tf-idf-similarity 0.0.6 → 0.0.7

data/lib/tf-idf-similarity/collection.rb

@@ -86,8 +86,6 @@ class TfIdfSimilarity::Collection
   # @param [Hash] opts optional arguments
   # @option opts [Symbol] :function one of :tfidf (default) or :bm25
   # @return [Float] the term's frequency in the document
-  #
-  # @note Like Lucene, we use a b value of 0.75 and a k1 value of 1.2.
   def term_frequency_inverse_document_frequency(document, term, opts = {})
     inverse_document_frequency(term, opts) * term_frequency(document, term, opts)
   end
@@ -115,7 +113,7 @@ class TfIdfSimilarity::Collection
   # @note Like Lucene, we use a b value of 0.75 and a k1 value of 1.2.
   def term_frequency(document, term, opts = {})
     if opts[:function] == :bm25
-      (document.term_counts[term] * 2.2) / (document.term_counts[term] + 0.3 + 0.9 * document.size / average_document_size)
+      (document.term_counts[term].to_i * 2.2) / (document.term_counts[term].to_i + 0.3 + 0.9 * document.size / average_document_size)
     else
       document.term_frequency term
     end

data/lib/tf-idf-similarity/document.rb

@@ -35,7 +35,7 @@ class TfIdfSimilarity::Document
   #
   # @see http://lucene.apache.org/core/4_0_0-BETA/core/org/apache/lucene/search/similarities/TFIDFSimilarity.html
   def term_frequency(term)
-    Math.sqrt term_counts[term]
+    Math.sqrt term_counts[term].to_i
   end
   alias_method :tf, :term_frequency
 

data/lib/tf-idf-similarity/version.rb

@@ -1,3 +1,3 @@
 module TfIdfSimilarity
-  VERSION = "0.0.6"
+  VERSION = "0.0.7"
 end

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: tf-idf-similarity
 version: !ruby/object:Gem::Version
-  version: 0.0.6
+  version: 0.0.7
   prerelease: 
 platform: ruby
 authors:
@@ -9,7 +9,7 @@ authors:
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2012-11-05 00:00:00.000000000 Z
+date: 2012-11-20 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: unicode_utils