TimeSeriesPredictor.predict

TimeSeriesPredictor.predict(data: TimeSeriesDataFrame | DataFrame | Path | str, known_covariates: TimeSeriesDataFrame | DataFrame | Path | str | None = None, model: str | None = None, use_cache: bool = True, random_seed: int | None = 123) → TimeSeriesDataFrame[source]

Return quantile and mean forecasts for the given dataset, starting from the end of each time series.

Parameters:

  • data (Union[TimeSeriesDataFrame, pd.DataFrame, Path, str]) –

    Time series data to forecast with.

    If known_covariates_names were specified when creating the predictor, data must include the columns listed in known_covariates_names with the covariates values aligned with the target time series.

    If train_data used to train the predictor contained past covariates or static features, then data must also include them (with same column names and dtypes).

    If provided data is an instance of pandas DataFrame, AutoGluon will attempt to automatically convert it to a TimeSeriesDataFrame.

  • known_covariates (Union[TimeSeriesDataFrame, pd.DataFrame, Path, str], optional) –

    If known_covariates_names were specified when creating the predictor, it is necessary to provide the values of the known covariates for each time series during the forecast horizon. That is:

    • The columns must include all columns listed in known_covariates_names

    • The item_id index must include all item ids present in data

    • The timestamp index must include the values for prediction_length many time steps into the future from the end of each time series in data

    See example below.

  • model (str, optional) – Name of the model that you would like to use for prediction. By default, the best model during training (with highest validation score) will be used.

  • random_seed (int or None, default = 123) – If provided, fixes the seed of the random number generator for all models. This guarantees reproducible results for most models (except those trained on GPU because of the non-determinism of GPU operations).

  • use_cache (bool, default = True) – If True, will attempt to use the cached predictions. If False, cached predictions will be ignored. This argument is ignored if cache_predictions was set to False when creating the TimeSeriesPredictor.

Examples

>>> print(data)
                    target  promotion  price
item_id timestamp
A       2020-01-05      20          0   19.9
        2020-01-06      40          1    9.9
        2020-01-07      32          0   15.0
B       2020-03-01      13          0    5.0
        2020-03-02      44          1    2.9
        2020-03-03      72          1    2.9
>>> predictor = TimeSeriesPredictor(prediction_length=2, known_covariates_names=["promotion", "price"]).fit(data)
>>> print(future_known_covariates)
                    promotion  price
item_id timestamp
A       2020-01-08          1   12.9
        2020-01-09          1   12.9
B       2020-03-04          0    5.0
        2020-03-05          0    7.0
>>> predictor.predict(data, known_covariates=future_known_covariates)
                      mean
item_id timestamp
A       2020-01-08    30.2
        2020-01-09    27.0
B       2020-03-04    17.1
        2020-03-05     8.3