6.1 Kmeans.py 文件源码

def test_Kmeans_nclusters(*data):
    '''
    test the performance with different n_clusters
    :param data: data, target
    :return: None
    '''
    X,labels_true=data
    nums=range(1,50)
    ARIs=[]
    Distances=[]
    for num in nums:
        clst=cluster.KMeans(n_clusters=num)
        clst.fit(X)
        predicted_labels=clst.predict(X)
        ARIs.append(adjusted_rand_score(labels_true,predicted_labels))
        Distances.append(clst.inertia_)

    ## graph
    fig=plt.figure()
    ax=fig.add_subplot(1,2,1)
    ax.plot(nums,ARIs,marker="+")
    ax.set_xlabel("n_clusters")
    ax.set_ylabel("ARI")
    ax=fig.add_subplot(1,2,2)
    ax.plot(nums,Distances,marker='o')
    ax.set_xlabel("n_clusters")
    ax.set_ylabel("inertia_")
    fig.suptitle("KMeans")
    plt.show()