lda-ruby 0.3.1 → 0.3.4

data/README.markdown

@@ -15,7 +15,7 @@ The original C code relied on files for the input and output. We felt it was nec
     lda.load_vocabulary("data/vocab.txt")
     lda.print_topics(20)          # print the topic 20 words per topic
 
-You can check out the mailing list for this project if you have any questions or mail lda-ruby@groups.google.com [email link]. If you have general questions about Latent Dirichlet Allocation, I urge you to use the [topic models mailing list][topic-models], since the people who monitor that are very knowledgeable.
+If you have general questions about Latent Dirichlet Allocation, I urge you to use the [topic models mailing list][topic-models], since the people who monitor that are very knowledgeable.  If you encounter bugs specific to lda-ruby, please post an issue on the Github project.
 
 ## Resources
 
@@ -24,7 +24,6 @@ You can check out the mailing list for this project if you have any questions or
 + [Wikipedia article on LDA][wikipedia]
 + [Sample AP data][ap-data]
 
-
 ## References
 
 Blei, David M., Ng, Andrew Y., and Jordan, Michael I. 2003. Latent dirichlet allocation. Journal of Machine Learning Research. 3 (Mar. 2003), 993-1022 [[pdf][pdf]].

data/Rakefile

@@ -1,5 +1,6 @@
 require 'rubygems'
 require 'rake'
+require 'yaml'
 
 begin
   require 'jeweler'
@@ -9,9 +10,10 @@ begin
     gem.description = %Q{Ruby port of Latent Dirichlet Allocation by David M. Blei. See http://www.cs.princeton.edu/~blei/lda-c/.}
     gem.email = "jasonmadams@gmail.com"
     gem.homepage = "http://github.com/ealdent/lda-ruby"
-    gem.authors = ['David Blei', 'Jason Adams']
+    gem.authors = ['David Blei', 'Jason Adams', 'Rio Akasaka']
     gem.extensions = ['ext/lda-ruby/extconf.rb']
     gem.require_paths = ['lib', 'ext']
+    gem.add_dependency 'shoulda'
     # gem is a Gem::Specification... see http://www.rubygems.org/read/chapter/20 for additional settings
   end
 

data/VERSION.yml

@@ -1,4 +1,5 @@
 --- 
 :major: 0
 :minor: 3
-:patch: 1
+:patch: 4
+:build: 

data/ext/lda-ruby/lda-inference.c

@@ -778,7 +778,7 @@ static VALUE wrap_em(VALUE self, VALUE start) {
 	if (!corpus_loaded)
 		return Qnil;
 
-	run_quiet_em(STR2CSTR(start), last_corpus);
+	run_quiet_em(StringValuePtr(start), last_corpus);
 
 	return Qnil;
 }
@@ -788,7 +788,7 @@ static VALUE wrap_em(VALUE self, VALUE start) {
  * Load settings from the given file.
  */
 static VALUE wrap_load_settings(VALUE self, VALUE settings_file) {
-	read_settings(STR2CSTR(settings_file));
+	read_settings(StringValuePtr(settings_file));
 
 	return Qtrue;
 }
@@ -800,7 +800,7 @@ static VALUE wrap_load_settings(VALUE self, VALUE settings_file) {
  */
 static VALUE wrap_load_corpus(VALUE self, VALUE filename) {
 	if (!corpus_loaded) {
-		last_corpus = read_data(STR2CSTR(filename));
+		last_corpus = read_data(StringValuePtr(filename));
 		corpus_loaded = TRUE;
 		return Qtrue;
 	} else {

data/ext/lda-ruby/lda-model.h

@@ -15,6 +15,8 @@
 void free_lda_model(lda_model*);
 void save_lda_model(lda_model*, char*);
 lda_model* new_lda_model(int, int);
+lda_model* quiet_new_lda_model(int num_terms, int num_topics);
+lda_model* new_lda_model(int num_terms, int num_topics);
 lda_suffstats* new_lda_suffstats(lda_model* model);
 void free_lda_suffstats(lda_model* model, lda_suffstats* ss);
 void corpus_initialize_ss(lda_suffstats* ss, lda_model* model, corpus* c);

