Performance improvement

[DonaldTrump88]

I am doing clustering of about 50K locations. Each cluster should have about 20 or less locations. Unfortunately it takes about 1 hour to finish the algorithm. My initial guess says that repeated distance calculation makes it slow, if I add the correct distance formula based on LatLong it will be slower.
If you also think so then adding distance matrix will be help to optimize it. Here is similar example in DBScan.
https://github.com/bhavikm/DBSCAN-clustering/blob/master/index.php
The matrix calculation can be done when user calls solve.

[DonaldTrump88]

I have read few positive reviews of mini batch clustering.
https://papers.nips.cc/paper/2016/file/8d317bdcf4aafcfc22149d77babee96d-Paper.pdf
https://scikit-learn.org/stable/modules/generated/sklearn.cluster.MiniBatchKMeans.html

[bdelespierre]

Thanks @Ninja-007, I'll give it a look. If you have suggestions for implementation feel free to start a PR

[halfhope]

Hi!

You can store a diagonal matrix in a one-dimensional array. It could be two times faster.

https://gist.github.com/halfhope/8589f5f97f76e066480dcfc7c0ac88da

[bdelespierre]

Hi @halfhope, thanks for your comment. Can you propose an implementation and make a pull-request?