[
https://issues.apache.org/jira/browse/MATH-1524?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=17058706#comment-17058706
]
Gilles Sadowski commented on MATH-1524:
---------------------------------------
{quote}It is the fastest method
{quote}
Question is whether there are *other* methods. IOW, is the following the right
API?
{code:java}
public class Clusterable {
// ...
default <T extends Clusterable> int[] sortByIncreasingDistance(List<?
extends Cluster<T> list, DistanceMeasure dist) {
// Compute centroids of each cluster in the list.
// Compute the distance from this point to each centroid.
// Return array of indices (into list) sorted in increasing order of
distance.
}
}
{code}
> "chooseInitialCenters" should move out from KMeansPlusPlusClusterer
> -------------------------------------------------------------------
>
> Key: MATH-1524
> URL: https://issues.apache.org/jira/browse/MATH-1524
> Project: Commons Math
> Issue Type: Improvement
> Reporter: Chen Tao
> Priority: Major
> Attachments: centroid.png, getCenter.png
>
> Time Spent: 20m
> Remaining Estimate: 0h
>
> There are two reason for "chooseInitialCenters" should be move out from
> "KMeansPlusPlusClusterer":
> # k-means++ clusterer is a special case of k-means clusterer, that k-means++
> initialize the cluster centers with k-means++ algorithm. Another case is
> initialize the cluster centers with random points.
> # The mini batch k-means will reuse "chooseInitialCenters".
--
This message was sent by Atlassian Jira
(v8.3.4#803005)
