6.1 Kmeans.py 文件源码

def test_Kmeans_n_init(*data):
    '''
    test the performance with different n_init and init paramter
    :param data: data, target
    :return: None
    '''
    X,labels_true=data
    nums=range(1,50)
    ## graph
    fig=plt.figure()

    ARIs_k=[]
    Distances_k=[]
    ARIs_r=[]
    Distances_r=[]
    for num in nums:
            clst=cluster.KMeans(n_init=num,init='k-means++')
            clst.fit(X)
            predicted_labels=clst.predict(X)
            ARIs_k.append(adjusted_rand_score(labels_true,predicted_labels))
            Distances_k.append(clst.inertia_)

            clst=cluster.KMeans(n_init=num,init='random')
            clst.fit(X)
            predicted_labels=clst.predict(X)
            ARIs_r.append(adjusted_rand_score(labels_true,predicted_labels))
            Distances_r.append(clst.inertia_)

    ax=fig.add_subplot(1,2,1)
    ax.plot(nums,ARIs_k,marker="+",label="k-means++")
    ax.plot(nums,ARIs_r,marker="+",label="random")
    ax.set_xlabel("n_init")
    ax.set_ylabel("ARI")
    ax.set_ylim(0,1)
    ax.legend(loc='best')
    ax=fig.add_subplot(1,2,2)
    ax.plot(nums,Distances_k,marker='o',label="k-means++")
    ax.plot(nums,Distances_r,marker='o',label="random")
    ax.set_xlabel("n_init")
    ax.set_ylabel("inertia_")
    ax.legend(loc='best')

    fig.suptitle("KMeans")
    plt.show()