search

NoahCarnahan / plagcomps

Other
6 stars 1 forks source link

trigram/unigram features all zeros #19

Open nrjones8 opened 10 years ago

nrjones8 commented 10 years ago

Clustering is getting confused when given a vector of all zeros (i.e. in the case that a document has no POS trigrams of VB,NN,VB). Not sure what the most logical fix is for this

NoahCarnahan commented 10 years ago

Is this a problem with kmeans or the outlier detection?

nrjones8 commented 10 years ago

kmeans

On Sat, Jan 25, 2014 at 1:03 PM, NoahCarnahan notifications@github.comwrote:

Is this a problem with kmeans or the outlier detection?

— Reply to this email directly or view it on GitHubhttps://github.com/NoahCarnahan/plagcomps/issues/19#issuecomment-33296879 .