01_simple.rb

require 'whatever/classifier'

classifier = Classifier.new

# training:
classifier.add_document(:text => "blah", :class => :a)
classifier.add_document(:text => "bleh", :class => :b)

# get model; training is automatically finalised
model = classifier.get_model

# do classification
puts model.classify(:text => "blah")        # OUTPUT: a

02_advanced.rb

require 'whatever/classifier'
require 'whatever/tokenizers/standard'
require 'whatever/preprocessors/stop_word_remover'
require 'whatever/preprocessors/kstemmer'

classifier = Classifier.new(:delayed_proprocessing => true)

tokenizer = StandardTokenizer.new
classifier.set_tokenizer(tokenizer)
# other useful tokenizers could be: PhraseTokenizer, KeyTermsTokenizer

stopper = StopWordRemover.new
classifier.add_preprocessor(stopper)

stemmer = KStemmer.new(:dictionary => 'english')
classifier.add_preprocessor(stemmer)

classifier.add_document(:id => 1, :text => "blah")
classifier.add_document(:id => 2, :text => "bleh", :class => :b)

classifer.set_class(:id => 1, :class => :a)

classifier.preprocess

# get model; training is automatically finalised
model = classifier.get_model

# do classification
puts model.classify(:text => "blah")        # OUTPUT: a