Reputation: 567
I have students data and I want to cluster them according to there attributes. The problem is that the student_id shouldn't be used in the clustering process, because it has nothing to do with the clustering, and I cannot just remove the student_id, because I won't be able then to know what is the according cluster to each student. My Array has the following structure:
Student_id | movies | chess | football | ....
---------------------------------------------------------
19324857 1 0 1 ...
Code
$studentsInfo = [[1,1,0,0,1,1], [1,1,1,1,0,0], [0,1,1,0,0,1], ....];
$kmeans = new KMeans(6);
$kmeans->cluster(studentsInfo);
There's a solution to search after the clustering process for each student's parameters, and then find his cluster, but it's not practical and time consuming, and I'm working with a lot of entries.
Upvotes: 0
Views: 222
Reputation: 1
PR just merged on master branch, so you can use keys as some kind of label ;) http://php-ml.readthedocs.io/en/latest/machine-learning/clustering/k-means/
Upvotes: 0