Whitespace

Author: samoli

LICENSE

@@ -146,7 +146,7 @@ such a program is covered only if its contents constitute a work based
 on the Library (independent of the use of the Library in a tool for
 writing it).  Whether that is true depends on what the Library does
 and what the program that uses the Library does.
-  
+
   1. You may copy and distribute verbatim copies of the Library's
 complete source code as you receive it, in any medium, provided that
 you conspicuously and appropriately publish on each copy an
@@ -426,4 +426,4 @@ the Free Software Foundation.
   14. If you wish to incorporate parts of the Library into other free
 programs whose distribution conditions are incompatible with these,
 write to the author to ask for permission.  For software which is
-copyrighted by
+copyrighted by

README.markdown

@@ -31,7 +31,7 @@ A Bayesian classifier by Lucas Carlson. Bayesian Classifiers are accurate, fast,
     b.train_interesting "here are some good words. I hope you love them"
     b.train_uninteresting "here are some bad words, I hate you"
     b.classify "I hate bad words and you" # returns 'Uninteresting'
-    
+
     require 'madeleine'
     m = SnapshotMadeleine.new("bayes_data") {
         Classifier::Bayes.new 'Interesting', 'Uninteresting'
@@ -52,8 +52,8 @@ Using Madeleine, your application can persist the learned data over time.
 ## LSI
 
 A Latent Semantic Indexer by David Fayram. Latent Semantic Indexing engines
-are not as fast or as small as Bayesian classifiers, but are more flexible, providing 
-fast search and clustering detection as well as semantic analysis of the text that 
+are not as fast or as small as Bayesian classifiers, but are more flexible, providing
+fast search and clustering detection as well as semantic analysis of the text that
 theoretically simulates human learning.
 
 ### Usage
@@ -66,27 +66,27 @@ theoretically simulates human learning.
               ["This text also involves cats. Cats!", :cat],
               ["This text involves birds. Birds.",:bird ]]
     strings.each {|x| lsi.add_item x.first, x.last}
-  
+
     lsi.search("dog", 3)
-    # returns => ["This text deals with dogs. Dogs.", "This text involves dogs too. Dogs! ", 
+    # returns => ["This text deals with dogs. Dogs.", "This text involves dogs too. Dogs! ",
     #             "This text also involves cats. Cats!"]
 
     lsi.find_related(strings[2], 2)
     # returns => ["This text revolves around cats. Cats.", "This text also involves cats. Cats!"]
-  
+
     lsi.classify "This text is also about dogs!"
     # returns => :dog
-  
+
 Please see the Classifier::LSI documentation for more information. It is possible to index, search and classify
-with more than just simple strings. 
+with more than just simple strings.
 
 ### Latent Semantic Indexing
 
 * http://www.c2.com/cgi/wiki?LatentSemanticIndexing
 * http://www.chadfowler.com/index.cgi/Computing/LatentSemanticIndexing.rdoc
 * http://en.wikipedia.org/wiki/Latent_semantic_analysis
 
-## Authors    
+## Authors
 
 * Lucas Carlson  ([email protected])
 * David Fayram II ([email protected])

install.rb

@@ -37,7 +37,7 @@
 files = FileList["**/*"]
 
 # File::safe_unlink *deprecated.collect{|f| File.join($sitedir, f.split(/\//))}
-files.each {|f| 
+files.each {|f|
   File::install(f, File.join($sitedir, *f.split(/\//)), 0644, true)
 }
 

lib/classifier.rb

@@ -27,4 +27,4 @@
 require 'rubygems'
 require 'classifier/extensions/string'
 require 'classifier/bayes'
-require 'classifier/lsi'
+require 'classifier/lsi'

lib/classifier/bayes.rb

@@ -6,7 +6,7 @@ module Classifier
 
 class Bayes
   # The class can be created with one or more categories, each of which will be
-  # initialized and given a training method. E.g., 
+  # initialized and given a training method. E.g.,
   #      b = Classifier::Bayes.new 'Interesting', 'Uninteresting', 'Spam'
 	def initialize(*categories)
 		@categories = Hash.new
@@ -56,7 +56,7 @@ def untrain(category, text)
 			end
 		end
 	end
-		
+
 	#
 	# Returns the scores in each category the provided +text+. E.g.,
 	#    b.classifications "I hate bad words and you"
@@ -80,14 +80,14 @@ def classifications(text)
 	end
 
