def run_example():
dataset = get_dataset("electricity")
serialize_path = Path("GluonTSTabularPredictor")
estimator = TabularEstimator(
freq="H",
prediction_length=24,
time_limit=600, # ten minutes for training
disable_auto_regression=
True, # makes prediction faster, but potentially less accurate
last_k_for_val=
24, # split the last 24 targets from each time series to be the validation data
quantiles_to_predict=[0.1, 0.5, 0.9],
)
n_train = 5
training_data = list(islice(dataset.train, n_train))
predictor = estimator.train(training_data=training_data)
os.makedirs(serialize_path, exist_ok=True)
predictor.serialize(serialize_path)
predictor = None
# the quantiles_to_predict parameters should be List[str] type
predictor = Predictor.deserialize(serialize_path)
forecasts = list(predictor.predict(training_data))
print(forecasts)
def run_example():
dataset = get_dataset("electricity")
serialize_path = Path("GluonTSTabularPredictor")
estimator = TabularEstimator(
freq="H",
prediction_length=24,
time_limit=10, # two minutes for training
disable_auto_regression=True, # makes prediction faster, but potentially less accurate
last_k_for_val=24, # split the last 24 targets from each time series to be the validation data
quantiles_to_predict=None,
)
n_train = 5
training_data = list(islice(dataset.train, n_train))
predictor = estimator.train(training_data=training_data)
os.makedirs(serialize_path, exist_ok=True)
predictor.serialize(serialize_path)
predictor = None
predictor = Predictor.deserialize(serialize_path)
forecasts = list(predictor.predict(training_data))
for entry, forecast in zip(training_data, forecasts):
ts = to_pandas(entry)
plt.figure()
plt.plot(ts[-7 * predictor.prediction_length :], label="target")
forecast.plot()
plt.show()
def run_example():
dataset = get_dataset("electricity")
estimator = TabularEstimator(
freq="H",
prediction_length=24,
time_limits=2 * 60, # two minutes for training
disable_auto_regression=
True, # makes prediction faster, but potentially less accurate
)
n_train = 5
training_data = list(islice(dataset.train, n_train))
predictor = estimator.train(training_data=training_data, )
forecasts = list(predictor.predict(training_data))
for entry, forecast in zip(training_data, forecasts):
ts = to_pandas(entry)
plt.figure()
plt.plot(ts[-7 * predictor.prediction_length:], label="target")
forecast.plot()
plt.show()
def test_tabular_estimator(
dataset,
freq,
prediction_length: int,
lag_indices: List[int],
disable_auto_regression: bool,
last_k_for_val: int,
validation_data: ListDataset,
):
estimator = TabularEstimator(
freq=freq,
prediction_length=prediction_length,
lag_indices=lag_indices,
time_limit=10,
disable_auto_regression=disable_auto_regression,
last_k_for_val=last_k_for_val,
)
def check_consistency(entry, f1, f2):
ts = to_pandas(entry)
start_timestamp = ts.index[-1] + pd.tseries.frequencies.to_offset(freq)
assert f1.samples.shape == (1, prediction_length)
assert f1.start_date == start_timestamp
assert f2.samples.shape == (1, prediction_length)
assert f2.start_date == start_timestamp
assert np.allclose(f1.samples, f2.samples)
with tempfile.TemporaryDirectory() as path:
predictor = estimator.train(dataset, validation_data=validation_data)
predictor.serialize(Path(path))
predictor = None
predictor = Predictor.deserialize(Path(path))
assert not predictor.auto_regression or any(
l < prediction_length for l in predictor.lag_indices
)
assert predictor.batch_size > 1
forecasts_serial = list(predictor._predict_serial(dataset))
forecasts_batch = list(predictor.predict(dataset))
for entry, f1, f2 in zip(dataset, forecasts_serial, forecasts_batch):
check_consistency(entry, f1, f2)
if not predictor.auto_regression:
forecasts_batch_autoreg = list(
predictor._predict_batch_autoreg(dataset)
)
for entry, f1, f2 in zip(
dataset, forecasts_serial, forecasts_batch_autoreg
):
check_consistency(entry, f1, f2)
def _get_estimator(self):
return TabularEstimator(
freq=self.freq,
prediction_length=self.prediction_length,
time_limit=self.params_aux["time_limit"],
last_k_for_val=self.prediction_length,
)