Python wordnet.NOUN属性代码示例

# 需要导入模块: from nltk.corpus import wordnet [as 别名]
# 或者: from nltk.corpus.wordnet import NOUN [as 别名]
def tag_semantic_similarity(x, y, ic):
    mx = wn.morphy(x)
    my = wn.morphy(y)

    if mx is None or my is None:
        return 0

    synX = wn.synsets(mx, pos=wn.NOUN)
    synY = wn.synsets(my, pos=wn.NOUN)

    if len(synX) > 0 and len(synY) > 0:
        maxSim = synX[0].lin_similarity(synY[0], ic)
    else:
        maxSim = 0

    return maxSim 

# 需要导入模块: from nltk.corpus import wordnet [as 别名]
# 或者: from nltk.corpus.wordnet import NOUN [as 别名]
def pos_tag_convert_penn_to_wn(tag):
    """
    Convert POS tag from Penn tagset to WordNet tagset.

    :param tag: a tag from Penn tagset
    :return: a tag from WordNet tagset or None if no corresponding tag could be found
    """
    from nltk.corpus import wordnet as wn

    if tag in ['JJ', 'JJR', 'JJS']:
        return wn.ADJ
    elif tag in ['RB', 'RBR', 'RBS']:
        return wn.ADV
    elif tag in ['NN', 'NNS', 'NNP', 'NNPS']:
        return wn.NOUN
    elif tag in ['VB', 'VBD', 'VBG', 'VBN', 'VBP', 'VBZ']:
        return wn.VERB
    return None 

# 需要导入模块: from nltk.corpus import wordnet [as 别名]
# 或者: from nltk.corpus.wordnet import NOUN [as 别名]
def get_wordnet_pos(self,treebank_tag):
        """
        return WORDNET POS compliance to WORDENT lemmatization (a,n,r,v) 
        """

        if treebank_tag.startswith('J'):
            return wordnet.ADJ

        elif treebank_tag.startswith('V'):
            return wordnet.VERB

        elif treebank_tag.startswith('N'):
            return wordnet.NOUN

        elif treebank_tag.startswith('R'):
            return wordnet.ADV

        else:
            return wordnet.NOUN 

# 需要导入模块: from nltk.corpus import wordnet [as 别名]
# 或者: from nltk.corpus.wordnet import NOUN [as 别名]
def graph_synsets(terms, pos=wn.NOUN, depth=2):
    """
    Create a networkx graph of the given terms to the given depth.
    """

    G = nx.Graph(
        name="WordNet Synsets Graph for {}".format(", ".join(terms)), depth=depth,
    )

    def add_term_links(G, term, current_depth):
        for syn in wn.synsets(term):
            for name in syn.lemma_names():
                G.add_edge(term, name)
                if current_depth < depth:
                    add_term_links(G, name, current_depth+1)

    for term in terms:
        add_term_links(G, term, 0)

    return G 

# 需要导入模块: from nltk.corpus import wordnet [as 别名]
# 或者: from nltk.corpus.wordnet import NOUN [as 别名]
def pos_tag_text(text):
    
    def penn_to_wn_tags(pos_tag):
        if pos_tag.startswith('J'):
            return wn.ADJ
        elif pos_tag.startswith('V'):
            return wn.VERB
        elif pos_tag.startswith('N'):
            return wn.NOUN
        elif pos_tag.startswith('R'):
            return wn.ADV
        else:
            return None
    
    tagged_text = tag(text)
    tagged_lower_text = [(word.lower(), penn_to_wn_tags(pos_tag))
                         for word, pos_tag in
                         tagged_text]
    return tagged_lower_text
    
# lemmatize text based on POS tags 

# 需要导入模块: from nltk.corpus import wordnet [as 别名]
# 或者: from nltk.corpus.wordnet import NOUN [as 别名]
def _pos_tuples():
    return [
        (wn.NOUN,'N','noun'),
        (wn.VERB,'V','verb'),
        (wn.ADJ,'J','adj'),
        (wn.ADV,'R','adv')] 

# 需要导入模块: from nltk.corpus import wordnet [as 别名]
# 或者: from nltk.corpus.wordnet import NOUN [as 别名]
def get_wordnet_pos(treebank_tag):
    if treebank_tag.startswith('J'):
        return wordnet.ADJ
    elif treebank_tag.startswith('V'):
        return wordnet.VERB
    elif treebank_tag.startswith('N'):
        return wordnet.NOUN
    elif treebank_tag.startswith('R'):
        return wordnet.ADV
    else:
        return None 

# 需要导入模块: from nltk.corpus import wordnet [as 别名]
# 或者: from nltk.corpus.wordnet import NOUN [as 别名]
def lemmatize_word(word, pos=wordnet.NOUN):
    return LEMMATIZER.lemmatize(word, pos) 

