Classifier

MultiplexClassifier

Multivariate Predict probaMultioutputUnequal length Missing values

MultiplexClassifier for selecting among different models.

MultiplexClassifier facilitates a framework for performing model selection process over different model classes. It should be used in conjunction with GridSearchCV to get full utilization. It can be used with univariate and multivariate classifiers, single-output and multi-output classifiers.

MultiplexClassifier is specified with a (named) list of classifiers and a selected_classifier hyper-parameter, which is one of the classifier names. The MultiplexClassifier then behaves precisely as the classifier with name selected_classifier, ignoring functionality in the other classifiers.

When used with GridSearchCV, MultiplexClassifier provides an ability to tune across multiple estimators, i.e., to perform AutoML, by tuning the selected_classifier hyper-parameter. This combination will then select one of the passed classifiers via the tuning algorithm.

Schnellstart

python

from sktime.classification.compose import MultiplexClassifier

estimator = MultiplexClassifier(classifiers: list, selected_classifier=None)

Parameter(2)

classifierslist of sktime classifiers, or

list of tuples (str, estimator) of sktime classifiers MultiplexClassifier can switch (“multiplex”) between these classifiers. These are “blueprint” classifiers, states do not change when fit is called.

selected_classifier: str or None, optional, Default=None.

If str, must be one of the classifier names.: If no names are provided, must coincide with auto-generated name strings. To inspect auto-generated name strings, call get_params.