Python nltk.wordpunct_tokenize方法代码示例

# 需要导入模块: import nltk [as 别名]
# 或者: from nltk import wordpunct_tokenize [as 别名]
def tokenize(self, text):
        """
        Returns a list of individual tokens from the text utilizing NLTK's
        tokenize built in utility (far better than split on space). It also
        removes any stopwords and punctuation from the text, as well as
        ensure that every token is normalized.

        For now, token = word as in bag of words (the feature we're using).
        """
        for token in wordpunct_tokenize(text):
            token = self.normalize(token)
            if token in self.punctuation: continue
            if token in self.stopwords: continue
            yield token 

# 需要导入模块: import nltk [as 别名]
# 或者: from nltk import wordpunct_tokenize [as 别名]
def parse(sent):
    parser = nltk.ChartParser(grammar)
    tokens = nltk.wordpunct_tokenize(sent)
    return parser.parse(tokens) 

# 需要导入模块: import nltk [as 别名]
# 或者: from nltk import wordpunct_tokenize [as 别名]
def recommend(self, terms):
        """
        Given input list of ingredient terms,
        return the k closest matching recipes.

        :param terms: list of strings
        :return: list of document indices of documents
        """
        vect_doc = self.vect.transform(wordpunct_tokenize(terms))
        distance_matches = self.knn.transform(vect_doc)
        # the result is a list with a 2-tuple of arrays
        matches = distance_matches[0][1][0]
        # the matches are the indices of documents
        return matches 

# 需要导入模块: import nltk [as 别名]
# 或者: from nltk import wordpunct_tokenize [as 别名]
def query(self, terms):
        """
        Given input list of ingredient terms,
        return the k closest matching recipes.

        :param terms: list of strings
        :return: list of document indices of documents
        """
        vect_doc = self.transformer.named_steps['transform'].fit_transform(
            wordpunct_tokenize(terms)
        )
        dists, inds = self.tree.query(vect_doc, k=self.k)
        return inds[0] 

# 需要导入模块: import nltk [as 别名]
# 或者: from nltk import wordpunct_tokenize [as 别名]
def words(self, fileids=None, categories=None):
        """
        Uses the built in word tokenizer to extract tokens from sentences.
        Note that this method uses BeautifulSoup to parse HTML content.
        """
        for sentence in self.sents(fileids, categories):
            for token in wordpunct_tokenize(sentence):
                yield token 

# 需要导入模块: import nltk [as 别名]
# 或者: from nltk import wordpunct_tokenize [as 别名]
def tokenize(self, fileids=None, categories=None):
        """
        Segments, tokenizes, and tags a document in the corpus.
        """
        for paragraph in self.corpus.paras(fileids=fileid):
            yield [
                pos_tag(nltk.wordpunct_tokenize(sent))
                for sent in nltk.sent_tokenize(paragraph)
            ] 

# 需要导入模块: import nltk [as 别名]
# 或者: from nltk import wordpunct_tokenize [as 别名]
def tokenize(self, fileids=None, categories=None):
        """
        Segments, tokenizes, and tags a document in the corpus.
        """
        for paragraph in self.paras(fileids=fileids):
            yield [
                pos_tag(wordpunct_tokenize(sent))
                for sent in sent_tokenize(paragraph)
            ] 

# 需要导入模块: import nltk [as 别名]
# 或者: from nltk import wordpunct_tokenize [as 别名]
def describe(self, fileids=None, categories=None):
        """
        Performs a single pass of the corpus and
        returns a dictionary with a variety of metrics
        concerning the state of the corpus.
        """
        started = time.time()

        # Structures to perform counting.
        counts  = nltk.FreqDist()
        tokens  = nltk.FreqDist()

        # Perform single pass over paragraphs, tokenize and count
        for para in self.paras(fileids, categories):
            counts['paras'] += 1

            for sent in sent_tokenize(para):
                counts['sents'] += 1

                for word in wordpunct_tokenize(sent):
                    counts['words'] += 1
                    tokens[word] += 1

