valid_rate=self.opt.Model["valid_data_rate"], shuffle=self.opt.Model['shuffle_train_data'])
|
|
|
+ train_x, valid_x, train_y, valid_y = self.train_valid_split(train_data[self.opt.features].values, train_data[target].values, valid_rate=self.opt.Model["valid_data_rate"], shuffle=self.opt.Model['shuffle_train_data'])
|
|
|
train_x, valid_x, train_y, valid_y = np.array(train_x), np.array(valid_x), np.array(train_y), np.array(valid_y)
|
|
|
else:
|
|
|
- train_x, valid_x, train_y, valid_y = self.get_train_data(train_datas, col_time, features, target)
|
|
|
+ train_x, valid_x, train_y, valid_y = self.get_train_data(train_datas, col_time, self.opt.features, target)
|
|
|
return train_x, train_y, valid_x, valid_y, scaled_train_bytes, scaled_target_bytes, scaled_cap
|
|
|
|
|
|
def pre_data_handler(self, data, feature_scaler, bp_data=False):
|
David