ealdent-lda-ruby 0.2.3 → 0.3.0

data/.gitignore

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

data/README

@@ -7,16 +7,15 @@ The original C code relied on files for the input and output. We felt it was nec
 Example usage:
 
 require 'lda'
-lda = Lda::Lda.new      # create an Lda object for training
 corpus = Lda::Corpus.new("data/data_file.dat")
-lda.corpus = corpus
-lda.em("random")        # run EM algorithm using random starting points
+lda = Lda::Lda.new(corpus)      # create an Lda object for training
+lda.em("random")                # run EM algorithm using random starting points
 lda.load_vocabulary("data/vocab.txt")
-lda.print_topics(20)    # print the topic 20 words per topic
+lda.print_topics(20)            # print the topic 20 words per topic
 
-See the rdocs for further information. You can also 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, since the people who monitor that are very knowledgeable.
+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, since the people who monitor that are very knowledgeable.
 
 
 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. 
+Blei, David M., Ng, Andrew Y., and Jordan, Michael I. 2003. Latent dirichlet allocation. Journal of Machine Learning Research. 3 (Mar. 2003), 993-1022.

data/README.markdown

@@ -8,19 +8,17 @@ The original C code relied on files for the input and output. We felt it was nec
 
 ### Example usage:
 
-    require 'lda'
-    lda = Lda::Lda.new      # create an Lda object for training
+    require 'lda-ruby'
     corpus = Lda::Corpus.new("data/data_file.dat")
-    lda.corpus = corpus
-    lda.em("random")        # run EM algorithm using random starting points
+    lda = Lda::Lda.new(corpus)    # create an Lda object for training
+    lda.em("random")              # run EM algorithm using random starting points
     lda.load_vocabulary("data/vocab.txt")
-    lda.print_topics(20)    # print the topic 20 words per topic
+    lda.print_topics(20)          # print the topic 20 words per topic
 
-See the rdocs for further information. You can also 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, since the people who monitor that are very knowledgeable.
+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.
 
 ## Resources
 
-
 + [Blog post about LDA-Ruby][lda-ruby]
 + [David Blei's lda-c code][blei]
 + [Wikipedia article on LDA][wikipedia]
@@ -29,11 +27,12 @@ See the rdocs for further information. You can also check out the mailing list f
 
 ## 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]]. 
+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]].
 
 [svmlight]: http://svmlight.joachims.org
 [lda-ruby]: http://mendicantbug.com/2008/11/17/lda-in-ruby/
 [blei]: http://www.cs.princeton.edu/~blei/lda-c/
 [wikipedia]: http://en.wikipedia.org/wiki/Latent_Dirichlet_allocation
 [ap-data]: http://www.cs.princeton.edu/~blei/lda-c/ap.tgz
-[pdf]: http://www.cs.princeton.edu/picasso/mats/BleiNgJordan2003_blei.pdf
+[pdf]: http://www.cs.princeton.edu/picasso/mats/BleiNgJordan2003_blei.pdf
+[topic-models]: https://lists.cs.princeton.edu/mailman/listinfo/topic-models

data/Rakefile

@@ -0,0 +1,58 @@
+require 'rubygems'
+require 'rake'
+
+begin
+  require 'jeweler'
+  Jeweler::Tasks.new do |gem|
+    gem.name = "lda-ruby"
+    gem.summary = %Q{Ruby port of Latent Dirichlet Allocation by David M. Blei.}
+    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.extensions = ['ext/lda-ruby/extconf.rb']
+    gem.require_paths = ['lib', 'ext']
+    # gem is a Gem::Specification... see http://www.rubygems.org/read/chapter/20 for additional settings
+  end
+
+rescue LoadError
+  puts "Jeweler (or a dependency) not available. Install it with: sudo gem install jeweler"
+end
+
+require 'rake/testtask'
+Rake::TestTask.new(:test) do |test|
+  test.libs << 'lib' << 'test'
+  test.pattern = 'test/**/*_test.rb'
+  test.verbose = true
+end
+
+begin
+  require 'rcov/rcovtask'
+  Rcov::RcovTask.new do |test|
+    test.libs << 'test'
+    test.pattern = 'test/**/*_test.rb'
+    test.verbose = true
+  end
+rescue LoadError
+  task :rcov do
+    abort "RCov is not available. In order to run rcov, you must: sudo gem install spicycode-rcov"
+  end
+end
+
+task :default => :test
+
+require 'rake/rdoctask'
+Rake::RDocTask.new do |rdoc|
+  if File.exist?('VERSION.yml')
+    config = YAML.load(File.read('VERSION.yml'))
+    version = "#{config[:major]}.#{config[:minor]}.#{config[:patch]}"
+  else
+    version = ""
+  end
+
+  rdoc.rdoc_dir = 'rdoc'
+  rdoc.title = "lda-ruby #{version}"
+  rdoc.rdoc_files.include('README*')
+  rdoc.rdoc_files.include('lib/**/*.rb')
+end
+