   #
-  # Returns the classification of the provided +text+, which is one of the 
+  # Returns the classification of the provided +text+, which is one of the
   # categories given in the initializer. E.g.,
   #    b.classify "I hate bad words and you"
   #    =>  'Uninteresting'
 	def classify(text)
 		(classifications(text).sort_by { |a| -a[1] })[0][0]
 	end
-	
+
 	#
 	# Provides training and untraining methods for the categories specified in Bayes#new
 	# For example:
@@ -106,7 +106,7 @@ def method_missing(name, *args)
 	    super  #raise StandardError, "No such method: #{name}"
 		end
 	end
-	
+
 	#
 	# Provides a list of category names
 	# For example:
@@ -115,7 +115,7 @@ def method_missing(name, *args)
 	def categories # :nodoc:
 		@categories.keys.collect {|c| c.to_s}
 	end
-	
+
 	#
 	# Allows you to add categories to the classifier.
 	# For example:
@@ -128,7 +128,7 @@ def categories # :nodoc:
 	def add_category(category)
 		@categories[category.prepare_category_name] = Hash.new
 	end
-	
+
 	alias append_category add_category
 end
 

lib/classifier/extensions/vector.rb

@@ -1,5 +1,5 @@
 # Author::    Ernest Ellingson
-# Copyright:: Copyright (c) 2005 
+# Copyright:: Copyright (c) 2005
 
 # These are extensions to the std-lib 'matrix' to allow an all ruby SVD
 
@@ -9,7 +9,7 @@
 class Array
   def sum(identity = 0, &block)
     return identity unless size > 0
-  
+
     if block_given?
       map(&block).sum
     else
@@ -22,7 +22,7 @@ class Vector
   def magnitude
     sumsqs = 0.0
     self.size.times do |i|
-      sumsqs += self[i] ** 2.0 
+      sumsqs += self[i] ** 2.0
     end
     Math.sqrt(sumsqs)
   end
@@ -42,7 +42,7 @@ class Matrix
   def Matrix.diag(s)
      Matrix.diagonal(*s)
   end
-  
+
   alias :trans :transpose
 
   def SV_decomp(maxSweeps = 20)
@@ -51,7 +51,7 @@ def SV_decomp(maxSweeps = 20)
     else
       q = self * self.trans
     end
-    
+
     qrot    = q.dup
     v       = Matrix.identity(q.row_size)
     azrot   = nil
@@ -75,16 +75,16 @@ def SV_decomp(maxSweeps = 20)
           mzrot[col,col] = hcos
           qrot = mzrot.trans * qrot * mzrot
           v = v * mzrot
-        end 
+        end
       end
       s_old = qrot.dup if cnt == 1
-      sum_qrot = 0.0 
+      sum_qrot = 0.0
       if cnt > 1
         qrot.row_size.times do |r|
           sum_qrot += (qrot[r,r]-s_old[r,r]).abs if (qrot[r,r]-s_old[r,r]).abs > 0.001
         end
         s_old = qrot.dup
-      end 
+      end
       break if (sum_qrot <= 0.001 and cnt > 1) or cnt >= maxSweeps
     end # of do while true
     s = []
@@ -93,7 +93,7 @@ def SV_decomp(maxSweeps = 20)
     end
     #puts "cnt = #{cnt}"
     if self.row_size >= self.column_size
-      mu = self *  v * Matrix.diagonal(*s).inverse     
+      mu = self *  v * Matrix.diagonal(*s).inverse
       return [mu, v, s]
     else
       puts v.row_size

lib/classifier/extensions/vector_serialize.rb

@@ -1,17 +1,17 @@
 module GSL
-  
+
   class Vector
     def _dump(v)
       Marshal.dump( self.to_a )
     end
-    
+
     def self._load(arr)
       arry = Marshal.load(arr)
       return GSL::Vector.alloc(arry)
     end
-    
+
   end
-  
+
   class Matrix
      class <<self
         alias :diag :diagonal

lib/classifier/extensions/word_hash.rb

@@ -4,20 +4,20 @@
 
 require "set"
 
-# These are extensions to the String class to provide convenience 
+# These are extensions to the String class to provide convenience
 # methods for the Classifier package.
 class String
-  
-  # Removes common punctuation symbols, returning a new string. 
+
+  # Removes common punctuation symbols, returning a new string.
   # E.g.,
   #   "Hello (greeting's), with {braces} < >...?".without_punctuation
   #   => "Hello  greetings   with  braces         "
   def without_punctuation
     tr( ',?.!;:"@#$%^&*()_=+[]{}\|<>/`~', " " ) .tr( "'\-", "")
   end
-  
+
   # Return a Hash of strings => ints. Each word in the string is stemmed,
-  # interned, and indexes to its frequency in the document.  
+  # interned, and indexes to its frequency in the document.
 	def word_hash
 		word_hash = clean_word_hash()
 		symbol_hash = word_hash_for_symbols(gsub(/[\w]/," ").split)
@@ -28,9 +28,9 @@ def word_hash
 	def clean_word_hash
 		word_hash_for_words gsub(/[^\w\s]/,"").split
 	end
-	
+
 	private
-	
+
 	def word_hash_for_words(words)
 		d = Hash.new(0)
 		words.each do |word|
@@ -50,7 +50,7 @@ def word_hash_for_symbols(words)
 		end
 		return d
 	end
-	
+
 	CORPUS_SKIP_WORDS = Set.new([
       "a",
       "again",