TELF.factorization.SPLITTransfer: Supervised transfer learning method via SPLIT and NMFk#

Supervised transfer learning method via SPLIT and NMFk

Available Functions#

`SPLITTransfer.__init__`(Ks_known, Ks_target)
`SPLITTransfer.fit`(X_known, X_target)
`SPLITTransfer.transform`(indicator)
`SPLITTransfer.fit_transform`(X_known, ...)
`SPLITTransfer.predict`([test])
`SPLITTransfer.get_feature_importances`(indicator)
`SPLITTransfer.get_score`(indicator)
`SPLITTransfer.fit_known`(X_known)
`SPLITTransfer.fit_target`(X_target)
`SPLITTransfer.fit_split`()
`SPLITTransfer.fit_transfer`(indicator)
`SPLITTransfer.learn_H`()
`SPLITTransfer.set_params`(parameters)
`SPLITTransfer.get_params`()

Module Contents#

class TELF.factorization.SPLITTransfer.SPLITTransfer(Ks_known, Ks_target, Ks_split_step=1, Ks_split_min=1, H_regress_gpu=False, H_learn_method='regress', nmfk_params_known={}, nmfk_params_target={}, nmfk_params_split={}, H_regress_iters=1000, H_regress_method='fro', H_regress_init='random', transfer_regress_params={}, transfer_method='SVR', transfer_model=None, verbose=True, random_state=42)[source]#

Bases: object

fit(X_known, X_target)[source]#

fit_known(X_known)[source]#

fit_split()[source]#

fit_target(X_target)[source]#

fit_transfer(indicator)[source]#

fit_transform(X_known, X_target, indicator: ndarray)[source]#

get_feature_importances(indicator, permi_params={}, feature_names=[], plot=True, rotate_xticks=False)[source]#

get_params()[source]#

get_score(indicator)[source]#

learn_H()[source]#

predict(test=True)[source]#

set_params(parameters)[source]#

transform(indicator: ndarray)[source]#