classifier 1.4.4 → 2.1.0

data/lib/classifier/lsi/content_node.rb

@@ -1,3 +1,5 @@
+# rbs_inline: enabled
+
 # Author::    David Fayram  (mailto:dfayram@lensmen.net)
 # Copyright:: Copyright (c) 2005 David Fayram II
 # License::   LGPL
@@ -7,34 +9,49 @@ module Classifier
   # raw_vector_with, it should be fairly straightforward to understand.
   # You should never have to use it directly.
   class ContentNode
-    attr_accessor :raw_vector, :raw_norm,
-                  :lsi_vector, :lsi_norm,
-                  :categories
+    # @rbs @word_hash: Hash[Symbol, Integer]
+
+    # @rbs @raw_vector: untyped
+    # @rbs @raw_norm: untyped
+    # @rbs @lsi_vector: untyped
+    # @rbs @lsi_norm: untyped
+    attr_accessor :raw_vector, :raw_norm, :lsi_vector, :lsi_norm
+
+    # @rbs @categories: Array[String | Symbol]
+    attr_accessor :categories
 
     attr_reader :word_hash
 
     # If text_proc is not specified, the source will be duck-typed
     # via source.to_s
+    #
+    # @rbs (Hash[Symbol, Integer], *String | Symbol) -> void
     def initialize(word_frequencies, *categories)
       @categories = categories || []
       @word_hash = word_frequencies
     end
 
     # Use this to fetch the appropriate search vector.
+    #
+    # @rbs () -> untyped
     def search_vector
       @lsi_vector || @raw_vector
     end
 
     # Use this to fetch the appropriate search vector in normalized form.
+    #
+    # @rbs () -> untyped
     def search_norm
       @lsi_norm || @raw_norm
     end
 
     # Creates the raw vector out of word_hash using word_list as the
     # key for mapping the vector space.
+    #
+    # @rbs (WordList) -> untyped
     def raw_vector_with(word_list)
-      vec = if $GSL
-              GSL::Vector.alloc(word_list.size)
+      vec = if Classifier::LSI.native_available?
+              Classifier::LSI.vector_class.alloc(word_list.size)
             else
               Array.new(word_list.size, 0)
             end
@@ -44,8 +61,9 @@ module Classifier
       end
 
       # Perform the scaling transform
-      total_words = $GSL ? vec.sum : vec.sum_with_identity
-      total_unique_words = vec.count { |word| word != 0 }
+      total_words = Classifier::LSI.native_available? ? vec.sum : vec.sum_with_identity
+      vec_array = Classifier::LSI.native_available? ? vec.to_a : vec
+      total_unique_words = vec_array.count { |word| word != 0 }
 
       # Perform first-order association transform if this vector has more
       # than one word in it.
@@ -60,10 +78,13 @@ module Classifier
           val = term_over_total * Math.log(term_over_total)
           weighted_total += val unless val.nan?
         end
-        vec = vec.collect { |val| Math.log(val + 1) / -weighted_total }
+
+        sign = weighted_total.negative? ? 1.0 : -1.0
+        divisor = sign * [weighted_total.abs, Vector::EPSILON].max
+        vec = vec.collect { |val| Math.log(val + 1) / divisor }
       end
 
-      if $GSL
+      if Classifier::LSI.native_available?
         @raw_norm   = vec.normalize
         @raw_vector = vec
       else

data/lib/classifier/lsi/word_list.rb

@@ -1,3 +1,5 @@
+# rbs_inline: enabled
+
 # Author::    David Fayram  (mailto:dfayram@lensmen.net)
 # Copyright:: Copyright (c) 2005 David Fayram II
 # License::   LGPL
@@ -5,29 +7,38 @@
 module Classifier
   # This class keeps a word => index mapping. It is used to map stemmed words
   # to dimensions of a vector.
-
   class WordList
+    # @rbs @location_table: Hash[Symbol, Integer]
+
+    # @rbs () -> void
     def initialize
       @location_table = {}
     end
 
     # Adds a word (if it is new) and assigns it a unique dimension.
+    #
+    # @rbs (Symbol) -> Integer?
     def add_word(word)
       term = word
       @location_table[term] = @location_table.size unless @location_table[term]
     end
 
     # Returns the dimension of the word or nil if the word is not in the space.
+    #
+    # @rbs (Symbol) -> Integer?
     def [](lookup)
       term = lookup
       @location_table[term]
     end
 
+    # @rbs (Integer) -> Symbol?
     def word_for_index(ind)
       @location_table.invert[ind]
     end
 
     # Returns the number of words mapped.
+    #
+    # @rbs () -> Integer
     def size
       @location_table.size
     end