clustering.py 文件源码

def k_means_clustering(instance_array, n_clusters=9, sin_cos = 1, number_of_starts = 30, seed=None, use_scikit=1,**kwargs):
    '''
    This runs the k-means clustering algorithm as implemented in scipy - change to scikit-learn?

    SH: 7May2013
    '''
    from sklearn.cluster import KMeans
    print 'starting kmeans algorithm, k=%d, retries : %d, sin_cos = %d'%(n_clusters,number_of_starts,sin_cos)
    if sin_cos==1:
        print '  using sine and cosine of the phases'
        sin_cos_instances = np.zeros((instance_array.shape[0],instance_array.shape[1]*2),dtype=float)
        sin_cos_instances[:,::2]=np.cos(instance_array)
        sin_cos_instances[:,1::2]=np.sin(instance_array)
        input_array = sin_cos_instances
        #code_book,distortion = vq.kmeans(sin_cos_instances, n_clusters,iter=number_of_starts)
        #cluster_assignments, point_distances = vq.vq(sin_cos_instances, code_book)
    else:
        print '  using raw phases'
        input_array = instance_array
        #code_book,distortion = vq.kmeans(instance_array, n_clusters,iter=number_of_starts)
        #cluster_assignments, point_distances = vq.vq(instance_array, code_book)
    #pickle.dump(multiple_run_results,file(k_means_output_filename,'w'))
    if use_scikit:
        print 'using scikit learn'
        tmp = KMeans(init='k-means++', n_clusters=n_clusters, n_init = number_of_starts, n_jobs=1, random_state = seed)
        cluster_assignments = tmp.fit_predict(input_array)
        code_book = tmp.cluster_centers_
    else:
        print 'using vq from scipy'
        code_book,distortion = vq.kmeans(input_array, n_clusters,iter=number_of_starts)
        cluster_assignments, point_distances = vq.vq(input_array, code_book)
    if sin_cos:
        cluster_details = {'k_means_centroids_sc':code_book}
    else:
        cluster_details = {'k_means_centroids':code_book}
    return cluster_assignments, cluster_details

##################################################################################
#############################k-means periodic algorithm##############################