Пример #1
0
def in_wordnet(word):
    base = wordnet.morphy(word)
    if base is None: base = word
    for d in wordnet.Dictionaries.values():
        if base in d: return True
        if word in d: return True
    return False
Пример #2
0
def in_wordnet(word):
    base = wordnet.morphy(word)
    if base is None:
        base = word
    for d in wordnet.Dictionaries.values():
        if base in d:
            return True
        if word in d:
            return True
    return False
Пример #3
0
 def select(cls, words):
     keywords = []
     for word in words:
         woord = wn.morphy(word, wn.NOUN)
         if (woord != None):
             keywords.append(woord)
     labels = []
     labels.append(wn.synset('politics.n.01'))
     labels.append(wn.synset('sport.n.01'))
     labels.append(wn.synset('food.n.01'))
     labels.append(wn.synset('party.n.01'))
     labels.append(wn.synset('education.n.01'))
     labels.append(wn.synset('book.n.01'))
     labels.append(wn.synset('tv.n.01'))
     labels.append(wn.synset('holiday.n.01'))
     labels.append(wn.synset('computer.n.01'))
     labels.append(wn.synset('science.n.01'))
     names = [
         'politics', 'sports', 'food', 'party', 'education', 'book', 'tv',
         'holiday', 'computer', 'science'
     ]
     #labels.append(wn.synset('animal.n.01'))
     #names = ['politics', 'sports', 'food', 'party', 'education', 'book', 'tv', 'holiday', 'computer', 'science', 'animal']
     length = len(labels)
     interest = np.zeros(length)
     for keyword in keywords:
         keyword = keyword + '.n.01'
         keyword = wn.synset(keyword)
         for label in labels:
             interest[labels.index(label)] = +keyword.path_similarity(label)
     classification = []
     #By changing n, one can output their top N interest classes
     n = 3
     for i in range(0, n):
         element = max(xrange(len(interest)), key=lambda x: interest[x])
         classification.append(names[element])
         interest[element] = 0
     return classification
Пример #4
0
def runWordnet():
        #if False:
          #for leaf in c.leaves():
            #if(leaf[1]=="VBN" or leaf[1]=="VBD" or leaf[1]=="JJ"):
            #if (re.match("TO|BE.*|DO.*|HV.*|MD|IN|PP", leaf[1])):  
            #  cfdcohort[cohortvalue].inc(leaf)         
            #  cfdleaves[leaf].inc(cohortvalue)
              
                    maxscore = -1
                    try:
                      verb = wordnet.morphy(leaf[0], wordnet.VERB)
                      senses = wordnet.V[verb]
                      for sense in senses:
                        ref_verbs = ["submit","obtain","enter","access","archive","retrieve","present","post","query","import","download","view","find","deposit"]
                        s = set([])
                        for ref in ref_verbs:
                          newscore = wordnet.V[ref][0].path_similarity(sense)
                          s.update(wordnet.V[ref][0].hypernym_paths()[0])
                          maxscore = max(maxscore,newscore)
                        print s,"\n\n"
                    except:
                      maxscore = -2
                    print maxscore
Пример #5
0
 def stem(self, word):
     return morphy(word)