本文整理匯總了Python中nltk.metrics.BigramAssocMeasures.likelihood_ratio方法的典型用法代碼示例。如果您正苦於以下問題：Python BigramAssocMeasures.likelihood_ratio方法的具體用法？Python BigramAssocMeasures.likelihood_ratio怎麽用？Python BigramAssocMeasures.likelihood_ratio使用的例子？那麽, 這裏精選的方法代碼示例或許可以為您提供幫助。您也可以進一步了解該方法所在類nltk.metrics.BigramAssocMeasures的用法示例。
在下文中一共展示了BigramAssocMeasures.likelihood_ratio方法的2個代碼示例，這些例子默認根據受歡迎程度排序。您可以為喜歡或者感覺有用的代碼點讚，您的評價將有助於係統推薦出更棒的Python代碼示例。
示例1: demo
# 需要導入模塊: from nltk.metrics import BigramAssocMeasures [as 別名]
# 或者: from nltk.metrics.BigramAssocMeasures import likelihood_ratio [as 別名]
def demo(scorer=None, compare_scorer=None):
"""Finds bigram collocations in the files of the WebText corpus."""
from nltk.metrics import BigramAssocMeasures, spearman_correlation, ranks_from_scores
if scorer is None:
scorer = BigramAssocMeasures.likelihood_ratio
if compare_scorer is None:
compare_scorer = BigramAssocMeasures.raw_freq
from nltk.corpus import stopwords, webtext
ignored_words = stopwords.words('english')
word_filter = lambda w: len(w) < 3 or w.lower() in ignored_words
for file in webtext.fileids():
words = [word.lower()
for word in webtext.words(file)]
cf = BigramCollocationFinder.from_words(words)
cf.apply_freq_filter(3)
cf.apply_word_filter(word_filter)
corr = spearman_correlation(ranks_from_scores(cf.score_ngrams(scorer)),
ranks_from_scores(cf.score_ngrams(compare_scorer)))
print(file)
print('\t', [' '.join(tup) for tup in cf.nbest(scorer, 15)])
print('\t Correlation to %s: %0.4f' % (compare_scorer.__name__, corr))
# Slows down loading too much
# bigram_measures = BigramAssocMeasures()
# trigram_measures = TrigramAssocMeasures() 示例2: demo
# 需要導入模塊: from nltk.metrics import BigramAssocMeasures [as 別名]
# 或者: from nltk.metrics.BigramAssocMeasures import likelihood_ratio [as 別名]
def demo(scorer=None, compare_scorer=None):
"""Finds bigram collocations in the files of the WebText corpus."""
from nltk.metrics import BigramAssocMeasures, spearman_correlation, ranks_from_scores
if scorer is None:
scorer = BigramAssocMeasures.likelihood_ratio
if compare_scorer is None:
compare_scorer = BigramAssocMeasures.raw_freq
from nltk.corpus import stopwords, webtext
ignored_words = stopwords.words('english')
word_filter = lambda w: len(w) < 3 or w.lower() in ignored_words
for file in webtext.fileids():
words = [word.lower()
for word in webtext.words(file)]
cf = BigramCollocationFinder.from_words(words)
cf.apply_freq_filter(3)
cf.apply_word_filter(word_filter)
print(file)
print('\t', [' '.join(tup) for tup in cf.nbest(scorer, 15)])
print('\t Correlation to %s: %0.4f' % (compare_scorer.__name__,
spearman_correlation(
ranks_from_scores(cf.score_ngrams(scorer)),
ranks_from_scores(cf.score_ngrams(compare_scorer)))))
# Slows down loading too much
# bigram_measures = BigramAssocMeasures()
# trigram_measures = TrigramAssocMeasures()