helpers.py 文件源码

def clustering( points, k=2,name='kmeans'):
    '''
    points: N_samples * N_features
    k: number of clusters
    '''
    if name == 'kmeans':
        kmeans = KMeans( n_clusters=k,n_init=100 ).fit(points)
        ## print within_variance
        #cluster_distance = kmeans.transform( points )
        #within_variance = sum( np.min(cluster_distance,axis=1) ) / float( points.shape[0] )
        #print("AvgWithinSS:"+str(within_variance))
        if len( np.unique(kmeans.labels_) ) > 1: 
            si = silhouette_score( points,kmeans.labels_ )
            #print("Silhouette:"+str(si))
        else:
            si = 0
            print("Silhouette:"+str(si))
        return kmeans.labels_,si

    if name == 'spec':
        spec= SpectralClustering( n_clusters=k,affinity='cosine' ).fit( points )
        si = silhouette_score( points,spec.labels_ )
        print("Silhouette:"+str(si))
        return spec.labels_,si