categorize 0.0.11 → 0.0.12

data/ext/categorize/categorize.c

@@ -12,7 +12,7 @@ VALUE Categorize = Qnil;
 VALUE CBagOfWords = Qnil;
 VALUE Models = Qnil;
 
-static VALUE method_make_model(VALUE, VALUE);
+static VALUE method_model(VALUE, VALUE);
 static int add_or_update_gram_from_index(int, char *);
 
 // Store all grams, used in  compare_top_grams.
@@ -25,7 +25,7 @@ void Init_categorize()
   Categorize = rb_define_module("Categorize");
   Models = rb_define_module_under(Categorize, "Models");
   CBagOfWords = rb_define_class_under(Models, "CBagOfWords", rb_cObject);
-  rb_define_method(CBagOfWords, "make_model", method_make_model, 1);
+  rb_define_method(CBagOfWords, "model", method_model, 1);
 }
 
 const bool DEBUG = false;
@@ -122,13 +122,13 @@ int compare_top_grams(const void *idx1, const void *idx2)
 }
 
 /*
- * make_model(array_of_tokens);
+ * model(array_of_tokens);
  * ==== Return
  * Top terms
  * ==== Parameters
  * array_of_tokens: Tokens to turn into grams and extract phrases from.
  */
-static VALUE method_make_model(VALUE self, VALUE array_of_tokens)
+static VALUE method_model(VALUE self, VALUE array_of_tokens)
 {
   int i, j;
   long array_of_tokens_len = RARRAY_LEN(array_of_tokens);

data/lib/categorize.rb

@@ -1,7 +1,7 @@
 # encoding: utf-8
 
 # The C extension is listed first.
-require 'categorize/categorize' unless ENV['NO_C_INCLUDE']
+require 'categorize/categorize'
 
 require 'categorize/models/abstract_model'
 require 'categorize/models/bag_of_words'

data/lib/categorize/model.rb

@@ -4,6 +4,7 @@ module Categorize
   module Model
     MIN_WORD_LENGTH = 3
     @bag_of_words = Models::BagOfWords.new
+    @c_bag_of_words = Models::CBagOfWords.new
 
     class << self
       #include Bow
@@ -21,12 +22,13 @@ module Categorize
       # ==== Parameters
       # items:: the items to be classified
       def make_model_c(strings)
-        strings.map { |s| preprocess(s) }
-        #ret = model_bow(array_of_tokens);
+        array_of_tokens = strings.map { |s| preprocess(s) }
+        ret = @c_bag_of_words.model(array_of_tokens);
         count = 0
         ret.reduce({}) do |hash, term|
           hash[term] ||= []
-          hash[term] << count += 1
+          hash[term] << count
+          count += 1
           hash
         end
       end
@@ -37,15 +39,14 @@ module Categorize
         ]
       end
 
-      private
-        def preprocess(string)
-          split_lower_strings = string.split(
-              Constants::Words::SPLIT_REGEX).map(&:downcase)
-          split_lower_strings.delete_if do |word|
-            word.length < MIN_WORD_LENGTH ||
-              Constants::Words::COMMON.include?(word)
-          end
+      def preprocess(string)
+        split_lower_strings = string.split(
+            Constants::Words::SPLIT_REGEX).map(&:downcase)
+        split_lower_strings.delete_if do |word|
+           word.length < MIN_WORD_LENGTH ||
+            Constants::Words::COMMON.include?(word)
         end
+      end
     end
   end
 end

data/lib/categorize/version.rb

@@ -1,5 +1,5 @@
 # encoding: utf-8
 
 module Categorize
-  VERSION = '0.0.11'
+  VERSION = '0.0.12'
 end

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: categorize
 version: !ruby/object:Gem::Version
-  version: 0.0.11
+  version: 0.0.12
   prerelease: 
 platform: ruby
 authors:
@@ -46,9 +46,6 @@ required_ruby_version: !ruby/object:Gem::Requirement
   - - ! '>='
     - !ruby/object:Gem::Version
       version: '0'
-      segments:
-      - 0
-      hash: -3553060524054293255
 required_rubygems_version: !ruby/object:Gem::Requirement
   none: false
   requirements: