tensorly.regression.kruskal_regression.KruskalRegressor

class KruskalRegressor(weight_rank, tol=1e-06, reg_W=1, n_iter_max=100, random_state=None, verbose=1)[source]

Kruskal tensor regression

Learns a low rank CP tensor weight
Parameters:

weight_rank : int

rank of the CP decomposition of the regression weights

tol : float

convergence value

reg_W : int, optional, default is 1

regularisation on the weights

n_iter_max : int, optional, default is 100

maximum number of iteration

random_state : None, int or RandomState, optional, default is None

verbose : int, default is 1

level of verbosity

fit(X, y)[source]

Fits the model to the data (X, y)

Parameters:

X : ndarray

tensor data of shape (n_samples, N1, …, NS)

y : 1D-array of shape (n_samples, )

labels associated with each sample

Returns:

self

get_params(**kwargs)[source]

Returns a dictionary of parameters

predict(X)[source]

Returns the predicted labels for a new data tensor

Parameters:

X : ndarray

tensor data of shape (n_samples, N1, …, NS)

set_params(**parameters)[source]

Sets the value of the provided parameters