Abstract classifier class to be inherited by all classifiers
Available conditional attributes:
(Conditional attributes enabled by default suffixed with +)
Initialize instance of Classifier
enable_ca : None or list of str
disable_ca : None or list of str
auto_train : bool
force_train : bool
space: str, optional :
postproc : Node instance, optional
descr : str
Create full copy of the classifier.
It might require classifier to be untrained first due to present SWIG bindings.
TODO: think about proper re-implementation, without enrollment of deepcopy
Factory method to return an appropriate sensitivity analyzer for the respective classifier.
Either classifier was already trained.
MUST BE USED WITH CARE IF EVER
Helper to avoid check if data was changed actually changed
Useful if just some aspects of classifier were changed since its previous training. For instance if dataset wasn’t changed but only classifier parameters, then kernel matrix does not have to be computed.
Words of caution: classifier must be previously trained, results always should first be compared to the results on not ‘retrainable’ classifier (without calling retrain). Some additional checks are enabled if debug id ‘CHECK_RETRAIN’ is enabled, to guard against obvious mistakes.
Providing summary over the classifier
Either classifier was already trained