zhengruifeng commented on pull request #35247: URL: https://github.com/apache/spark/pull/35247#issuecomment-1016473613
in each iteration, `val newCenter = distanceMeasureInstance.centroid(sum, weightSum)` is called to get the new center vector, and `CosineDistanceMeasure` will normalize the center. So the final vectors all have norm 1. It seems just a special attribute in spark's impl, I'm not sure whether other impls normalize the centers too. -- This is an automated message from the Apache Git Service. To respond to the message, please log on to GitHub and use the URL above to go to the specific comment. To unsubscribe, e-mail: [email protected] For queries about this service, please contact Infrastructure at: [email protected] --------------------------------------------------------------------- To unsubscribe, e-mail: [email protected] For additional commands, e-mail: [email protected]