data/lda-ruby.gemspec

@@ -1,78 +1,76 @@
 # Generated by jeweler
-# DO NOT EDIT THIS FILE
-# Instead, edit Jeweler::Tasks in Rakefile, and run `rake gemspec`
+# DO NOT EDIT THIS FILE DIRECTLY
+# 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 = "0.3.1"
+  s.version = "0.3.4"
 
   s.required_rubygems_version = Gem::Requirement.new(">= 0") if s.respond_to? :required_rubygems_version=
-  s.authors = ["David Blei", "Jason Adams"]
-  s.date = %q{2009-08-11}
+  s.authors = ["David Blei", "Jason Adams", "Rio Akasaka"]
+  s.date = %q{2011-07-29}
   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"]
   s.extra_rdoc_files = [
     "README",
-     "README.markdown"
+    "README.markdown"
   ]
   s.files = [
-    ".gitignore",
-     "CHANGELOG",
-     "README",
-     "README.markdown",
-     "Rakefile",
-     "VERSION.yml",
-     "ext/lda-ruby/Makefile",
-     "ext/lda-ruby/cokus.c",
-     "ext/lda-ruby/cokus.h",
-     "ext/lda-ruby/extconf.rb",
-     "ext/lda-ruby/lda-alpha.c",
-     "ext/lda-ruby/lda-alpha.h",
-     "ext/lda-ruby/lda-data.c",
-     "ext/lda-ruby/lda-data.h",
-     "ext/lda-ruby/lda-inference.c",
-     "ext/lda-ruby/lda-inference.h",
-     "ext/lda-ruby/lda-model.c",
-     "ext/lda-ruby/lda-model.h",
-     "ext/lda-ruby/lda.h",
-     "ext/lda-ruby/utils.c",
-     "ext/lda-ruby/utils.h",
-     "lda-ruby.gemspec",
-     "lib/lda-ruby.rb",
-     "lib/lda-ruby/corpus/corpus.rb",
-     "lib/lda-ruby/corpus/data_corpus.rb",
-     "lib/lda-ruby/corpus/directory_corpus.rb",
-     "lib/lda-ruby/corpus/text_corpus.rb",
-     "lib/lda-ruby/document/data_document.rb",
-     "lib/lda-ruby/document/document.rb",
-     "lib/lda-ruby/document/text_document.rb",
-     "lib/lda-ruby/vocabulary.rb",
-     "license.txt",
-     "test/data/.gitignore",
-     "test/data/docs.dat",
-     "test/data/wiki-test-docs.yml",
-     "test/lda_ruby_test.rb",
-     "test/test_helper.rb"
+    "CHANGELOG",
+    "README",
+    "README.markdown",
+    "Rakefile",
+    "VERSION.yml",
+    "ext/lda-ruby/Makefile",
+    "ext/lda-ruby/cokus.c",
+    "ext/lda-ruby/cokus.h",
+    "ext/lda-ruby/extconf.rb",
+    "ext/lda-ruby/lda-alpha.c",
+    "ext/lda-ruby/lda-alpha.h",
+    "ext/lda-ruby/lda-data.c",
+    "ext/lda-ruby/lda-data.h",
+    "ext/lda-ruby/lda-inference.c",
+    "ext/lda-ruby/lda-inference.h",
+    "ext/lda-ruby/lda-model.c",
+    "ext/lda-ruby/lda-model.h",
+    "ext/lda-ruby/lda.h",
+    "ext/lda-ruby/utils.c",
+    "ext/lda-ruby/utils.h",
+    "lda-ruby.gemspec",
+    "lib/lda-ruby.rb",
+    "lib/lda-ruby/corpus/corpus.rb",
+    "lib/lda-ruby/corpus/data_corpus.rb",
+    "lib/lda-ruby/corpus/directory_corpus.rb",
+    "lib/lda-ruby/corpus/text_corpus.rb",
+    "lib/lda-ruby/document/data_document.rb",
+    "lib/lda-ruby/document/document.rb",
+    "lib/lda-ruby/document/text_document.rb",
+    "lib/lda-ruby/vocabulary.rb",
+    "license.txt",
+    "test/data/.gitignore",
+    "test/data/docs.dat",
+    "test/data/sample.rb",
+    "test/data/wiki-test-docs.yml",
+    "test/lda_ruby_test.rb",
+    "test/test_helper.rb"
   ]
   s.homepage = %q{http://github.com/ealdent/lda-ruby}
-  s.rdoc_options = ["--charset=UTF-8"]
   s.require_paths = ["lib", "ext"]
-  s.rubygems_version = %q{1.3.4}
+  s.rubygems_version = %q{1.6.2}
   s.summary = %q{Ruby port of Latent Dirichlet Allocation by David M. Blei.}
-  s.test_files = [
-    "test/lda_ruby_test.rb",
-     "test/test_helper.rb"
-  ]
 
   if s.respond_to? :specification_version then
-    current_version = Gem::Specification::CURRENT_SPECIFICATION_VERSION
     s.specification_version = 3
 
