def test_invalid_aggfuncs(forecasters, aggfunc):
"""Check if invalid aggregation functions return Error."""
y = make_forecasting_problem()
forecaster = EnsembleForecaster(forecasters=forecasters, aggfunc=aggfunc)
forecaster.fit(y, fh=[1, 2])
with pytest.raises(ValueError, match=r"not recognized"):
forecaster.predict()
def test_avg_mean(forecasters):
"""Assert `mean` aggfunc returns the same values as `average` with equal weights."""
y = make_forecasting_problem()
forecaster = EnsembleForecaster(forecasters)
forecaster.fit(y, fh=[1, 2, 3])
mean_pred = forecaster.predict()
forecaster_1 = EnsembleForecaster(forecasters, aggfunc="mean", weights=[1, 1])
forecaster_1.fit(y, fh=[1, 2, 3])
avg_pred = forecaster_1.predict()
pd.testing.assert_series_equal(mean_pred, avg_pred)
def test_aggregation_unweighted(forecasters, aggfunc):
"""Assert aggfunc returns the correct values."""
y = make_forecasting_problem()
forecaster = EnsembleForecaster(forecasters=forecasters, aggfunc=aggfunc)
forecaster.fit(y, fh=[1, 2, 3])
actual_pred = forecaster.predict()
predictions = []
_aggfunc = VALID_AGG_FUNCS[aggfunc]["unweighted"]
for _, forecaster in forecasters:
f = forecaster
f.fit(y)
f_pred = f.predict(fh=[1, 2, 3])
predictions.append(f_pred)
predictions = pd.DataFrame(predictions).T
expected_pred = predictions.apply(func=_aggfunc, axis=1)
pd.testing.assert_series_equal(actual_pred, expected_pred)
def run_sktimes(dept_id, store_id):
# create timeseries for fbprophet
ts = CreateTimeSeries(dept_id, store_id)
# sktime ensembler
forecaster = EnsembleForecaster([
('naive_ses', NaiveForecaster(sp=28, strategy="seasonal_last")),
('naive', NaiveForecaster(strategy="last")),
('theta_ses', ThetaForecaster(sp=28)), ('theta', ThetaForecaster()),
("exp_ses", ExponentialSmoothing(seasonal="additive", sp=28)),
("exp_damped",
ExponentialSmoothing(trend='additive',
damped=True,
seasonal="additive",
sp=28))
])
forecaster.fit(ts.y + 1)
y_pred = forecaster.predict(np.arange(1, 29))
return np.append(np.array([dept_id, store_id]), y_pred - 1)
def test_aggregation_weighted(forecasters, aggfunc, weights):
"""Assert weighted aggfunc returns the correct values."""
y = make_forecasting_problem()
forecaster = EnsembleForecaster(
forecasters=forecasters, aggfunc=aggfunc, weights=weights
)
forecaster.fit(y, fh=[1, 2, 3])
actual_pred = forecaster.predict()
predictions = []
for _, forecaster in forecasters:
f = forecaster
f.fit(y)
f_pred = f.predict(fh=[1, 2, 3])
predictions.append(f_pred)
predictions = pd.DataFrame(predictions).T
_aggfunc = VALID_AGG_FUNCS[aggfunc]["weighted"]
expected_pred = pd.Series(
_aggfunc(predictions, axis=1, weights=np.array(weights)),
index=predictions.index,
)
# expected_pred = predictions.apply(func=_aggfunc, axis=1, weights=weights)
pd.testing.assert_series_equal(actual_pred, expected_pred)
def test_aggregation_weighted(forecasters, aggfunc, weights):
"""Assert weighted aggfunc returns the correct values."""
y = make_forecasting_problem()
forecaster = EnsembleForecaster(forecasters=forecasters,
aggfunc=aggfunc,
weights=weights)
forecaster.fit(y, fh=[1, 2, 3])
actual_pred = forecaster.predict()
predictions = []
for _, forecaster in forecasters:
f = forecaster
f.fit(y)
f_pred = f.predict(fh=[1, 2, 3])
predictions.append(f_pred)
predictions = pd.DataFrame(predictions)
if aggfunc == "mean":
func = np.average
else:
func = gmean
expected_pred = predictions.apply(func=func, axis=0, weights=weights)
pd.testing.assert_series_equal(actual_pred, expected_pred)
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), '%')