K-means最优K值计算(利用SSE)

 参考代码

def distEclud(vecA, vecB):
    """
    计算两个向量的欧式距离的平方,并返回
    """
    return np.sum(np.power(vecA - vecB, 2))
 
def test_Kmeans_nclusters(data_train):
    """
    计算不同的k值时,SSE的大小变化
    """
    data_train = data_train.values
    nums=range(2,10)
    SSE = []
    for num in nums:
        sse = 0
        kmodel = KMeans(n_clusters=num, n_jobs=4)
        kmodel.fit(data_train)
        # 簇中心
        cluster_ceter_list = kmodel.cluster_centers_
        # 个样本属于的簇序号列表
        cluster_list = kmodel.labels_.tolist()
        for index in  range(len(data)):
            cluster_num = cluster_list[index]
            sse += distEclud(data_train[index, :], cluster_ceter_list[cluster_num])
        print("簇数是",num , "时; SSE是", sse)
        SSE.append(sse)
    return nums, SSE
 
nums, SSE = test_Kmeans_nclusters(filter_zscore_data)

 

你可能感兴趣的:(Python,数据分析)