lsa.py 文件源码

def randomizedSVD(self):
        # http://scikit-learn.org/stable/modules/decomposition.html#truncated-singular-value-decomposition-and-latent-semantic-analysis
        # http://stackoverflow.com/questions/31523575/get-u-sigma-v-matrix-from-truncated-svd-in-scikit-learn
        U, S, V = randomized_svd(self.bag_of_words_matrix.T, 
                                      n_components=self.dimensions,
                                      n_iter=5,
                                      random_state=None)
        self.U = U
        self.S = S
        self.V = V
        self.tokens_representation = np.matrix(U) * np.diag(S)
        self.documents_representation = (np.diag(S) * np.matrix(V)).T