ITMO_FS.ensembles.ranking_based.Mixed

class ITMO_FS.ensembles.ranking_based.Mixed(filters)

Performs feature selection based on several filters, selecting features this way: Get ranks from every filter from input. Then loops through, on every iteration=i selects features on i position on every filter then shuffles them, then adds to result list without duplication, continues until specified number of features

Parameters:filters (list of filter functions) –

Examples

>>> from ITMO_FS.filters.univariate.measures import spearman_corr,pearson_corr
>>> from ITMO_FS.ensembles.ranking_based.Mixed import Mixed
>>> from sklearn.datasets import make_classification
>>> x, y = make_classification(1000, 50, n_informative = 5, n_redundant = 3, n_repeated = 2, shuffle = True)
>>> mixed = Mixed([spearman_corr, pearson_corr])
>>> mixed.fit(x, y)
>>> print(mixed.transform(x, 20))

__init__(filters)

Initialize self. See help(type(self)) for accurate signature.