Reputation: 11282
How do I compute the cosine similarity distance of two documents in Perl? A few questions: 1) Are there already modules for computing the cosine similarity distance in CPAN? Or is this task easy enough to code up? 2) When I say documents, I really mean that one "document" is a sentence and the other "document" is just a list of keywords. To be fair, should I tokenize, lowercase and sort all the keywords in each document respectively before computing the cosine similarity distance?
Upvotes: 0
Views: 1538
Reputation: 62109
Well, a quick search for cosine similarity on CPAN brings up Text::Document.
Upvotes: 3