Question

是否可以在NLTK中获得短语的一致性？

import nltk
from nltk.corpus import PlaintextCorpusReader

corpus_loc = "c://temp//text//"
files = ".*\.txt"
read_corpus = PlaintextCorpusReader(corpus_loc, files)
corpus  = nltk.Text(read_corpus.words())
test = nltk.TextCollection(corpus_loc)

corpus.concordance("claim")

例如上面的返回

on okay okay okay i can give you the claim number and my information and
 decide on the shop okay okay so the claim number is xxxx - xx - xxxx got

现在，如果我尝试corpus.concordance("claim number")它不起作用...我确实有代码通过使用.partition()方法和相同的一些进一步编码来执行此操作...但我我想知道是否可以使用concordance来做同样的事情。

Answer 1

我把这个解决方案联系在一起......

def n_concordance_tokenised(text,phrase,left_margin=5,right_margin=5):
    #concordance replication via https://simplypython.wordpress.com/2014/03/14/saving-output-of-nltk-text-concordance/

    phraseList=phrase.split(' ')

    c = nltk.ConcordanceIndex(text.tokens, key = lambda s: s.lower())

    #Find the offset for each token in the phrase
    offsets=[c.offsets(x) for x in phraseList]
    offsets_norm=[]
    #For each token in the phraselist, find the offsets and rebase them to the start of the phrase
    for i in range(len(phraseList)):
        offsets_norm.append([x-i for x in offsets[i]])
    #We have found the offset of a phrase if the rebased values intersect
    #--
    # http://stackoverflow.com/a/3852792/454773
    #the intersection method takes an arbitrary amount of arguments
    #result = set(d[0]).intersection(*d[1:])
    #--
    intersects=set(offsets_norm[0]).intersection(*offsets_norm[1:])

    concordance_txt = ([text.tokens[map(lambda x: x-left_margin if (x-left_margin)&gt;0 else 0,[offset])[0]:offset+len(phraseList)+right_margin]
                    for offset in intersects])

    outputs=[''.join([x+' ' for x in con_sub]) for con_sub in concordance_txt]
    return outputs

def n_concordance(txt,phrase,left_margin=5,right_margin=5):
    tokens = nltk.word_tokenize(txt)
    text = nltk.Text(tokens)

    return

n_concordance_tokenised(text,phrase,left_margin=left_margin,right_margin=right_margin)

n_concordance_tokenised(text1,'monstrous size')
>> [u'one was of a most monstrous size . ... This came towards ',
    u'; for Whales of a monstrous size are oftentimes cast up dead ']

在Python中使用NLTK的短语的一致性

1 个答案: