ts_benchmark.baselines.time_series_library package

The following module is the adapter required for embedding the models in time series library into TFB.

ts_benchmark.baselines.time_series_library.adapters_for_transformers module

Functions

generate_model_factory(model_name, ...)

Generate model factory information for creating Transformer Adapters model adapters.

transformer_adapter(model_info)

Classes

TransformerAdapter(model_name, model_class, ...)

TransformerConfig(**kwargs)

class TransformerAdapter(model_name, model_class, **kwargs)[source]

Bases: ModelBase

batch_forecast(horizon: int, batch_maker: BatchMaker, **kwargs) → numpy.ndarray[source]

Make predictions by batch.

Parameters:

  • horizon – The length of each prediction.

  • batch_maker – Make batch data used for prediction.

Returns:

An array of predicted results.

forecast(horizon: int, train: pandas.DataFrame) → numpy.ndarray[source]

Make predictions.

Parameters:

  • horizon – The predicted length.

  • testdata – Time series data used for prediction.

Returns:

An array of predicted results.

forecast_fit(train_valid_data: pandas.DataFrame, train_ratio_in_tv: float) → ModelBase[source]

Train the model.

Parameters:

  • train_data – Time series data used for training.

  • train_ratio_in_tv – Represents the splitting ratio of the training set validation set. If it is equal to 1, it means that the validation set is not partitioned.

Returns:

The fitted model object.

property model_name

Returns the name of the model.

multi_forecasting_hyper_param_tune(train_data: pandas.DataFrame)[source]
padding_data_for_forecast(test)[source]
static required_hyper_params() → dict[source]

Return the hyperparameters required by model.

Returns:

An empty dictionary indicating that model does not require additional hyperparameters.

single_forecasting_hyper_param_tune(train_data: pandas.DataFrame)[source]
validate(valid_data_loader, criterion)[source]
class TransformerConfig(**kwargs)[source]

Bases: object

property pred_len
generate_model_factory(model_name: str, model_class: type, required_args: dict) → Dict[source]

Generate model factory information for creating Transformer Adapters model adapters.

Parameters:

  • model_name – Model name.

  • model_class – Model class.

  • required_args – The required parameters for model initialization.

Returns:

A dictionary containing model factories and required parameters.

transformer_adapter(model_info: Type[object]) → object[source]