skada.DASVMClassifier
- skada.DASVMClassifier(base_estimator=None, k=3, max_iter=1000, save_estimators=False, save_indices=False, **kwargs)[source]
DASVM Estimator:
- Parameters:
- base_estimatorBaseEstimator
The estimator that will be used in the algorithm, It is a SVC by default, but can use any classifier equipped with a decision_function method
- k: int>0
The number of points per classes that will be discarded/added at each steps of the algorithm
- max_iterint
The maximal number of iteration of the algorithm when using fit
- save_estimatorsBool
True if this object should remembers all the fitted estimators
- save_indicesBool
- True if this object should remembers all the values of
index_source_deleted and index_target_added
References
[11]Bruzzone, L., & Marconcini, M. 'Domain adaptation problems: A DASVM classification technique and a circular validation strategy.' IEEE transactions on pattern analysis and machine intelligence, (2009).
