聚类分析.pptVIP

Analyze Classify TwoStep cluster… Categorical: Vehicle type Continuous Variables: Sales in thousands 4-year resale value Price in thousands Engine size Horsepower Wheelbase Width Length Curb weight Fuel capacity Fuel efficiency Plots: Variable Importance Plot: 选中：Rank of variable importance 选中： By variable Output: Working data file: 选中：Create cluster membership variable 聚类要注意的问题 聚类结果主要受所选择的变量影响。如果去掉一些变量，或者增加一些变量，结果会很不同。 相比之下，聚类方法的选择则不那么重要了。因此，聚类之前一定要目标明确。? 另外就分成多少类来说，也要有道理。只要你高兴，从分层聚类的计算机结果可以得到任何可能数量的类。但是，聚类的目的是要使各类之间的距离尽可能地远，而类中点的距离尽可能的近，而且分类结果还要有令人信服的解释。这一点就不是数学可以解决的了。 该结束聚类了吧！ The silhouette plot displays a measure of how close each point in one cluster is to points in the neighboring clusters. This measure ranges from +1, indicating points that are very distant from neighboring clusters, through 0, indicating points that are not distinctly in one cluster or another, to -1, indicating points that are probably assigned to the wrong cluster. For each observation i, the?silhouette width?s(i)?is defined as follows:?Put a(i) = average dissimilarity between i and all other points of the cluster to which i belongs (if i is the?only?observation in its cluster,?s(i) := 0 without further calculations). For all?other?clusters C, put?d(i,C)?= average dissimilarity of i to all observations of C. The smallest of these?d(i,C)?is b(i) := \min_C d(i,C), and can be seen as the dissimilarity between i and its “neighbor” cluster, i.e., the nearest one to which it does?not?belong. Finally, s(i) := ( b(i) - a(i) ) / max( a(i), b(i) ). silhouette plot can give you an idea of how well-separated the resulting clusters are. The silhouette plot displays a measure of how close each point in one cluster is to points in the neighboring clusters. This measure ranges from +1, indicating points that are very distant from neighboring clusters, through 0, indicating points that are not distinctly in one cluster or another, to -1, indicating points that are probably assigned to the wrong clus