RapidMiner 9.7 is Now Available

Lots of amazing new improvements including true version control! Learn more about what's new here.


Analyzing cluster homogeneity and using Cluster Distance Performnace

nidhi_s019nidhi_s019 Member Posts: 2 Contributor I
edited November 2018 in Help

Hi, I have implemented k-means clustering on a dataset. I have tried analyzing k of clustering by looking at parallel and deviation chart given in rapid-miner. Further, the aim is to analyze homogeneity of clusters.  Out of various performance models given, the operator "Cluster Distance Performance" operator is used on results of k-means clustering. 1)Are there any other operators that can provide such analysis? 2) The dataset that I have has numeric vectors with large values (in hundreds and thousands), also I have a dataset which have extremely small values (upto 5th-8th place of decimal) . I am not sure of how to interpret the results that I get from the operator  "Cluster Distance Performance".. Can someone please help me with this? Though I read that smaller the value of Davies Bouldin better is the clustering. Please find attached for reference a snapshot of performance operator result and Centroid table. Thanks.

Sign In or Register to comment.