gluonts.model.trivial.constant module#

class gluonts.model.trivial.constant.ConstantPredictor(samples: ndarray)[source]#

Bases: RepresentablePredictor

A Predictor that always produces the same forecast.

Parameters:

samples – Samples to use to construct SampleForecast objects for every prediction.

predict_item(item: Dict[str, Any]) → SampleForecast[source]#
class gluonts.model.trivial.constant.ConstantValuePredictor(prediction_length: int, value: float = 0.0, num_samples: int = 1)[source]#

Bases: RepresentablePredictor

A Predictor that always produces the same value as forecast.

Parameters:

  • value – The value to use as forecast.

  • prediction_length – Prediction horizon.

predict_item(item: Dict[str, Any]) → SampleForecast[source]#