capability__multioutput#

capability__multioutput()[source]#

Capability: the estimator can handle multi-output time series.

  • String name: "capability:multioutput"

  • Public capability tag

  • Values: boolean, True / False

  • Example: True

  • Default: False

This tag applies to classifiers and regressors.

If the tag is True, the estimator can handle multivariate target time series, i.e., time series with multiple variables in the target argument y.

If the tag is False, the estimator can only handle univariate targets natively, and will broadcast to variables (ordinary transformers), or raise an error (others).

This condition is specific to target data (e.g., classifier or regressor y), primary input data (X) is not considered.

The capability for primary input data is controlled by the tag capability:multivariate.

The condition is also specific to the data type used, in terms of how being “multivariate” is represented. For instance, a pandas based time series specification is considered multivariate if it has more than one column.