user_clustering_artist_taset.py 文件源码

def gen_cluster(keys = None, cluster_matrix = None):
    km = MiniBatchKMeans(n_clusters=50, batch_size=1000)
#     km = KMeans(n_jobs=-1, n_clusters=50)
    print "Clustering data..."
    labels = pd.DataFrame(km.fit_predict(cluster_matrix.values))
    res = pd.concat([keys, labels], axis = 1, ignore_index=True)
    return res