本文整理汇总了Python中nltk.metrics.BigramAssocMeasures.raw_freq方法的典型用法代码示例。如果您正苦于以下问题：Python BigramAssocMeasures.raw_freq方法的具体用法？Python BigramAssocMeasures.raw_freq怎么用？Python BigramAssocMeasures.raw_freq使用的例子？那么, 这里精选的方法代码示例或许可以为您提供帮助。您也可以进一步了解该方法所在类nltk.metrics.BigramAssocMeasures的用法示例。
在下文中一共展示了BigramAssocMeasures.raw_freq方法的2个代码示例，这些例子默认根据受欢迎程度排序。您可以为喜欢或者感觉有用的代码点赞，您的评价将有助于系统推荐出更棒的Python代码示例。
示例1: demo
# 需要导入模块: from nltk.metrics import BigramAssocMeasures [as 别名]
# 或者: from nltk.metrics.BigramAssocMeasures import raw_freq [as 别名]
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
# 需要导入模块: from nltk.metrics import BigramAssocMeasures [as 别名]
# 或者: from nltk.metrics.BigramAssocMeasures import raw_freq [as 别名]
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()