ealdent-lda-ruby 0.3.0 → 0.3.1

data/CHANGELOG

@@ -0,0 +1,17 @@
+Version 0.3.0
+=============
+
+- Completely broke backwards compatibility
+- Reworked many classes to make functionality more reasonable
+- Added ability to load documents from text files
+
+Version 0.2.3
+=============
+
+- Bug fixes by Todd Foster
+
+
+Version 0.2.2
+=============
+
+- First stable release

data/VERSION.yml

@@ -1,4 +1,4 @@
 --- 
 :major: 0
 :minor: 3
-:patch: 0
+:patch: 1

data/lda-ruby.gemspec

@@ -1,12 +1,15 @@
+# Generated by jeweler
+# DO NOT EDIT THIS FILE
+# Instead, edit Jeweler::Tasks in Rakefile, and run `rake gemspec`
 # -*- encoding: utf-8 -*-
 
 Gem::Specification.new do |s|
   s.name = %q{lda-ruby}
-  s.version = "0.3.0"
+  s.version = "0.3.1"
 
   s.required_rubygems_version = Gem::Requirement.new(">= 0") if s.respond_to? :required_rubygems_version=
   s.authors = ["David Blei", "Jason Adams"]
-  s.date = %q{2009-07-24}
+  s.date = %q{2009-08-11}
   s.description = %q{Ruby port of Latent Dirichlet Allocation by David M. Blei. See http://www.cs.princeton.edu/~blei/lda-c/.}
   s.email = %q{jasonmadams@gmail.com}
   s.extensions = ["ext/lda-ruby/extconf.rb"]
@@ -16,6 +19,7 @@ Gem::Specification.new do |s|
   ]
   s.files = [
     ".gitignore",
+     "CHANGELOG",
      "README",
      "README.markdown",
      "Rakefile",

data/lib/lda-ruby.rb

@@ -86,7 +86,7 @@ module Lda
     #
     # See also +print_topics+.
     #
-    def top_words(words_per_topic = 10)
+    def top_word_indices(words_per_topic = 10)
       raise 'No vocabulary loaded.' unless @vocab
 
       # find the highest scoring words per topic
@@ -100,6 +100,17 @@ module Lda
       topics
     end
 
+    def top_words(words_per_topic = 10)
+      output = Hash.new
+
+      topics = top_word_indices(words_per_topic)
+      topics.each_pair do |topic_num, words|
+        output[topic_num] = words.map { |w| @vocab[w] }
+      end
+
+      output
+    end
+
     #
     # Get the phi matrix which can be used to assign probabilities to words
     # belonging to a specific topic in each document.  The return value is a

data/lib/lda-ruby/vocabulary.rb

@@ -1,6 +1,6 @@
 module Lda
   class Vocabulary
-    attr_reader :words
+    attr_reader :words, :indexes
 
     def initialize(words = nil)
       @words = Hash.new do |hash, key|
@@ -13,10 +13,17 @@ module Lda
       end
 
       words.each { |w| @words[w] } if words
+      @indexes = Hash.new
+
+      @words.each_pair do |w, i|
+        @indexes[i] = w
+      end
     end
 
     def check_word(word)
-      @words[word.dup]
+      w = @words[word.dup]
+      @indexes[w] = word.dup
+      w
     end
 
     def load_file(filename)

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification 
 name: ealdent-lda-ruby
 version: !ruby/object:Gem::Version 
-  version: 0.3.0
+  version: 0.3.1
 platform: ruby
 authors: 
 - David Blei
@@ -10,7 +10,7 @@ autorequire:
 bindir: bin
 cert_chain: []
 
-date: 2009-07-24 00:00:00 -07:00
+date: 2009-08-11 00:00:00 -07:00
 default_executable: 
 dependencies: []
 
@@ -25,6 +25,7 @@ extra_rdoc_files:
 - README.markdown
 files: 
 - .gitignore
+- CHANGELOG
 - README
 - README.markdown
 - Rakefile