Kmeans information and cluster analysis
1 view (last 30 days)
Show older comments
Hello so I recently used kmeans clustering to group customers with similar purchase order histories/customer data. I have obtained the IDk, c , sumd, and d values obtained from the kmeans function. My question is with this data, How am I supposed to extract information so I can learn about what is in the clusters? Are there any functions or methods to describe the affects of the variables? Please help.
0 Comments
Answers (1)
Nirja Mehta
on 1 Dec 2016
The outputs of kmeans will help you in visualizing the way your data is separated among k number of clusters. The outputs contain the following information:
idx - cluster indices
C — Cluster centroid locations
sumd — Within-cluster sums of point-to-centroid distances
D — Distances from each point to every centroid
With this information, you can plot the clusters and the cluster centroids as shown in the following link: K-Means Plot
0 Comments
See Also
Categories
Find more on Statistics and Machine Learning Toolbox in Help Center and File Exchange
Community Treasure Hunt
Find the treasures in MATLAB Central and discover how the community can help you!
Start Hunting!