-    if Gem::Version.new(Gem::RubyGemsVersion) >= Gem::Version.new('1.2.0') then
+    if Gem::Version.new(Gem::VERSION) >= Gem::Version.new('1.2.0') then
+      s.add_runtime_dependency(%q<shoulda>, [">= 0"])
     else
+      s.add_dependency(%q<shoulda>, [">= 0"])
     end
   else
+    s.add_dependency(%q<shoulda>, [">= 0"])
   end
 end
+

data/test/data/sample.rb

@@ -0,0 +1,20 @@
+#!/usr/bin/ruby
+
+require 'rubygems'
+require 'lda-ruby'
+
+# Load the Corpus.  The AP data from David Blei's website is in the "DataCorpus" format
+corpus = Lda::DataCorpus.new("ap/ap.dat")
+
+# Initialize the Lda instance with the corpus
+lda = Lda::Lda.new(corpus)
+
+# Run the EM algorithm using random starting points.  Fixed starting points will use the first n documents
+# to initialize the topics, where n is the number of topics.
+lda.em("random")              # run EM algorithm using random starting points
+
+# Load the vocabulary file necessary with DataCorpus objects
+lda.load_vocabulary("ap/vocab.txt")
+
+# Print the top 20 words per topic
+lda.print_topics(20)

data/test/lda_ruby_test.rb

@@ -110,7 +110,7 @@ class LdaRubyTest < Test::Unit::TestCase
 
     context "An Lda::DataCorpus instance loaded from a file" do
       setup do
-        @filename = 'data/docs.dat'
+        @filename = File.join(File.dirname(__FILE__), 'data', 'docs.dat')
         @filetext = File.open(@filename, 'r') { |f| f.read }
         @corpus = Lda::DataCorpus.new(@filename)
       end
@@ -126,7 +126,7 @@ class LdaRubyTest < Test::Unit::TestCase
 
     context "An Lda::TextCorpus instance loaded from a file" do
       setup do
-        @filename = 'data/wiki-test-docs.yml'
+        @filename = File.join(File.dirname(__FILE__), 'data', 'wiki-test-docs.yml')
         @filedocs = YAML::load_file(@filename)
         @corpus = Lda::TextCorpus.new(@filename)
       end
@@ -142,13 +142,13 @@ class LdaRubyTest < Test::Unit::TestCase
 
     context "An Lda::DirectoryCorpus instance loaded from a directory" do
       setup do
-        @path = 'data/tmp'
+        @path = File.join(File.dirname(__FILE__), 'data', 'tmp')
         @extension = 'txt'
         Dir.mkdir(@path)
-        @original_filename = 'data/wiki-test-docs.yml'
+        @original_filename = File.join(File.dirname(__FILE__), 'data', 'wiki-test-docs.yml')
         @filedocs = YAML::load_file(@original_filename)
         @filedocs.each_with_index do |doc, idx|
-          File.open("data/tmp/doc_#{idx + 1}.txt", 'w') { |f| f.write(doc) }
+          File.open(File.join(@path, "doc_#{idx + 1}.txt"), 'w') { |f| f.write(doc) }
         end
 
         @corpus = Lda::DirectoryCorpus.new(@path, @extension)
@@ -173,11 +173,11 @@ class LdaRubyTest < Test::Unit::TestCase
     setup do
       @vocab = Lda::Vocabulary.new
       @words = ['word1', 'word2', 'word3', 'word4', 'word5', 'word6']
-      @filename1 = 'data/tmp_file.txt'
+      @filename1 = File.join(File.dirname(__FILE__), 'data', 'tmp_file.txt')
       File.open(@filename1, 'w') do |f|
         @words.each { |w| f.write("#{w}\n") }
       end
-      @filename2 = 'data/tmp_file.yml'
+      @filename2 = File.join(File.dirname(__FILE__), 'data', 'tmp_file.yml')
       File.open(@filename2, 'w') { |f| YAML::dump(@words, f) }
     end
 
