Spaces:
Runtime error
Runtime error
| import pandas as pd | |
| from xgboost import XGBRegressor | |
| from sktime.forecasting.compose import make_reduction | |
| from statsmodels.tsa.tsatools import freq_to_period | |
| from sklearn.model_selection import train_test_split | |
| from sktime.forecasting.base import ForecastingHorizon | |
| from sktime.performance_metrics.forecasting import mean_absolute_percentage_error | |
| class MultivariateForecasting(): | |
| def __init__( | |
| self, | |
| n_predict: int, | |
| data: pd.DataFrame, | |
| window_length: 10 | |
| ): | |
| ''' | |
| data: data must contains datetime column, and y column as target. Everything else will be considered as exogenous data | |
| n_predict: how may future values are expected to produce | |
| window_length default to 10 following sktime's default setting | |
| test_size : test size is same size as n predict | |
| ''' | |
| self.data = data.copy() | |
| self.n_predict = n_predict | |
| # Set datetime as the index | |
| self.data.set_index('datetime', inplace=True) | |
| self.data.index = pd.to_datetime(self.data.index) | |
| self.exog = self.data.drop(columns=['y']).reset_index(drop=True) | |
| self.window_length = window_length | |
| # Keep n_predict rows of latest exog data for prediction use | |
| self.exog_train = self.exog[:- self.n_predict] | |
| self.exog_pred = self.exog[-self.n_predict:] | |
| # If we need to use n_predict rows of exog data for prediction, we are going to remove n_predict rows of y historical data | |
| # This will make sure the shape of 2 data consistent | |
| self.y = self.data['y'][self.n_predict:] | |
| # test size is same size as the forecast window_length | |
| # self.X_train = self.X[:-self.window_length] | |
| # self.X_test = self.X[-self.window_length:] | |
| # self.y_train = self.y[:-self.window_length] | |
| # self.y_test = self.y[-self.window_length:] | |
| # self.fh_test = ForecastingHorizon( | |
| # self.y_test.index, | |
| # is_relative=False) | |
| # self.fh = ForecastingHorizon( | |
| # self.exog.index, | |
| # is_relative=False) | |
| self.models = {} | |
| def train_xgboost(self): | |
| regressor = XGBRegressor( | |
| objective='reg:squarederror', | |
| random_state=42) | |
| forecaster = make_reduction( | |
| regressor, strategy='recursive', | |
| window_length=self.window_length) | |
| forecaster.fit(y=self.y_train, X=self.X_train) | |
| y_pred = forecaster.predict(fh=self.fh_test, X=self.X_test) | |
| self.models['xgboost'] = {} | |
| self.models['xgboost']['mape'] = mean_absolute_percentage_error( | |
| self.y_test, y_pred, symmetric=False) | |
| self.models['xgboost']['test'] = y_pred | |
| forecaster.fit(y=self.y, X=self.X) | |
| self.models['xgboost']['forecast'] = forecaster.predict( | |
| fh=self.fh, X=self.exog) | |