new.py 文件源码

def train(X, y, true_k=50, minibatch=False, showLable=True):
    # ??????????????k-means?
    fout = open('pro1_cluster.txt', 'w+')
    if minibatch:
        km = MiniBatchKMeans(n_clusters=true_k, init='k-means++', n_init=1,
                             init_size=1000, batch_size=1000, verbose=False)
    else:
        km = KMeans(n_clusters=true_k, init='k-means++', max_iter=300, n_init=1,
                    verbose=False)
    km.fit(X)
    print y.dtype
    if showLable:
        print("Top terms per cluster:")
        order_centroids = km.cluster_centers_.argsort()[:, ::-1]
        terms = y
        # print y
        result = list(km.predict(X))
        print('Cluster distribution:')
        print(dict([(i, result.count(i)) for i in result]))
        cluster_list = {}
        for i in range(true_k):
            cluster_list[i] = []
        for j in range(len(result)):
            # print terms[j]
            # print result[j]
            cluster_list[result[j]].append([terms[j], X[j]])
        for i in cluster_list.keys():
            cluster = cluster_list[i]
            if len(cluster) > 0:
                for bet in cluster:
                    vec = bet[1].tolist()
                    # fout.write(bet[0] + str(vec) + '\n')
                    # print bet
                    fout.write(bet[0] + '\n')
                fout.write('-------------------\n')

    return -km.score(X)
    fout.close()