使用NLTK创建新的语料库我估计我的标题的答案通常是去阅读文档,但是我浏览了一下NLTK书但它没有给出答案。我对Python有点陌生。我有一堆.txt文件,我希望能够使用NLTK为该语料库提供的语料库功能。nltk_data.我试过PlaintextCorpusReader但我只能说:>>>import nltk>>>from nltk.corpus import PlaintextCorpusReader>>>corpus_root = './'>>>newcorpus = PlaintextCorpusReader(corpus_root, '.*')>>>newcorpus.words()如何分割newcorpus使用Punkt的句子?我试过使用Punkt函数,但是Punkt函数无法读取PlaintextCorpusReader班级,等级?你还能告诉我如何将分割后的数据写入文本文件吗?
3 回答
holdtom
TA贡献1805条经验 获得超10个赞
PlaintextCorpusReader
def __init__(self, root, fileids, word_tokenizer=WordPunctTokenizer(), sent_tokenizer=nltk.data.LazyLoader( 'tokenizers/punkt/english.pickle'), para_block_reader=read_blankline_block, encoding='utf8'):
nltk.data.LazyLoader('tokenizers/punkt/english.pickle')
.
>>> import nltk.data>>> text = """ ... Punkt knows that the periods in Mr. Smith and Johann S. Bach ... do not mark sentence boundaries. And sometimes sentences ... can start with non-capitalized words. i is a good variable ... name. ... """>>> tokenizer = nltk.data.load('tokenizers/punkt/english.pickle')>>> tokenizer.tokenize(text.strip())
皈依舞
TA贡献1851条经验 获得超3个赞
如何使用文本文件目录创建NLTK语料库?
newcorpus/ file1.txt file2.txt ...
import osfrom nltk.corpus.reader.plaintext import PlaintextCorpusReadercorpusdir = 'newcorpus/' # Directory of corpus.newcorpus = PlaintextCorpusReader(corpusdir, '.*')
注:PlaintextCorpusReader
nltk.tokenize.sent_tokenize()
nltk.tokenize.word_tokenize()
import osfrom nltk.corpus.reader.plaintext import PlaintextCorpusReader# Let's create a corpus with 2 texts in different textfile.txt1 = """This is a foo bar sentence.\nAnd this is the first txtfile in the corpus."""txt2 = """Are you a foo bar? Yes I am. Possibly, everyone is.\n"""corpus = [txt1,txt2]# Make new dir for the corpus.corpusdir = 'newcorpus/'if not os.path.isdir(corpusdir): os.mkdir(corpusdir)# Output the files into the directory.filename = 0for text in corpus: filename+=1 with open(corpusdir+str(filename)+'.txt','w') as fout: print>>fout, text# Check that our corpus do exist and the files are correct.assert os.path.isdir(corpusdir)for infile, text in zip(sorted(os.listdir(corpusdir)),corpus): assert open(corpusdir+infile,'r').read().strip() == text.strip()# Create a new corpus by specifying the parameters# (1) directory of the new corpus# (2) the fileids of the corpus# NOTE: in this case the fileids are simply the filenames.newcorpus = PlaintextCorpusReader('newcorpus/', '.*')# Access each file in the corpus.for infile in sorted(newcorpus.fileids()): print infile # The fileids of each file. with newcorpus.open(infile) as fin: # Opens the file. print fin.read().strip() # Prints the content of the fileprint# Access the plaintext; outputs pure string/basestring.print newcorpus.raw().strip()print # Access paragraphs in the corpus. (list of list of list of strings)# NOTE: NLTK automatically calls nltk.tokenize.sent_tokenize and # nltk.tokenize.word_tokenize.## Each element in the outermost list is a paragraph, and# Each paragraph contains sentence(s), and# Each sentence contains token(s)print newcorpus.paras()print# To access pargraphs of a specific fileid.print newcorpus.paras(newcorpus.fileids()[0])# Access sentences in the corpus. (list of list of strings)# NOTE: That the texts are flattened into sentences that contains tokens.print newcorpus.sents()print# To access sentences of a specific fileid.print newcorpus.sents(newcorpus.fileids()[0])# Access just tokens/words in the corpus. (list of strings)print newcorpus.words()# To access tokens of a specific fileid.print newcorpus.words(newcorpus.fileids()[0])
>>> from nltk.tokenize import sent_tokenize, word_tokenize>>> txt1 = """This is a foo bar sentence.\nAnd this is the first txtfile in the corpus.""">>> sent_tokenize(txt1)['This is a foo bar sentence.', 'And this is the first txtfile in the corpus.']>>> word_tokenize(sent_tokenize(txt1)[0])['This', 'is', 'a', 'foo', 'bar', 'sentence', '.']
慕森王
TA贡献1777条经验 获得超3个赞
>>> import nltk >>> from nltk.corpus import PlaintextCorpusReader >>> corpus_root = './' >>> newcorpus = PlaintextCorpusReader(corpus_root, '.*') """ if the ./ dir contains the file my_corpus.txt, then you can view say all the words it by doing this """ >>> newcorpus.words('my_corpus.txt')
添加回答
举报
0/150
提交
取消