# 需要导入模块: from nltk.corpus import wordnet [as 别名]
# 或者: from nltk.corpus.wordnet import NOUN [as 别名]
def lemmatize_sentence(sentence):
    res = []
    sentence_ = get_valid_words(sentence)
    for word, pos in pos_tag(sentence_):
        wordnet_pos = get_wordnet_pos(pos) or wordnet.NOUN
        res.append(lemmatize_word(word, pos=wordnet_pos))
    return res 

# 需要导入模块: from nltk.corpus import wordnet [as 别名]
# 或者: from nltk.corpus.wordnet import NOUN [as 别名]
def check_robustpca(trainCollection, testCollection, feature):
    ready = True
    
    # check matlab    
    if not check_matlab():
        print_msg('RobustPCA (%s, %s, %s)' % (trainCollection, testCollection, feature), 'Matlab is not available or incorrectly configured.')
        ready = False
    
    # check if knn is available
    if not check_knn(trainCollection, testCollection, feature):
        print_msg('RobustPCA (%s, %s, %s)' % (trainCollection, testCollection, feature), 'KNN is not available.')        
        ready = False

    # check data files
    datafiles = [ os.path.join(ROOT_PATH, trainCollection, 'TextData', 'id.userid.lemmtags.txt'),
                  os.path.join(ROOT_PATH, trainCollection, 'FeatureData', feature)]
    res = find_missing_files(datafiles)
    if res:
        print_msg('RobustPCA (%s, %s, %s)' % (trainCollection, testCollection, feature), 'the following files or folders are missing:\n%s' % res)
        return False    
              
    # check external dependencies  
    try:
        import h5py
        import numpy
        import scipy.io
        import scipy.sparse
        from nltk.corpus import wordnet as wn
        from nltk.corpus import wordnet_ic
        brown_ic = wordnet_ic.ic('ic-brown.dat')
        wn.morphy('cat')
        wn.synsets('cat', pos=wn.NOUN)
    except Exception, e:
        try:
            import nltk
            nltk.download('brown')
            nltk.download('wordnet')
            nltk.download('wordnet_ic')
        except Exception, e:
            print e
            ready = False 

# 需要导入模块: from nltk.corpus import wordnet [as 别名]
# 或者: from nltk.corpus.wordnet import NOUN [as 别名]
def wup_similarity(tagx, tagy):
    scores = []
    for pos in [wn.NOUN, wn.VERB, wn.ADJ, wn.ADJ_SAT, wn.ADV]:
        try:
            synsetx = wn.synset('%s.%s.01' % (tagx,pos))
            synsety = wn.synset('%s.%s.01' % (tagy,pos))
            score = synsetx.wup_similarity(synsety)
            if score is None:
                score = 0
        except Exception, e:
            score = 0
        scores.append(score) 

# 需要导入模块: from nltk.corpus import wordnet [as 别名]
# 或者: from nltk.corpus.wordnet import NOUN [as 别名]
def test_pos_tag_convert_penn_to_wn():
    assert pos_tag_convert_penn_to_wn('JJ') == wn.ADJ
    assert pos_tag_convert_penn_to_wn('RB') == wn.ADV
    assert pos_tag_convert_penn_to_wn('NN') == wn.NOUN
    assert pos_tag_convert_penn_to_wn('VB') == wn.VERB

    for tag in ('', 'invalid', None):
        assert pos_tag_convert_penn_to_wn(tag) is None 

# 需要导入模块: from nltk.corpus import wordnet [as 别名]
# 或者: from nltk.corpus.wordnet import NOUN [as 别名]
def __get_wordnet_pos(self, treebank_tag):

        if treebank_tag.startswith("J"):
            return wordnet.ADJ
        elif treebank_tag.startswith("V"):
            return wordnet.VERB
        elif treebank_tag.startswith("N"):
            return wordnet.NOUN
        elif treebank_tag.startswith("R"):
            return wordnet.ADV
        else:
            return "" 

# 需要导入模块: from nltk.corpus import wordnet [as 别名]
# 或者: from nltk.corpus.wordnet import NOUN [as 别名]
def tagwn(self, tag):
        """
        Returns the WordNet tag from the Penn Treebank tag.
        """
        return {
            'N': wn.NOUN,
            'V': wn.VERB,
            'R': wn.ADV,
            'J': wn.ADJ
        }.get(tag[0], wn.NOUN) 

# 需要导入模块: from nltk.corpus import wordnet [as 别名]
# 或者: from nltk.corpus.wordnet import NOUN [as 别名]
def get_wordnet_pos(treebank_tag):
        """ Converts a Penn Tree-Bank part of speech tag into a corresponding WordNet-friendly tag. 
        Borrowed from: http://stackoverflow.com/questions/15586721/wordnet-lemmatization-and-pos-tagging-in-python. """
        if treebank_tag.startswith('J') or treebank_tag.startswith('A'):
            return wordnet.ADJ
        elif treebank_tag.startswith('V'):
            return wordnet.VERB
        elif treebank_tag.startswith('N'):
            return wordnet.NOUN
        elif treebank_tag.startswith('R'):
            return wordnet.ADV
        else:
            return 'OTHER'