Contents

require File.expand_path('../language-detector', __FILE__)

TWEETS_FILENAME = "datasets/tweets_5000.txt"

training_sentences = File.readlines(TWEETS_FILENAME).map{ |tweet| tweet.normalize }
detector = LanguageDetector.new(:ngram_size => 2)
detector.train(30, training_sentences)
detector.yamlize("detector.yaml")

puts detector.classifier.get_prior_category_probability(0)
puts detector.classifier.get_prior_category_probability(1)

Version data entries

1 entries across 1 versions & 1 rubygems

Version	Path
unsupervised-language-detection-0.0.1	lib/unsupervised-language-detection/train-english-tweet-detector.rb