data/VERSION.yml

@@ -1,4 +1,4 @@
 --- 
-:patch: 3
 :major: 0
-:minor: 2
+:minor: 3
+:patch: 0

data/ext/lda-ruby/Makefile

@@ -0,0 +1,181 @@
+
+SHELL = /bin/sh
+
+#### Start of system configuration section. ####
+
+srcdir = .
+topdir = /home/taf2/.local/include/ruby-1.9.1
+hdrdir = /home/taf2/.local/include/ruby-1.9.1
+arch_hdrdir = /home/taf2/.local/include/ruby-1.9.1/$(arch)
+VPATH = $(srcdir):$(arch_hdrdir)/ruby:$(hdrdir)/ruby
+prefix = $(DESTDIR)/home/taf2/.local
+exec_prefix = $(prefix)
+vendorhdrdir = $(rubyhdrdir)/vendor_ruby
+sitehdrdir = $(rubyhdrdir)/site_ruby
+rubyhdrdir = $(includedir)/$(RUBY_INSTALL_NAME)-$(ruby_version)
+vendordir = $(libdir)/$(RUBY_INSTALL_NAME)/vendor_ruby
+sitedir = $(libdir)/$(RUBY_INSTALL_NAME)/site_ruby
+mandir = $(datarootdir)/man
+localedir = $(datarootdir)/locale
+libdir = $(exec_prefix)/lib
+psdir = $(docdir)
+pdfdir = $(docdir)
+dvidir = $(docdir)
+htmldir = $(docdir)
+infodir = $(datarootdir)/info
+docdir = $(datarootdir)/doc/$(PACKAGE)
+oldincludedir = $(DESTDIR)/usr/include
+includedir = $(prefix)/include
+localstatedir = $(prefix)/var
+sharedstatedir = $(prefix)/com
+sysconfdir = $(prefix)/etc
+datadir = $(datarootdir)
+datarootdir = $(prefix)/share
+libexecdir = $(exec_prefix)/libexec
+sbindir = $(exec_prefix)/sbin
+bindir = $(exec_prefix)/bin
+rubylibdir = $(libdir)/$(ruby_install_name)/$(ruby_version)
+archdir = $(rubylibdir)/$(arch)
+sitelibdir = $(sitedir)/$(ruby_version)
+sitearchdir = $(sitelibdir)/$(sitearch)
+vendorlibdir = $(vendordir)/$(ruby_version)
+vendorarchdir = $(vendorlibdir)/$(sitearch)
+
+CC = gcc
+CXX = g++
+LIBRUBY = $(LIBRUBY_SO)
+LIBRUBY_A = lib$(RUBY_SO_NAME)-static.a
+LIBRUBYARG_SHARED = -Wl,-R -Wl,$(libdir) -L$(libdir) -l$(RUBY_SO_NAME)
+LIBRUBYARG_STATIC = -Wl,-R -Wl,$(libdir) -L$(libdir) -l$(RUBY_SO_NAME)-static
+OUTFLAG = -o 
+COUTFLAG = -o 
+
+RUBY_EXTCONF_H = 
+cflags   = $(optflags) $(debugflags) $(warnflags)
+optflags = -O0
+debugflags = -g3 -ggdb
+warnflags = -Wall -Wno-parentheses
+CFLAGS   =  -fPIC  $(cflags)  -fPIC -Wall -ggdb -O0 
+INCFLAGS = -I. -I$(arch_hdrdir) -I$(hdrdir)/ruby/backward -I$(hdrdir) -I$(srcdir)
+DEFS     = 
+CPPFLAGS = -D USE_RUBY  $(DEFS) $(cppflags)
+CXXFLAGS = $(CFLAGS)  $(cxxflags)
+ldflags  = -L.  -rdynamic -Wl,-export-dynamic
+dldflags = 
+archflag = 
+DLDFLAGS = $(ldflags) $(dldflags) $(archflag)
+LDSHARED = $(CC) -shared
+LDSHAREDXX = $(CXX) -shared
+AR = ar
+EXEEXT = 
+
+RUBY_INSTALL_NAME = ruby
+RUBY_SO_NAME = ruby
+arch = x86_64-linux
+sitearch = x86_64-linux
+ruby_version = 1.9.1
+ruby = /home/taf2/.local/bin/ruby
+RUBY = $(ruby)
+RM = rm -f
+RM_RF = $(RUBY) -run -e rm -- -rf
