cluster.py 文件源码

def k_means(self, n_clusters, batch_size=1000):
        """
        Perform K-mean clustering

        Parameters
        ----------
        n_clusters : int
           number of clusters
        batch_size : int
           the bath size for the MiniBatchKMeans algorithm
        """
        from sklearn.cluster import MiniBatchKMeans
        pars = {"batch_size": batch_size, 'is_hierarchical': False,
                "metric": self.metric}
        km = MiniBatchKMeans(n_clusters=n_clusters, init='k-means++',
                             n_init=10,
                             init_size=batch_size, batch_size=batch_size)
        return self._cluster_func(n_clusters, km, pars)