        # Compute the number of files and categories in the corpus
        n_fileids = len(self.resolve(fileids, categories) or self.fileids())
        n_topics  = len(self.categories(self.resolve(fileids, categories)))

        # Return data structure with information
        return {
            'files':  n_fileids,
            'topics': n_topics,
            'paras':  counts['paras'],
            'sents':  counts['sents'],
            'words':  counts['words'],
            'vocab':  len(tokens),
            'lexdiv': float(counts['words']) / float(len(tokens)),
            'ppdoc':  float(counts['paras']) / float(n_fileids),
            'sppar':  float(counts['sents']) / float(counts['paras']),
            'secs':   time.time() - started,
        } 

# 需要导入模块: import nltk [as 别名]
# 或者: from nltk import wordpunct_tokenize [as 别名]
def tokenize(self, fileid):
        """
        Segments, tokenizes, and tags a document in the corpus. Returns a
        generator of paragraphs, which are lists of sentences, which in turn
        are lists of part of speech tagged words.
        """
        for paragraph in self.corpus.paras(fileids=fileid):
            yield [
                pos_tag(wordpunct_tokenize(sent))
                for sent in sent_tokenize(paragraph)
            ] 

# 需要导入模块: import nltk [as 别名]
# 或者: from nltk import wordpunct_tokenize [as 别名]
def words(self):
        """
        Returns a generator of words.
        """
        for sent in self.sents():
            for word in nltk.wordpunct_tokenize(sent):
                yield word 

# 需要导入模块: import nltk [as 别名]
# 或者: from nltk import wordpunct_tokenize [as 别名]
def tagged_tokens(self):
        for sent in self.sents():
            for word in nltk.wordpunct_tokenize(sent):
                yield nltk.pos_tag(word) 

# 需要导入模块: import nltk [as 别名]
# 或者: from nltk import wordpunct_tokenize [as 别名]
def calculate_language_scores(text):
    """
    Calculate probability of given text to be written in several languages and
    return a dictionary that looks like {'french': 2, 'spanish': 4, 'english': 0}.

    :param text: Text to analyze.
    :type text: str

    :return: Dictionary with languages and unique stopwords seen in analyzed text.
    :rtype: dict(str -> int)

    :raises: TypeError
    """
    if not isinstance(text, basestring):
        raise TypeError("Expected basestring, got '%s' instead" % type(text))
    if not text:
        return {}

    languages_ratios = {}

    # Split the text into separate tokens, using natural language punctuation signs.
    tokens = wordpunct_tokenize(text)
    tokenized_words = [word.lower() for word in tokens]

    for language in stopwords.fileids():
        stopwords_set = set(stopwords.words(language))
        words_set = set(tokenized_words)
        common_elements = words_set.intersection(stopwords_set)
        languages_ratios[language] = len(common_elements)  # language "score"

    return languages_ratios


#------------------------------------------------------------------------------ 

# 需要导入模块: import nltk [as 别名]
# 或者: from nltk import wordpunct_tokenize [as 别名]
def normalize(sent):
    return wordpunct_tokenize(sent.lower()) 

# 需要导入模块: import nltk [as 别名]
# 或者: from nltk import wordpunct_tokenize [as 别名]
def tokenize(sent):
    tokens = tokenizer.tokenize(sent)
    ret = []
    for t in tokens:
        if '<' not in t:
            ret.extend(wordpunct_tokenize(t))
        else:
            ret.append(t)
    return ret 

# 需要导入模块: import nltk [as 别名]
# 或者: from nltk import wordpunct_tokenize [as 别名]
def tokenize_and_normalize(s):
    """Tokenize and normalize string."""
    token_list = []
    tokens = wordpunct_tokenize(s.lower())
    token_list.extend([x for x in tokens if not re.fullmatch('[' + string.punctuation + ']+', x)])
    return token_list