In case of larger lists, you can find the clusters after clustering. There won't be many. Then do a brute force and find "farthest" and "nearest" clusters. Then compare the vectors of farthest and nearest "clusters" to find the farthest and nearest "vector pairs".
________________________________________ From: Raviv Pavel [[email protected]] Sent: Wednesday, January 25, 2012 4:44 PM To: [email protected] Subject: Re: Finding max/min distance Since my list is fairly short (~2000 vectors) i sued the brute-force way and did exactly that. I was hoping mahout had something smarter, in case I'll have to handle much larger lists. * * *--*Raviv On Wed, Jan 25, 2012 at 5:22 PM, Paritosh Ranjan <[email protected]> wrote: > Do you want to find the pair of vectors which are "farthest" and "nearest" > ? > If yes, I think you will have to compare all pairs using > > double distance(Vector v1, Vector v2); > > of DistanceMeasure. > > I don't think Mahout has something in built for this. > ________________________________________ > From: Raviv Pavel [[email protected]] > Sent: Wednesday, January 25, 2012 2:39 PM > To: [email protected] > Subject: Finding max/min distance > > Given a list of vectors and a distance measure, what's the fastest way to > find the maximum & minimum distances in the list ? > > Thanks. > *--*Raviv >
