metacluster.py 文件源码

def compute_centroid_set(self):

        INPUT_ITR = subset_iterator(
            X=self.docv,
            m=self.subcluster_m,
            repeats=self.subcluster_repeats,
        )

        kn = self.subcluster_kn
        clf = SpectralClustering(
            n_clusters=kn,
            affinity="precomputed",
        )

        C = []

        for X in INPUT_ITR:
            # Remove any rows that have zero vectors
            bad_row_idx = ((X**2).sum(axis=1) == 0)

            X = X[~bad_row_idx]
            A = cosine_affinity(X)

            # "Force" symmetry due to rounding errors
            A = np.maximum( A, A.transpose() )

            labels = clf.fit_predict(A)

            # Compute the centroids
            (N, dim) = X.shape
            centroids = np.zeros((kn, dim))

            for i in range(kn):
                idx = labels == i
                mu = X[idx].mean(axis=0)
                mu /= np.linalg.norm(mu)
                centroids[i] = mu

            C.append(centroids)

        return np.vstack(C)