Does any know the reference/link where i can find the MATLAB implementation of gap statistics for clustering as mentioned in this paper?
Asked
Active
Viewed 3,348 times
1
-
4Please, don't cross-post on SO and MatlabCentral! – chl Jun 05 '11 at 08:48
-
2The gap statistic takes 20 lines of code or less to implement. It may be faster just to write it yourself. – cardinal Jun 05 '11 at 14:45
-
@chi ok will not repeat the same. – Learner Jun 05 '11 at 15:14
1 Answers
3
The Statistics Toolbox implements the gap statistic as a class in the package clustering.evaluation since R2013b:
load fisheriris;
rng('default'); % For reproducibility
eva = evalclusters(meas,'kmeans','gap','KList',[1:6])
figure;
plot(eva);

You can also use this file exchange.
Franck Dernoncourt
- 46,817
- 33
- 176
- 288
-
+1. I always have a sweet-spot for question archaeologists. On another note, R2013b seems to have really invested in the Stats toolbox functionality. I also saw a first actually usable LME implementation. – usεr11852 Nov 03 '13 at 05:25
-
The file linked does not produce the same graph for the same data set. It recommends two clusters, rather than 4 on R2011a. – Druckles Apr 28 '14 at 16:45
-
Well one of them is wrong or use some variant as the algorithm to compute the gap is supposed to be deterministic :) – Franck Dernoncourt Apr 28 '14 at 19:33