cluster.py 文件源码

def ward_hc(self, n_clusters, n_neighbors=10):
        """
        Perform Ward hierarchical clustering

        Parameters
        ----------
        n_clusters : int
            number of clusters
        lsi_components : int
            apply LSA before the clustering algorithm
        n_neighbors : int
            N nearest neighbors used for computing the connectivity matrix
        """
        from sklearn.cluster import AgglomerativeClustering
        from sklearn.neighbors import kneighbors_graph
        pars = {'n_neighbors': n_neighbors, 'is_hierarchical': True,
                "metric": self.metric}
        if 'lsi' not in self.pipeline:
            raise ValueError("you must use lsi with birch clustering "
                             "for scaling reasons.")

        # This is really not efficient as
        # it's done a second time in _cluster_func
        X = self.pipeline.data
        connectivity = kneighbors_graph(X, n_neighbors=n_neighbors,
                                        include_self=False)

        km = AgglomerativeClustering(n_clusters=n_clusters, linkage='ward',
                                     connectivity=connectivity)

        return self._cluster_func(n_clusters, km, pars)