Python wordnet.synsets函数代码示例

 def findSimilarity(self):
     #As we recommend only one item first item of this list will be recommended item
     #Second item can be list of items
     '''So what we try to do is get exact synset of first item and get 10 synsets (to reduce computation costs) of second list of items over 
     which the first item was preferred/recommended'''
     
     recommendation = wn.synsets(self.recoItems[0])  # @UndefinedVariable
     recommendationFiltered = []
     for eachSyn in recommendation:
         if self.recoItems[0] in str(eachSyn):
             recommendationFiltered.append(eachSyn)
             
     choices = {}
     for eachItem in self.recoItems[1]:
         choices[eachItem] = wn.synsets(eachItem)[:10]   # @UndefinedVariable getting only 10 items
     
     choiceScores = {}
     for key, value in choices.iteritems():
         choiceScores[key] = []
         for eachValue in choices[key]:            
             for eachRecoSyn in recommendationFiltered:                
                 choiceScores[key].append(eachRecoSyn.path_similarity(eachValue))
                         
     maxChoiceScores = {}
     
     for eachKey in choiceScores.keys():        
         maxChoiceScores[eachKey] = max(choiceScores[eachKey])
     
     return maxChoiceScores

def parseLyrics2(outlist):
	bandLyricInfo = {} 
	master = [['death', 0],['violence',0],['sacrifice',0],['nature',0],['peace',0],['storm',0],['spirit',0],[ 'dark',0],['scream',0],['pain',0],['blood',0],['flesh',0],['love',0],['greed',0],['poison',0],['anger',0],['revenge',0],['misery',0],['hell',0],['heaven',0],['hate',0],['soul',0],['battle',0],['ghost',0],['joy',0],['light',0],['omen',0],['miracle',0],['magic',0],['universe',0],['disease',0],['god',0],['satan',0],['struggle',0],['heart',0]]
	for key in outlist:
		templist = copy.deepcopy(master) ;
		#key = 'Queensryche'
		raw = outlist[key];
		raw = raw.lower();
		words = re.findall(r'\w+', raw,flags = re.UNICODE | re.LOCALE) # punctuation
		imp_words = filter(lambda x: x not in stopwords.words('english'), words) # filter noise
		lmt = WordNetLemmatizer()
		words_new = [lmt.lemmatize(x) for x in words]
		dw = list(set(words_new))
		
		for word in dw:
			for m in templist:
				p1 = wordnet.synsets(word) ;
				p2 = wordnet.synsets(m[0]) ;
				if(len(p1) >0 and len(p2) >0):
					c = p1[0].wup_similarity(p2[0])
					if(c > m[1]):
						m[1] = c
		# sort words according to similarity
		tnew = sorted(templist,key=lambda val:val[1],reverse=True) [0:10] ;
		# remove the other column
		for l in tnew:
			del l[1]
		print 'Done ',key
		#break ;
		bandLyricInfo[key] = tnew
		#del templist
	return bandLyricInfo

def relation(a,b) :
    ''' Given two words(strings) returns a number that denotes relation between
    the two words.

    Parameters
    ----------
    a : string
    b : string

    Returns
    -------
    float
        relation (less than 1) between two strings

    Notes
    -----
    First it applies BFS on the nltk wordnet and finds the least distance between
    the two given words. If the distance is x the function returns 1/(x+1), else return 0.

    '''
    a = wn.synsets(a)
    b = wn.synsets(b)
    visited_a = set([])
    visited_b = set([])
    stemmed_a = set([])
    stemmed_b = set([])
    depth = 0
    while True:
        if depth > 2:
            return 0
        new_a = set([])
        depth += 1
        for syn in a:
            if stemmer.stem(syn.lemma_names[0]) in stemmed_b:
                return 1.0/depth
            if syn in visited_a:
                continue
            visited_a.add(syn)
            stemmed_a.add(stemmer.stem(syn.lemma_names[0]))
            hyp = set(syn.hyponyms())
            for lemma in syn.lemma_names:
                None
                hyp |= set(wn.synsets(lemma))
            new_a |= hyp
        a = new_a
        new_b = set([])
        depth += 1
        for syn in b:
            if stemmer.stem(syn.lemma_names[0]) in stemmed_a:
                return 1.0/depth
            if syn in visited_b:
                continue
            visited_b.add(syn)
            stemmed_b.add(stemmer.stem(syn.lemma_names[0]))
            hyp = set(syn.hyponyms())
            for lemma in syn.lemma_names:
                None
                hyp |= set(wn.synsets(lemma))
            new_b |= hyp
        b = new_b

def tell(para1,para2):
	#Strip anything but not alphanum
	para1=re.sub(r'[^\w ]+', '', para1)
	para2=re.sub(r'[^\w ]+', '', para2)
	
	para1=para1.lower().split()
	para2=para2.lower().split()
	
