Stefano Mazzocchi
0c4b79c53a
more polish on the clustering dialog
...
git-svn-id: http://google-refine.googlecode.com/svn/trunk@260 7d457c2a-affb-35e4-300a-418c747d4874
2010-03-09 20:58:51 +00:00
Stefano Mazzocchi
8ce21461cb
getting closer to the desired functionality... still way too slow though
...
git-svn-id: http://google-refine.googlecode.com/svn/trunk@256 7d457c2a-affb-35e4-300a-418c747d4874
2010-03-09 17:28:50 +00:00
Stefano Mazzocchi
50e58fb863
ngram-blocking gives more expected results... but slow as hell, maybe bug in the vptree code?
...
git-svn-id: http://google-refine.googlecode.com/svn/trunk@255 7d457c2a-affb-35e4-300a-418c747d4874
2010-03-09 09:05:20 +00:00
Stefano Mazzocchi
546f87a536
let's try with another knn method
...
git-svn-id: http://google-refine.googlecode.com/svn/trunk@254 7d457c2a-affb-35e4-300a-418c747d4874
2010-03-09 08:09:35 +00:00
Stefano Mazzocchi
5b079b04b7
- moved from float to double to avoid excessive casting from secondstring
...
- added a few of the more powerful distances
- fixed a bug in the VPTree builder (although is still not working as I expect it to)
git-svn-id: http://google-refine.googlecode.com/svn/trunk@248 7d457c2a-affb-35e4-300a-418c747d4874
2010-03-09 05:11:36 +00:00
Stefano Mazzocchi
f7b0caa1b8
now kNN clustering is fully operational... not very practical though, needs more work and testing
...
git-svn-id: http://google-refine.googlecode.com/svn/trunk@225 7d457c2a-affb-35e4-300a-418c747d4874
2010-03-07 08:27:13 +00:00
Stefano Mazzocchi
976c1da5c7
much improved facet clustering dialog and functionality
...
NOTE: kNN clustering code operational but is not working as expected
git-svn-id: http://google-refine.googlecode.com/svn/trunk@219 7d457c2a-affb-35e4-300a-418c747d4874
2010-03-06 10:17:58 +00:00