最大熵

http://yeslib.com/detail/3637

* 最大熵的优缺点

* 情感分析

http://blog.csdn.net/laozhaokun/article/details/37937337

# -*- coding: utf-8 -*-
import nltk.classify.util
from nltk.classify import NaiveBayesClassifier
from nltk.corpus import movie_reviews


def word_feats(words):
    return dict([(word, True) for word in words])


negids = movie_reviews.fileids('neg')
posids = movie_reviews.fileids('pos')

negfeats = [(word_feats(movie_reviews.words(fileids=[f])), 'neg') for f in negids]
posfeats = [(word_feats(movie_reviews.words(fileids=[f])), 'pos') for f in posids]

negcutoff = len(negfeats) * 3 / 4
poscutoff = len(posfeats) * 3 / 4

trainfeats = negfeats[:negcutoff] + posfeats[:poscutoff]
testfeats = negfeats[negcutoff:] + posfeats[poscutoff:]
print 'train on %d instances, test on %d instances' % (len(trainfeats), len(testfeats))

# classifier = NaiveBayesClassifier.train(trainfeats)
classifier=MaxentClassifier.train(trainfeats,'megam',maxiter=1)
print 'accuracy:', nltk.classify.util.accuracy(classifier, testfeats)
classifier.show_most_informative_features()