partial_svd(matrix, n_eigenvecs=None, flip=False, random_state=None, **kwargs)

Computes a fast partial SVD on matrix

If n_eigenvecs is specified, sparse eigendecomposition is used on either matrix.dot(matrix.T) or matrix.T.dot(matrix).


A 2D tensor.

n_eigenvecsint, optional, default is None

If specified, number of eigen[vectors-values] to return.

flipbool, default is False

If True, the SVD sign ambiguity is resolved by making the largest component in the columns of U, positive.

random_state: {None, int, np.random.RandomState}

If specified, use it for sampling starting vector in a partial SVD(scipy.sparse.linalg.eigsh)


kwargs are used to absorb the difference of parameters among the other SVD functions

U2-D tensor, shape (matrix.shape[0], n_eigenvecs)

Contains the right singular vectors

S1-D tensor, shape (n_eigenvecs, )

Contains the singular values of matrix

V2-D tensor, shape (n_eigenvecs, matrix.shape[1])

Contains the left singular vectors