def forecast(self):
from openweatherdata import series_to_list
from sktime.forecasting.theta import ThetaForecaster
import numpy
forecaster = ThetaForecaster(sp=48)
forecaster.fit(self.pd_past5days)
self.pd_predictions = forecaster.predict(numpy.arange(1, 48))
self.predictions = series_to_list(self.pd_predictions)
self.next(self.plot)
def test_forecaster_with_initial_level():
y = np.log1p(load_airline())
y_train, y_test = temporal_train_test_split(y)
fh = np.arange(len(y_test)) + 1
f = ThetaForecaster(initial_level=0.1, sp=12)
f.fit(y_train)
y_pred = f.predict(fh=fh)
np.testing.assert_allclose(y_pred, y_test, rtol=0.05)
def test_predictive_performance_on_airline():
y = np.log1p(load_airline())
y_train, y_test = temporal_train_test_split(y)
fh = np.arange(len(y_test)) + 1
f = ThetaForecaster(sp=12)
f.fit(y_train)
y_pred = f.predict(fh=fh)
# Performance on this particular dataset should be reasonably good.
np.testing.assert_allclose(y_pred, y_test, rtol=0.05)
def test_pred_errors_against_y_test(fh):
y = load_airline()
y_train, y_test = temporal_train_test_split(y)
f = ThetaForecaster()
f.fit(y_train, fh)
y_pred = f.predict(return_pred_int=False)
errors = f._compute_pred_errors(alpha=0.1)
if isinstance(errors, pd.Series):
errors = [errors] # make iterable
y_test = y_test.iloc[check_fh(fh) - 1]
for error in errors:
assert np.all(y_test > y_pred - error)
assert np.all(y_test < y_pred + error)
def test_pred_errors_against_y_test(fh):
y = load_airline()
y_train, y_test = temporal_train_test_split(y)
f = ThetaForecaster()
f.fit(y_train, fh)
y_pred = f.predict(return_pred_int=False)
intervals = f.compute_pred_int(y_pred, [0.1])
y_test = y_test.iloc[check_fh(fh) - 1]
# Performance should be good enough that all point forecasts lie within the
# prediction intervals.
for ints in intervals:
assert np.all(y_test > ints["lower"])
assert np.all(y_test < ints["upper"])
def test_forecaster_with_initial_level():
"""Check prediction performance on airline dataset.
Performance on this dataset should be reasonably good.
Raises
------
AssertionError - if point forecasts do not lie close to the test data
"""
y = np.log1p(load_airline())
y_train, y_test = temporal_train_test_split(y)
fh = np.arange(len(y_test)) + 1
f = ThetaForecaster(initial_level=0.1, sp=12)
f.fit(y_train)
y_pred = f.predict(fh=fh)
np.testing.assert_allclose(y_pred, y_test, rtol=0.05)
def main():
df = datasets.load_airline(
) #Univariate, monthly records from 1949 to 60 (144 records)
y_train, y_test = temporal_train_test_split(
df, test_size=36) #36 months for testing
forecaster = NaiveForecaster(
strategy='seasonal_last', sp=12
) #model strategy: last, mean, seasonal_last. sp=12months (yearly season)
forecaster.fit(y_train) #fit
fh = np.arange(1,
len(y_test) +
1) #forecast horizon: array with the same lenght of y_test
y_pred = forecaster.predict(fh) #pred
forecaster2 = AutoARIMA(sp=12, suppress_warnings=True, trace=1)
forecaster2.fit(y_train)
y_pred2 = forecaster2.predict(fh)
forecaster3 = ExponentialSmoothing(trend='add',
damped='True',
seasonal='multiplicative',
sp=12)
forecaster3.fit(y_train)
y_pred3 = forecaster3.predict(fh)
forecaster4 = ThetaForecaster(sp=12)
forecaster4.fit(y_train)
y_pred4 = forecaster4.predict(fh)
forecaster5 = EnsembleForecaster([
('NaiveForecaster', NaiveForecaster(strategy='seasonal_last', sp=12)),
('AutoARIMA', AutoARIMA(sp=12, suppress_warnings=True)),
('Exp Smoothing',
ExponentialSmoothing(trend='add',
damped='True',
seasonal='multiplicative',
sp=12)), ('Theta', ThetaForecaster(sp=12))
])
forecaster5.fit(y_train)
y_pred5 = forecaster5.predict(fh)
plot_ys(y_train,
y_test,
y_pred,
y_pred2,
y_pred3,
y_pred4,
y_pred5,
labels=[
'Train', 'Test', 'Naive Forecaster', 'AutoARIMA',
'Exp Smoothing', 'Theta', 'Ensemble'
])
plt.xlabel('Months')
plt.ylabel('Number of flights')
plt.title(
'Time series of the number of international flights in function of time'
)
plt.show()
print('SMAPE Error for NaiveForecaster is:',
100 * round(smape_loss(y_test, y_pred), 3), '%')
print('SMAPE Error for AutoARIMA is:',
100 * round(smape_loss(y_test, y_pred2), 3), '%')
print('SMAPE Error for Exp Smoothing is:',
100 * round(smape_loss(y_test, y_pred3), 3), '%')
print('SMAPE Error for Theta is:',
100 * round(smape_loss(y_test, y_pred4), 3), '%')
print('SMAPE Error for Ensemble is:',
100 * round(smape_loss(y_test, y_pred5), 3), '%')
#pip install sktime import numpy as np from sktime.datasets import load_airline from sktime.forecasting.theta import ThetaForecaster from sktime.forecasting.model_selection import temporal_train_test_split from sktime.performance_metrics.forecasting import smape_loss y = load_airline() y_train, y_test = temporal_train_test_split(y) fh = np.arange(1, len(y_test) + 1) # forecasting horizon forecaster = ThetaForecaster(sp=12) # monthly seasonal periodicity forecaster.fit(y_train) y_pred = forecaster.predict(fh) smape_loss(y_test, y_pred)