+RMDIRS = $(RUBY) -run -e rmdir -- -p
+MAKEDIRS = mkdir -p
+INSTALL = /usr/bin/install -c
+INSTALL_PROG = $(INSTALL) -m 0755
+INSTALL_DATA = $(INSTALL) -m 644
+COPY = cp
+
+#### End of system configuration section. ####
+
+preload = 
+
+libpath = . $(libdir)
+LIBPATH =  -L. -L$(libdir) -Wl,-R$(libdir)
+DEFFILE = 
+
+CLEANFILES = mkmf.log
+DISTCLEANFILES = 
+DISTCLEANDIRS = 
+
+extout = 
+extout_prefix = 
+target_prefix = 
+LOCAL_LIBS = 
+LIBS = $(LIBRUBYARG_SHARED)  -lpthread -lrt -ldl -lcrypt -lm   -lc
+SRCS = lda-model.c lda-data.c utils.c lda-alpha.c cokus.c lda-inference.c
+OBJS = lda-model.o lda-data.o utils.o lda-alpha.o cokus.o lda-inference.o
+TARGET = lda_ext
+DLLIB = $(TARGET).so
+EXTSTATIC = 
+STATIC_LIB = 
+
+BINDIR        = $(bindir)
+RUBYCOMMONDIR = $(sitedir)$(target_prefix)
+RUBYLIBDIR    = $(sitelibdir)$(target_prefix)
+RUBYARCHDIR   = $(sitearchdir)$(target_prefix)
+HDRDIR        = $(rubyhdrdir)/ruby$(target_prefix)
+ARCHHDRDIR    = $(rubyhdrdir)/$(arch)/ruby$(target_prefix)
+
+TARGET_SO     = $(DLLIB)
+CLEANLIBS     = $(TARGET).so 
+CLEANOBJS     = *.o  *.bak
+
+all:    $(DLLIB)
+static: $(STATIC_LIB)
+
+clean-rb-default::
+clean-rb::
+clean-so::
+clean: clean-so clean-rb-default clean-rb
+		@-$(RM) $(CLEANLIBS) $(CLEANOBJS) $(CLEANFILES)
+
+distclean-rb-default::
+distclean-rb::
+distclean-so::
+distclean: clean distclean-so distclean-rb-default distclean-rb
+		@-$(RM) Makefile $(RUBY_EXTCONF_H) conftest.* mkmf.log
+		@-$(RM) core ruby$(EXEEXT) *~ $(DISTCLEANFILES)
+		@-$(RMDIRS) $(DISTCLEANDIRS)
+
+realclean: distclean
+install: install-so install-rb
+
+install-so: $(RUBYARCHDIR)
+install-so: $(RUBYARCHDIR)/$(DLLIB)
+$(RUBYARCHDIR)/$(DLLIB): $(DLLIB)
+	$(INSTALL_PROG) $(DLLIB) $(RUBYARCHDIR)
+install-rb: pre-install-rb install-rb-default
+install-rb-default: pre-install-rb-default
+pre-install-rb: Makefile
+pre-install-rb-default: Makefile
+$(RUBYARCHDIR):
+	$(MAKEDIRS) $@
+
+site-install: site-install-so site-install-rb
+site-install-so: install-so
+site-install-rb: install-rb
+
+.SUFFIXES: .c .m .cc .cxx .cpp .C .o
+
+.cc.o:
+	$(CXX) $(INCFLAGS) $(CPPFLAGS) $(CXXFLAGS) $(COUTFLAG)$@ -c $<
+
+.cxx.o:
+	$(CXX) $(INCFLAGS) $(CPPFLAGS) $(CXXFLAGS) $(COUTFLAG)$@ -c $<
+
+.cpp.o:
+	$(CXX) $(INCFLAGS) $(CPPFLAGS) $(CXXFLAGS) $(COUTFLAG)$@ -c $<
+
+.C.o:
+	$(CXX) $(INCFLAGS) $(CPPFLAGS) $(CXXFLAGS) $(COUTFLAG)$@ -c $<
+
+.c.o:
+	$(CC) $(INCFLAGS) $(CPPFLAGS) $(CFLAGS) $(COUTFLAG)$@ -c $<
+
+$(DLLIB): $(OBJS) Makefile
+	@-$(RM) $(@)
+	$(LDSHARED) -o $@ $(OBJS) $(LIBPATH) $(DLDFLAGS) $(LOCAL_LIBS) $(LIBS)
+
+
+
+$(OBJS): $(hdrdir)/ruby.h $(hdrdir)/ruby/defines.h $(arch_hdrdir)/ruby/config.h