@@ -208,7 +208,7 @@ class LdaRubyTest < Test::Unit::TestCase
 
   context "An Lda::Lda instance" do
     setup do
-      @filename = 'data/wiki-test-docs.yml'
+      @filename = File.join(File.dirname(__FILE__), 'data', 'wiki-test-docs.yml')
       @filedocs = YAML::load_file(@filename)
       @corpus = Lda::TextCorpus.new(@filename)
 

data/test/test_helper.rb

@@ -1,6 +1,7 @@
 require 'rubygems'
 require 'test/unit'
 require 'shoulda'
+require 'yaml'
 
 $LOAD_PATH.unshift(File.join(File.dirname(__FILE__), '..', 'lib'))
 $LOAD_PATH.unshift(File.dirname(__FILE__))

metadata

@@ -1,30 +1,39 @@
---- !ruby/object:Gem::Specification 
+--- !ruby/object:Gem::Specification
 name: lda-ruby
-version: !ruby/object:Gem::Version 
-  version: 0.3.1
+version: !ruby/object:Gem::Version
+  version: 0.3.4
+  prerelease: 
 platform: ruby
-authors: 
+authors:
 - David Blei
 - Jason Adams
+- Rio Akasaka
 autorequire: 
 bindir: bin
 cert_chain: []
-
-date: 2009-08-11 00:00:00 -04:00
+date: 2011-07-29 00:00:00.000000000 -04:00
 default_executable: 
-dependencies: []
-
+dependencies:
+- !ruby/object:Gem::Dependency
+  name: shoulda
+  requirement: &2161566540 !ruby/object:Gem::Requirement
+    none: false
+    requirements:
+    - - ! '>='
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :runtime
+  prerelease: false
+  version_requirements: *2161566540
 description: Ruby port of Latent Dirichlet Allocation by David M. Blei. See http://www.cs.princeton.edu/~blei/lda-c/.
 email: jasonmadams@gmail.com
 executables: []
-
-extensions: 
+extensions:
 - ext/lda-ruby/extconf.rb
-extra_rdoc_files: 
+extra_rdoc_files:
 - README
 - README.markdown
-files: 
-- .gitignore
+files:
 - CHANGELOG
 - README
 - README.markdown
@@ -58,38 +67,34 @@ files:
 - license.txt
 - test/data/.gitignore
 - test/data/docs.dat
+- test/data/sample.rb
 - test/data/wiki-test-docs.yml
 - test/lda_ruby_test.rb
 - test/test_helper.rb
 has_rdoc: true
 homepage: http://github.com/ealdent/lda-ruby
 licenses: []
-
 post_install_message: 
-rdoc_options: 
-- --charset=UTF-8
-require_paths: 
+rdoc_options: []
+require_paths:
 - lib
 - ext
-required_ruby_version: !ruby/object:Gem::Requirement 
-  requirements: 
-  - - ">="
-    - !ruby/object:Gem::Version 
-      version: "0"
-  version: 
-required_rubygems_version: !ruby/object:Gem::Requirement 
-  requirements: 
-  - - ">="
-    - !ruby/object:Gem::Version 
-      version: "0"
-  version: 
+required_ruby_version: !ruby/object:Gem::Requirement
+  none: false
+  requirements:
+  - - ! '>='
+    - !ruby/object:Gem::Version
+      version: '0'
+required_rubygems_version: !ruby/object:Gem::Requirement
+  none: false
+  requirements:
+  - - ! '>='
+    - !ruby/object:Gem::Version
+      version: '0'
 requirements: []
-
 rubyforge_project: 
-rubygems_version: 1.3.4
+rubygems_version: 1.6.2
 signing_key: 
 specification_version: 3
 summary: Ruby port of Latent Dirichlet Allocation by David M. Blei.
-test_files: 
-- test/lda_ruby_test.rb
-- test/test_helper.rb
+test_files: []

data/.gitignore

@@ -1,5 +0,0 @@
-*.o
-*.bundle
-*.tmproj
-pkg
-test/blei