Python nltk.corpus.wordnet.morphy() Examples

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 

def wordnet_similarity_matrix(embeddings):
    """
    Makes a similarity matrix from WordNet.
    Embeddings argument is only used to get set of words to use.
    """
    sim_mat = np.zeros((len(embeddings.iw), len(embeddings.iw)))
    words = {word:wn.morphy(word) for word in embeddings.iw}
    lemmas = {lemma:word for word, lemma in words.iteritems()}
    for i, word in enumerate(words):
        if words[word] == None:
            continue
        synonyms = set(chain.from_iterable([o_word.lemma_names() 
            for o_word in wn.synsets(words[word])]))
        for o_word in synonyms:
            if o_word in lemmas:
                sim_mat[embeddings.wi[word], embeddings.wi[lemmas[o_word]]] = 1.
    print np.sum(sim_mat)
    np.fill_diagonal(sim_mat, 0)
    return sim_mat 

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 

def get(self, k, default=None):
        try:
            return self[k]
        except KeyError as e:
            if self._lowercase_if_OOV:
                lowercased = k.lower()
                if lowercased in self.vocabulary:
                    return self[lowercased]
            if self._lemmatize_if_OOV:
                lemma = wordnet.morphy(k)
                if lemma in self.vocabulary:
                    return self[lemma]
            return default 

def get_multi(self, k, default=None):
        try:
            return self.multi_vectors[self.vocabulary[k]]
        except KeyError as e:
            if self._lowercase_if_OOV:
                lowercased = k.lower()
                if lowercased in self.vocabulary:
                    return self.multi_vectors[self.vocabulary[lowercased]]
            if self._lemmatize_if_OOV:
                lemma = wordnet.morphy(k)
                if lemma in self.vocabulary:
                    return self.multi_vectors[self.vocabulary[lemma]]
            return default 

def obtain_linguistic_relationships(word):
    word = word.strip('"')
    linguistic_relationships = []
    linguistic_relationships.append(('copy', word))
    base_word = wn.morphy(word)
    if base_word == None:
        base_word = word.lower()
    if word != base_word:
        linguistic_relationships.append(('inflection', base_word))
    linguistic_relationships.extend(\
      [('synonym', lemma) for lemma in obtain_synonyms(word)])
    linguistic_relationships.extend(\
      [('hypernym', lemma) for lemma in obtain_hypernyms(word)])
    linguistic_relationships.extend(\
      [('hyponym', lemma) for lemma in obtain_hyponyms(word)])
    linguistic_relationships.extend(\
      [('holonym', lemma) for lemma in obtain_holonyms(word)])
    linguistic_relationships.extend(\
      [('meronym', lemma) for lemma in obtain_meronyms(word)])
    linguistic_relationships.extend(\
      [('antonym', lemma) for lemma in obtain_antonyms(word)])
    linguistic_relationships.extend(\
      [('entailed', lemma) for lemma in obtain_entailments(word)])
    linguistic_relationships.extend(\
      [('derivation', lemma) for lemma in obtain_derivations(word)])
    return linguistic_relationships

# Check if word1 is synonym of word2, but checking whether the intersection
# between the synset of word1 and the synset of word2.
# If word1 = 'car' and word2 = 'automobile', this function should return True. 

def get_verbocean_relations(verb1, verb2):
    if verb1 in verbocean and verb2 in verbocean[verb1]:
        return set(verbocean[verb1][verb2])
    return set()

# Find linguistic relationship between two words.
# Remaining relationships that I would like to implement:
# linguistic_relationship('man', 'men') would return 'plural'.
# linguistic_relationship('go', 'went') would return 'present'.
# BUG: linguistic_relationship('man', 'men') returns
#   ['synonym', 'hypernym', 'hyponym'] because 'man' and 'men' have the same
#   lemma but wn.morphy cannot recognize it. We should detect this and prevent
#   those relationships from triggering. However,
#   linguistic_relationship('woman', 'women') returns ['inflection'] as expected,
#   until we implement the 'plural' relationship. 

def linguistic_relationship(word1, word2):
    (word1, word2) = (word1.strip('"'), word2.strip('"'))
    if word1 == word2:
        return ['copy']
    base_word1 = wn.morphy(word1)
    base_word2 = wn.morphy(word2)
    if base_word1 == None:
        base_word1 = word1.lower()
    if base_word2 == None:
        base_word2 = word2.lower()
    ling_relations = []
    if word1 != word2 and base_word1 == base_word2:
        return ['inflection']
    if is_synonym(base_word1, base_word2):
        ling_relations.append('synonym')
    if is_hypernym(base_word1, base_word2):
        ling_relations.append('hyponym')
    if is_hyponym(base_word1, base_word2):
        ling_relations.append('hypernym')
    if is_similar(base_word1, base_word2):
        ling_relations.append('similar')
    if is_holonym(base_word1, base_word2):
        ling_relations.append('holonym')
    if is_meronym(base_word1, base_word2):
        ling_relations.append('meronym')
    if is_antonym(base_word1, base_word2):
        ling_relations.append('antonym')
    if is_entailed(base_word1, base_word2):
        ling_relations.append('entailed')
    if is_derivation(word1, word2):
        ling_relations.append('derivation')
    # Typical types of verbocean relations are "happens-before" or "stronger-than"
    ling_relations.extend(get_verbocean_relations(base_word1, base_word2))
    return ling_relations 

def page_from_reference(href):
    '''
    Returns a tuple of the HTML page built and the new current word

