def helper_test_models_accuracy(self, series, past_covariates,
min_rmse_model):
# for every model, test whether it predicts the target with a minimum r2 score of `min_rmse`
train_series, test_series = train_test_split(series, 70)
train_past_covariates, _ = train_test_split(past_covariates, 70)
for output_chunk_length in [1, 5]:
for idx, model in enumerate(self.models):
model_instance = model(
lags=12,
lags_past_covariates=2,
output_chunk_length=output_chunk_length,
)
model_instance.fit(series=train_series,
past_covariates=train_past_covariates)
prediction = model_instance.predict(
n=len(test_series),
series=train_series,
past_covariates=past_covariates,
)
current_rmse = rmse(prediction, test_series)
# in case of multi-series take mean rmse
mean_rmse = np.mean(current_rmse)
self.assertTrue(
mean_rmse <= min_rmse_model[idx],
f"{str(model_instance)} model was not able to predict data as well as expected. "
f"A mean rmse score of {mean_rmse} was recorded.",
)
def test_kalman_missing_values(self):
sine = tg.sine_timeseries(
length=100,
value_frequency=0.05) + 0.1 * tg.gaussian_timeseries(length=100)
values = sine.values()
values[20:22] = np.nan
values[28:40] = np.nan
sine_holes = TimeSeries.from_values(values)
sine = TimeSeries.from_values(sine.values())
kf = KalmanFilter(dim_x=2)
kf.fit(sine_holes[-50:]) # fit on the part with no holes
# reconstructruction should succeed
filtered_series = kf.filter(sine_holes, num_samples=100)
# reconstruction error should be sufficiently small
self.assertLess(rmse(filtered_series, sine), 0.1)
def helper_test_models_accuracy(self, model_instance, n, series,
past_covariates, min_rmse):
# for every model, test whether it predicts the target with a minimum r2 score of `min_rmse`
train_series, test_series = train_test_split(series,
pd.Timestamp("20010101"))
train_past_covariates, _ = train_test_split(past_covariates,
pd.Timestamp("20010101"))
model_instance.fit(series=train_series,
past_covariates=train_past_covariates)
prediction = model_instance.predict(n=n,
past_covariates=past_covariates)
current_rmse = rmse(test_series, prediction)
self.assertTrue(
current_rmse <= min_rmse,
f"Model was not able to denoise data. A rmse score of {current_rmse} was recorded.",
)
def test_multiple_ts(self):
lags = 4
lags_past_covariates = 3
model = RegressionModel(lags=lags,
lags_past_covariates=lags_past_covariates)
target_series = tg.linear_timeseries(start_value=0,
end_value=49,
length=50)
past_covariates = tg.linear_timeseries(start_value=100,
end_value=149,
length=50)
past_covariates = past_covariates.stack(
tg.linear_timeseries(start_value=400, end_value=449,
length=50))
target_train, target_test = target_series.split_after(0.7)
past_covariates_train, past_covariates_test = past_covariates.split_after(
0.7)
model.fit(
series=[target_train, target_train + 0.5],
past_covariates=[
past_covariates_train, past_covariates_train + 0.5
],
)
predictions = model.predict(
10,
series=[target_train, target_train + 0.5],
past_covariates=[past_covariates, past_covariates + 0.5],
)
self.assertEqual(len(predictions[0]), 10,
f"Found {len(predictions)} instead")
# multiple TS, both future and past covariates, checking that both covariates lead to better results than
# using a single one (target series = past_cov + future_cov + noise)
np.random.seed(42)
linear_ts_1 = tg.linear_timeseries(start_value=10,
end_value=59,
length=50)
linear_ts_2 = tg.linear_timeseries(start_value=40,
end_value=89,
length=50)
past_covariates = tg.sine_timeseries(length=50) * 10
future_covariates = (
tg.sine_timeseries(length=50, value_frequency=0.015) * 50)
target_series_1 = linear_ts_1 + 4 * past_covariates + 2 * future_covariates
target_series_2 = linear_ts_2 + 4 * past_covariates + 2 * future_covariates
target_series_1_noise = (linear_ts_1 + 4 * past_covariates +
2 * future_covariates +
tg.gaussian_timeseries(std=7, length=50))
target_series_2_noise = (linear_ts_2 + 4 * past_covariates +
2 * future_covariates +
tg.gaussian_timeseries(std=7, length=50))
target_train_1, target_test_1 = target_series_1.split_after(0.7)
target_train_2, target_test_2 = target_series_2.split_after(0.7)
(
target_train_1_noise,
target_test_1_noise,
) = target_series_1_noise.split_after(0.7)
(
target_train_2_noise,
target_test_2_noise,
) = target_series_2_noise.split_after(0.7)
# testing improved denoise with multiple TS
# test 1: with single TS, 2 covariates should be better than one
model = RegressionModel(lags=3, lags_past_covariates=5)
model.fit([target_train_1_noise], [past_covariates])
prediction_past_only = model.predict(
n=len(target_test_1),
series=[target_train_1_noise, target_train_2_noise],
past_covariates=[past_covariates] * 2,
)
model = RegressionModel(lags=3,
lags_past_covariates=5,
lags_future_covariates=(5, 0))
model.fit([target_train_1_noise], [past_covariates],
[future_covariates])
prediction_past_and_future = model.predict(
n=len(target_test_1),
series=[target_train_1_noise, target_train_2_noise],
past_covariates=[past_covariates] * 2,
future_covariates=[future_covariates] * 2,
)
error_past_only = rmse(
[target_test_1, target_test_2],
prediction_past_only,
inter_reduction=np.mean,
)
error_both = rmse(
[target_test_1, target_test_2],
prediction_past_and_future,
inter_reduction=np.mean,
)
self.assertTrue(error_past_only > error_both)
# test 2: with both covariates, 2 TS should learn more than one (with little noise)
model = RegressionModel(lags=3,
lags_past_covariates=5,
lags_future_covariates=(5, 0))
model.fit(
[target_train_1_noise, target_train_2_noise],
[past_covariates] * 2,
[future_covariates] * 2,
)
prediction_past_and_future_multi_ts = model.predict(
n=len(target_test_1),
series=[target_train_1_noise, target_train_2_noise],
past_covariates=[past_covariates] * 2,
future_covariates=[future_covariates] * 2,
)
error_both_multi_ts = rmse(
[target_test_1, target_test_2],
prediction_past_and_future_multi_ts,
inter_reduction=np.mean,
)
self.assertTrue(error_both > error_both_multi_ts)
train, val = series.split_after(pd.Timestamp('20200810'))
from darts.models import ExponentialSmoothing
model = ExponentialSmoothing()
model.fit(train)
prediction = model.predict(len(val))
import matplotlib.pyplot as plt
series.plot(label='actual', lw=3)
prediction.plot(label='forecast', lw=3)
plt.legend()
plt.xlabel('Year')
from darts.models.prophet import Prophet
models = [ExponentialSmoothing(), Prophet()]
backtests = [
model.backtest(series, start=pd.Timestamp('20200810'), forecast_horizon=3)
for model in models
]
from darts.metrics import mape, rmse
for i, m in enumerate(models):
err = rmse(backtests[i], series)
backtests[i].plot(lw=3, label='{}, RMSE={:.2f}'.format(m, err))
plt.title('Predictive verification of 3 methods')
plt.legend()
plt.savefig("result2_pcr_positive_daily.png", bbox_inches='tight', dpi=120)