data/ext/lda-ruby/extconf.rb

@@ -0,0 +1,9 @@
+ENV["ARCHFLAGS"] = "-arch #{`uname -p` =~ /powerpc/ ? 'ppc' : 'i386'}"
+
+require 'mkmf'
+
+$CFLAGS << ' -Wall -ggdb -O0'
+$defs.push( "-D USE_RUBY" )
+
+dir_config('lda-ruby/lda')
+create_makefile("lda-ruby/lda")

data/{lib → ext/lda-ruby}/lda-inference.c

@@ -34,7 +34,7 @@
 #ifdef USE_RUBY
 #include "ruby.h"
 
-VALUE rb_mLda;
+VALUE rb_cLdaModule;
 VALUE rb_cLda;
 VALUE rb_cLdaCorpus;
 VALUE rb_cLdaDocument;
@@ -83,7 +83,7 @@ double lda_inference(document* doc, lda_model* model, double* var_gamma, double*
           printf("phi for term: %d of %d\n", index, model->num_terms);
 				  phi[n][k] = 0.0;
         }
-        else { 
+        else {
 				  phi[n][k] =
 				  	digamma_gam[k] +
 				  	model->log_prob_w[k][index];
@@ -142,7 +142,7 @@ double compute_likelihood(document* doc, lda_model* model, double** phi, double*
 	for (k = 0; k < model->num_topics; k++)
 	{
 		likelihood += (model->alpha - 1)*(dig[k] - digsum) + lgamma(var_gamma[k]) - (var_gamma[k] - 1)*(dig[k] - digsum);
-		
+
 		for (n = 0; n < doc->length; n++)
 		{
 			if (phi[n][k] > 0)
@@ -261,7 +261,7 @@ void run_em(char* start, char* directory, corpus* corpus) {
 	    } else {
             quiet_lda_mle(model, ss, 0);
 	    }
-		    
+
 		model->alpha = INITIAL_ALPHA;
 	} else if (strcmp(start, "random")==0) {
 		model = new_lda_model(corpus->num_terms, NTOPICS);
@@ -499,7 +499,7 @@ void run_quiet_em(char* start, corpus* corpus) {
 
 	lda_suffstats* ss = NULL;
 	if (strncmp(start, "seeded",6)==0) {
-		model = new_lda_model(corpus->num_terms, NTOPICS);
+		model = quiet_new_lda_model(corpus->num_terms, NTOPICS);
 		model->alpha = INITIAL_ALPHA;
 		ss = new_lda_suffstats(model);
 		if (VERBOSE) {
@@ -513,7 +513,7 @@ void run_quiet_em(char* start, corpus* corpus) {
       quiet_lda_mle(model, ss, 0);
 		}
 	} else if (strncmp(start, "fixed",5)==0) {
-	  model = new_lda_model(corpus->num_terms, NTOPICS);
+	  model = quiet_new_lda_model(corpus->num_terms, NTOPICS);
     model->alpha = INITIAL_ALPHA;
 	  ss = new_lda_suffstats(model);
 	  corpus_initialize_fixed_ss(ss, model, corpus);
@@ -523,7 +523,7 @@ void run_quiet_em(char* start, corpus* corpus) {
       quiet_lda_mle(model, ss, 0);
     }
 	} else if (strncmp(start, "random",6)==0) {
-		model = new_lda_model(corpus->num_terms, NTOPICS);
+		model = quiet_new_lda_model(corpus->num_terms, NTOPICS);
 		model->alpha = INITIAL_ALPHA;
 		ss = new_lda_suffstats(model);
 		random_initialize_ss(ss, model);
@@ -605,7 +605,7 @@ void run_quiet_em(char* start, corpus* corpus) {
 