    :param href: The hypertext reference to be solved
    :type href: str
    :return: A tuple (page,word), where page is the new current HTML page
             to be sent to the browser and
             word is the new current word
    :rtype: A tuple (str,str)
    '''
    word = href.word
    pos_forms = defaultdict(list)
    words = word.split(',')
    words = [w for w in [w.strip().lower().replace(' ', '_')
                         for w in words]
             if w != ""]
    if len(words) == 0:
        # No words were found.
        return "", "Please specify a word to search for."

    # This looks up multiple words at once.  This is probably not
    # necessary and may lead to problems.
    for w in words:
        for pos in [wn.NOUN, wn.VERB, wn.ADJ, wn.ADV]:
            form = wn.morphy(w, pos)
            if form and form not in pos_forms[pos]:
                pos_forms[pos].append(form)
    body = ''
    for pos,pos_str,name in _pos_tuples():
        if pos in pos_forms:
            body += _hlev(3, name) + '\n'
            for w in pos_forms[pos]:
                # Not all words of exc files are in the database, skip
                # to the next word if a KeyError is raised.
                try:
                    body += _collect_all_synsets(w, pos, href.synset_relations)
                except KeyError:
                    pass
    if not body:
        body = "The word or words '%s' where not found in the dictonary." % word
    return body, word



#####################################################################
# Static pages
##################################################################### 

def plural_rule(ans):
    singular = wordnet.morphy(ans)
    if singular is not None and singular != ans:
        return singular
    else:
        return ans 

def page_from_reference(href):
    '''
    Returns a tuple of the HTML page built and the new current word

    :param href: The hypertext reference to be solved
    :type href: str
    :return: A tuple (page,word), where page is the new current HTML page
             to be sent to the browser and
             word is the new current word
    :rtype: A tuple (str,str)
    '''
    word = href.word
    pos_forms = defaultdict(list)
    words = word.split(',')
    words = [w for w in [w.strip().lower().replace(' ', '_')
                         for w in words]
             if w != ""]
    if len(words) == 0:
        # No words were found.
        return "", "Please specify a word to search for."

    # This looks up multiple words at once.  This is probably not
    # necessary and may lead to problems.
    for pos in [wn.NOUN, wn.VERB, wn.ADJ, wn.ADV]:
        form = wn.morphy(w, pos)
        if form and form not in pos_forms[pos]:
            pos_forms[pos].append(form)
    body = ''
    for pos,pos_str,name in _pos_tuples():
        if pos in pos_forms:
            body += _hlev(3, name) + '\n'
            for w in pos_forms[pos]:
                # Not all words of exc files are in the database, skip
                # to the next word if a KeyError is raised.
                try:
                    body += _collect_all_synsets(w, pos, href.synset_relations)
                except KeyError:
                    pass
    if not body:
        body = "The word or words '%s' where not found in the dictonary." % word
    return body, word



#####################################################################
# Static pages
##################################################################### 

def page_from_reference(href):
    '''
    Returns a tuple of the HTML page built and the new current word

    :param href: The hypertext reference to be solved
    :type href: str
    :return: A tuple (page,word), where page is the new current HTML page
             to be sent to the browser and
             word is the new current word
    :rtype: A tuple (str,str)
    '''
    word = href.word
    pos_forms = defaultdict(list)
    words = word.split(',')
    words = [w for w in [w.strip().lower().replace(' ', '_') for w in words] if w != ""]
    if len(words) == 0:
        # No words were found.
        return "", "Please specify a word to search for."

    # This looks up multiple words at once.  This is probably not
    # necessary and may lead to problems.
    for w in words:
        for pos in [wn.NOUN, wn.VERB, wn.ADJ, wn.ADV]:
            form = wn.morphy(w, pos)
            if form and form not in pos_forms[pos]:
                pos_forms[pos].append(form)
    body = ''
    for pos, pos_str, name in _pos_tuples():
        if pos in pos_forms:
            body += _hlev(3, name) + '\n'
            for w in pos_forms[pos]:
                # Not all words of exc files are in the database, skip
                # to the next word if a KeyError is raised.
                try:
                    body += _collect_all_synsets(w, pos, href.synset_relations)
                except KeyError:
                    pass
    if not body:
        body = "The word or words '%s' where not found in the dictonary." % word
    return body, word


#####################################################################
# Static pages
#####################################################################