weka[10] - SimpleKmeans

最新推荐文章于 2022-06-15 21:36:00 发布

VIP文章杨之之

最新推荐文章于 2022-06-15 21:36:00 发布

阅读量4k

点赞数 1

分类专栏： weka 文章标签： weka clustering kmeans

本文链接：https://blog.csdn.net/u011292007/article/details/37595917

版权

classification的算法还有一些，不过还是打算先进入clustering的阶段。后续再回去补。

这一篇主要看看kmeans。kmeans是最简单的一种聚类算法，很清晰的EM思路。他的主要缺陷是聚类个数无法确定(靠人为设定)，受初始中心点影响较大。

下面直接看看代码：国际惯例，看看buildCluster

    getCapabilities().testWithFail(data);

    m_Iterations = 0;

    m_ReplaceMissingFilter = new ReplaceMissingValues();
    Instances instances = new Instances(data);
				
    instances.setClassIndex(-1);
    if (!m_dontReplaceMissing) {
      m_ReplaceMissingFilter.setInputFormat(instances);
      instances = Filter.useFilter(instances, m_ReplaceMissingFilter);
    }

    m_FullMissingCounts = new int[instances.numAttributes()];
    if (m_displayStdDevs) {
      m_FullStdDevs = new double[instances.numAttributes()];
    }
    m_FullNominalCounts = new int[instances.numAttributes()][0];

m_FullMissingCounts就是统计每个属性的缺失值

    m_FullMeansOrMediansOrModes = moveCentroid(0, instances, false);
    for (int i = 0; i < instances.numAttributes(); i++) {
      m_FullMissingCounts[i] = instances.attributeStats(i).missingCount;
      if (instances.attribute(i).isNumeric()) {
        if (m_displayStdDevs) {
          m_FullStdDevs[i] = Math.sqrt(instances.variance(i));
        }
        if (m_FullMissingCounts[i] == instances.numInstances()) {
          m_FullMeansOrMediansOrModes[i] = Double.NaN; // mark missing as mean
        }
      } else {
        m_FullNominalCounts[i] = instances.attributeStats(i).nominalCounts;
        if (m_FullMissingCounts[i] 
            > m_FullNominalCounts[i][Utils.maxIndex(m_FullNominalCounts[i])]) {
          m_FullMeansOrMediansOrModes[i] =