 /*
  * Set all of the settings in one command:
- * 
+ *
  *  * init_alpha
  *  * num_topics
  *  * max_iter
@@ -710,7 +710,7 @@ static VALUE wrap_get_num_topics(VALUE self) {
  */
 static VALUE wrap_set_initial_alpha(VALUE self, VALUE initial_alpha) {
 	INITIAL_ALPHA = (float)NUM2DBL(initial_alpha);
-	
+
 	return initial_alpha;
 }
 
@@ -719,7 +719,7 @@ static VALUE wrap_set_initial_alpha(VALUE self, VALUE initial_alpha) {
  */
 static VALUE wrap_set_num_topics(VALUE self, VALUE ntopics) {
 	NTOPICS = NUM2INT(ntopics);
-	
+
 	return ntopics;
 }
 
@@ -735,7 +735,7 @@ static VALUE wrap_get_estimate_alpha(VALUE self) {
  */
 static VALUE wrap_set_estimate_alpha(VALUE self, VALUE est_alpha) {
 	ESTIMATE_ALPHA = NUM2INT(est_alpha);
-	
+
 	return est_alpha;
 }
 
@@ -760,7 +760,7 @@ static VALUE wrap_set_verbosity(VALUE self, VALUE verbosity) {
     } else {
         VERBOSE = FALSE;
     }
-    
+
     return verbosity;
 }
 
@@ -777,7 +777,7 @@ static VALUE wrap_set_verbosity(VALUE self, VALUE verbosity) {
 static VALUE wrap_em(VALUE self, VALUE start) {
 	if (!corpus_loaded)
 		return Qnil;
-	
+
 	run_quiet_em(STR2CSTR(start), last_corpus);
 
 	return Qnil;
@@ -815,7 +815,7 @@ static VALUE wrap_ruby_corpus(VALUE self, VALUE rcorpus) {
 	corpus* c;
 	int i = 0;
 	int j = 0;
-	
+
 	c = malloc(sizeof(corpus));
 	c->num_terms = NUM2INT(rb_iv_get(rcorpus, "@num_terms"));
 	c->num_docs = NUM2INT(rb_iv_get(rcorpus, "@num_docs"));
@@ -825,7 +825,7 @@ static VALUE wrap_ruby_corpus(VALUE self, VALUE rcorpus) {
 		VALUE one_doc = rb_ary_entry(doc_ary, i);
 		VALUE words = rb_iv_get(one_doc, "@words");
 		VALUE counts = rb_iv_get(one_doc, "@counts");
-		
+
 		c->docs[i].length = NUM2INT(rb_iv_get(one_doc, "@length"));
 		c->docs[i].total = NUM2INT(rb_iv_get(one_doc, "@total"));
 		c->docs[i].words = malloc(sizeof(int) * c->docs[i].length);
@@ -834,18 +834,18 @@ static VALUE wrap_ruby_corpus(VALUE self, VALUE rcorpus) {
 			int one_word = NUM2INT(rb_ary_entry(words, j));
 			int one_count = NUM2INT(rb_ary_entry(counts, j));
       if( one_word > c->num_terms ) {
-        rb_raise(rb_eRuntimeError, "error term count(%d) less then word index(%d)", c->num_terms, one_word);
+        rb_raise(rb_eRuntimeError, "error term count(%d) less than word index(%d)", c->num_terms, one_word);
       }
 			c->docs[i].words[j] = one_word;
 			c->docs[i].counts[j] = one_count;
 		}
 	}
-	
+
 	last_corpus = c;
 	corpus_loaded = TRUE;
-	
+
 	rb_iv_set(self, "@corpus", rcorpus);
-	
+
 	return Qtrue;
 }
 
@@ -856,11 +856,11 @@ static VALUE wrap_ruby_corpus(VALUE self, VALUE rcorpus) {
 static VALUE wrap_get_gamma(VALUE self) {
 	if (!model_loaded)
 		return Qnil;
-	
+
 	// last_gamma is a double[num_docs][num_topics]
 	VALUE arr;
 	int i = 0, j = 0;
-	
+
 	arr = rb_ary_new2(last_corpus->num_docs);
 	for (i = 0; i < last_corpus->num_docs; i++) {
 		VALUE arr2 = rb_ary_new2(last_model->num_topics);
@@ -869,7 +869,7 @@ static VALUE wrap_get_gamma(VALUE self) {
 		}
 		rb_ary_store(arr, i, arr2);
 	}
-	
+
 	return arr;
 }
 
