k-means clustering: save the number of iterations in a matrix

9 次查看（过去 30 天）
pavlos
pavlos 2014-1-31
回答： Phu Lai 2016-12-8
Hello,
With the following command the number of iterations are displayed in the Command Window.
idx = kmeans(X,30,'display','iter');
iter phase num sum
1 1 365 40.9896
2 1 60 37.0645
3 1 18 36.001
4 1 3 35.7457
5 1 1 35.6472
6 2 39 34.8684
7 2 32 34.1611
8 2 16 33.7392
9 2 11 33.3268
10 2 4 33.2144
11 2 1 33.2046
11 iterations, total sum of distances = 33.2046
Is there a way to save the displayed number of iterations and the total sum of distances in a matrix stored in the Workspace?
Thank you. Best,
Pavlos

请先登录，再回答此问题。

采纳的回答

David Sanchez
David Sanchez 2014-1-31
[IDX,C,sumd,D] = kmeans(X,30,'display','iter');
where
sum(sumd)
is the sum of distances The number of iterations is not stored in any variable

更多回答（1 个）

Phu Lai
Phu Lai 2016-12-8
Another way around to get the number of iterations is modifying the kmeans.m source code :)

类别

在 Help Center 和 File Exchange 中查找有关 k-Means and k-Medoids Clustering 的更多信息

标签

产品

Community Treasure Hunt

Find the treasures in MATLAB Central and discover how the community can help you!

Start Hunting!

Translated by