本文整理汇总了Python中nltk.collocations.BigramCollocationFinder.nbest方法的典型用法代码示例。如果您正苦于以下问题：Python BigramCollocationFinder.nbest方法的具体用法？Python BigramCollocationFinder.nbest怎么用？Python BigramCollocationFinder.nbest使用的例子？那么恭喜您, 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.collocations.BigramCollocationFinder的用法示例。
在下文中一共展示了BigramCollocationFinder.nbest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: get_unibigram_features
# 需要导入模块: from nltk.collocations import BigramCollocationFinder [as 别名]
# 或者: from nltk.collocations.BigramCollocationFinder import nbest [as 别名]
def get_unibigram_features(all_words, uni_feanum, bi_feanum):
word_fd = nltk.FreqDist(all_words)
bigram_fd = nltk.FreqDist(nltk.bigrams(all_words))
if uni_feanum == 'max':
uni_feanum = len(list(word_fd.keys()))
elif uni_feanum > len(list(word_fd.keys())):
uni_feanum = len(list(word_fd.keys()))
if bi_feanum == 'max':
bi_feanum = len(list(bigram_fd.keys()))
elif bi_feanum > len(list(bigram_fd.keys())):
bi_feanum = len(list(bigram_fd.keys()))
finder = BigramCollocationFinder(word_fd, bigram_fd)
bigrams = finder.nbest(BigramAssocMeasures.chi_sq, bi_feanum)
print "the number of unigram features is", uni_feanum
print "the number of bigram features is", bi_feanum
featuples = word_fd.most_common(uni_feanum)
selected_words = []
for i in range(uni_feanum):
selected_words.append(featuples[i][0])
features = []
for ngram in itertools.chain(selected_words, bigrams):
features.append(ngram)
return features示例2: FreqDist
# 需要导入模块: from nltk.collocations import BigramCollocationFinder [as 别名]
# 或者: from nltk.collocations.BigramCollocationFinder import nbest [as 别名]
print "---------- 100 collocations -----------"
overall_text.collocations(num=100)
print "---------- ---------------- -----------"
print overall_text.concordance('Imperium')
index = nltk.text.ConcordanceIndex(master_tokens, key=lambda s:s.lower())
sys.exit(0)
from nltk import bigrams
from nltk import collocations
from nltk import FreqDist
from nltk.collocations import BigramCollocationFinder
# http://nltk.googlecode.com/svn/trunk/doc/howto/collocations.html
# http://stackoverflow.com/questions/9151326/python-nltk-find-collocations-without-dot-separated-words
bigram_measures = collocations.BigramAssocMeasures()
word_fd = FreqDist(master_tokens)
bigram_fd = FreqDist(bigrams(master_tokens))
finder = BigramCollocationFinder(word_fd, bigram_fd)
#finder.apply_word_filter(lambda w: w in ('.', ','))
# only when collocation occurs 3+ times
finder.apply_freq_filter(3)
scored = finder.score_ngrams(bigram_measures.raw_freq)
#print sorted(bigram for bigram, score in scored)
print "========================================="
print sorted(finder.nbest(bigram_measures.raw_freq,200),reverse=True)