@@ -882,31 +882,31 @@ static VALUE wrap_get_gamma(VALUE self) {
 static VALUE wrap_get_phi(VALUE self) {
     if (!model_loaded)
         return Qnil;
-    
+
     VALUE arr = rb_ary_new2(last_corpus->num_docs);
     int i = 0, j = 0, k = 0;
-    
+
     //int max_length = max_corpus_length(last_corpus);
     short error = 0;
-    
+
     for (i = 0; i < last_corpus->num_docs; i++) {
         VALUE arr1 = rb_ary_new2(last_corpus->docs[i].length);
-        
+
         lda_inference(&(last_corpus->docs[i]), last_model, last_gamma[i], last_phi, &error);
-        
+
         for (j = 0; j < last_corpus->docs[i].length; j++) {
             VALUE arr2 = rb_ary_new2(last_model->num_topics);
-            
+
             for (k = 0; k < last_model->num_topics; k++) {
                 rb_ary_store(arr2, k, rb_float_new(last_phi[j][k]));
             }
-            
+
             rb_ary_store(arr1, j, arr2);
         }
-        
+
         rb_ary_store(arr, i, arr1);
     }
-    
+
     return arr;
 }
 
@@ -918,11 +918,11 @@ static VALUE wrap_get_phi(VALUE self) {
 static VALUE wrap_get_model_beta(VALUE self) {
 	if (!model_loaded)
 		return Qnil;
-		
+
 	// beta is a double[num_topics][num_terms]
 	VALUE arr;
 	int i = 0, j = 0;
-	
+
 	arr = rb_ary_new2(last_model->num_topics);
 	for (i = 0; i < last_model->num_topics; i++) {
 		VALUE arr2 = rb_ary_new2(last_model->num_terms);
@@ -931,7 +931,7 @@ static VALUE wrap_get_model_beta(VALUE self) {
 		}
 		rb_ary_store(arr, i, arr2);
 	}
-	
+
 	return arr;
 }
 
@@ -944,28 +944,27 @@ static VALUE wrap_get_model_settings(VALUE self) {
 		return Qnil;
 
 	VALUE arr;
-	
+
 	arr = rb_ary_new();
 	rb_ary_push(arr, rb_int_new(last_model->num_topics));
 	rb_ary_push(arr, rb_int_new(last_model->num_terms));
 	rb_ary_push(arr, rb_float_new(last_model->alpha));
-	
+
 	return arr;		//	[num_topics, num_terms, alpha]
 }
 
 
-void Init_lda_ext() {
+void Init_lda() {
   corpus_loaded = FALSE;
   model_loaded = FALSE;
   VERBOSE = TRUE;
 
-  rb_require("lda");
-
-  rb_mLda = rb_define_module("Lda");
-  rb_cLda = rb_define_class_under(rb_mLda, "Lda", rb_cObject);
-  rb_cLdaCorpus = rb_define_class_under(rb_mLda, "Corpus", rb_cObject);
-  rb_cLdaDocument = rb_define_class_under(rb_mLda, "Document", rb_cObject);
+  rb_require("lda-ruby");
 
+  rb_cLdaModule   = rb_define_module("Lda");
+  rb_cLda         = rb_define_class_under(rb_cLdaModule, "Lda", rb_cObject);
+  rb_cLdaCorpus   = rb_define_class_under(rb_cLdaModule, "Corpus", rb_cObject);
+  rb_cLdaDocument = rb_define_class_under(rb_cLdaModule, "Document", rb_cObject);
 
   // method to load the corpus
   rb_define_method(rb_cLda, "fast_load_corpus_from_file", wrap_load_corpus, 1);
@@ -988,7 +987,7 @@ void Init_lda_ext() {
   rb_define_method(rb_cLda, "em_max_iter", wrap_get_em_max_iter, 0);
   rb_define_method(rb_cLda, "em_max_iter=", wrap_set_em_max_iter, 1);
   rb_define_method(rb_cLda, "em_convergence", wrap_get_em_converged, 0);
-  rb_define_method(rb_cLda, "em_convergence=", wrap_set_em_converged, 1);	
+  rb_define_method(rb_cLda, "em_convergence=", wrap_set_em_converged, 1);
   rb_define_method(rb_cLda, "init_alpha=", wrap_set_initial_alpha, 1);
   rb_define_method(rb_cLda, "init_alpha", wrap_get_initial_alpha, 0);
   rb_define_method(rb_cLda, "est_alpha=", wrap_set_estimate_alpha, 1);