	if para1==[] or para2==[]:
		return 0

	if not filter(lambda t:t.lower() not in stopwords, para1) == []:
		para1=filter(lambda t:t.lower() not in stopwords, para1)
	if not filter(lambda t:t.lower() not in stopwords, para2) == []:
		para2=filter(lambda t:t.lower() not in stopwords, para2)
	
	score=len(set(para1).intersection(para2))
	score_1=float(score)/math.sqrt(len(para2)*len(para1))
	
	para1_with_dictionary=reduce(lambda x,y:x+y, map(lambda word:[l.name for s in wordnet.synsets(word) for l in s.lemmas],para1))
	para1_with_dictionary=map(lambda ele:ele.lower(), para1_with_dictionary)
	#^^ Returns duplicated elements as well. So we need to remove the duplicates. Converting into set does that
	
	para2_with_dictionary=reduce(lambda x,y:x+y, map(lambda word:[l.name for s in wordnet.synsets(word) for l in s.lemmas],para2))
	para2_with_dictionary=map(lambda ele:ele.lower(), para2_with_dictionary)
	
	#^^ Returns duplicated elements as well. So we need to remove the duplicates. While taking intersection the same is handled

	score1=len(set(para1_with_dictionary).intersection(para2))
	score2=len(set(para2_with_dictionary).intersection(para1))

	score_2=float(max(score1,score2))/min(len(para2),len(para1))
	
	score=(score_1+score_2)/2
	return score

def parse_file(f):
  for l in f.readlines():    
    word = l.strip()
    synsets = wn.synsets(word)
    
    if word in synonym_values:
      continue
    
    # get first order synonyms
    synonyms = set()
    for synset in synsets:
      synonyms = set(synonyms) | set(synset.lemma_names)
  
    # add in synonyms of those synonyms
    for syn in synonyms:
      for syn_synset in wn.synsets(syn):
        synonyms = set(synonyms) | set(syn_synset.lemma_names)
    
    synonyms_with_values = set(synonyms) & set(synonym_values.keys())
    
    if not len(synonyms_with_values):
      continue
    
    avg = 0
    total = 0
    for syn in synonyms_with_values:
      value = synonym_values[syn]
      avg = (avg * total + float(value)) / (total + 1)
      total += 1
    
    # print "Adding", word, avg
    synonym_values[word] = int(abs_ceil(avg))
  
  f.close()

def scoreFile(filename, targetWords, verbose=False):
    meanScore = 0.0
    baseWordCount = 0
    wordCount = 0
    f = file(filename)
    for l in f:
        wordScored = False
        fields = [x.strip().lower() for x in re.split(r"\s+", l)]
        if (targetWords is not None) and (fields[0] not in targetWords):
            continue
        baseSynsets = wordnet.synsets(fields[0])
        if baseSynsets is None:
            continue
        for word in fields[1:]:
            # Ignore identical word if it occurs
            if word == fields[0]:
                continue
            targetSynsets = wordnet.synsets(word)
            if targetSynsets is None:
                continue
            wordScore = scoreWord(baseSynsets, targetSynsets)
            meanScore += wordScore
            wordCount += 1
            wordScored = True
        baseWordCount += 1 if wordScored else 0
        if verbose:
            if (baseWordCount > 0) and (baseWordCount % 1000 == 0):
                print "Words scored : %d, Current Score : %f" % (
                    baseWordCount,
                    meanScore / (wordCount if wordCount > 0 else 1),
                )
    f.close()
    meanScore /= wordCount if wordCount > 0 else 1
    return {"baseWordCount": baseWordCount, "totalWordCount": wordCount, "meanScore": meanScore}

	def hypernyms(self, word, question):
		hyper = []
		sentence = self.parse(question)
		pos = ''
		for sent, tag in sentence[0]: 
			if sent == word:
				pos = tag
				break
		if pos in ['JJ','JJR','JJS']:
			for synset in wn.synsets(word, pos = wn.ADJ):
				for lemma in synset.lemmas():
					if lemma.name() not in hyper and len(hyper)<7:
						hyper.append(lemma.name())
		elif pos in ['NN','NNS']:
			for synset in wn.synsets(word, pos = wn.NOUN):
				for lemma in synset.lemmas():
					if lemma.name() not in hyper and len(hyper)<7:
						hyper.append(lemma.name())
		elif pos in ['VB','VBG','VBD','VBN','VBP','VBZ']:
			for synset in wn.synsets(word, pos = wn.VERB):
				for lemma in synset.lemmas():
					if lemma.name() not in hyper and len(hyper)<7:
						hyper.append(lemma.name())
		elif pos in ['RB','RBR','RBS']:
			for synset in wn.synsets(word, pos = wn.ADV):
				for lemma in synset.lemmas():
					if lemma.name() not in hyper and len(hyper)<7:
						hyper.append(lemma.name())
		return hyper

def c_wn_max_path_similarity(score,word_from,word_to):
	"""
	WordNet path similarity for the most similar synsets. (1 if same word)
	
	This feature can be precomputed by EQUALS
	"""
	
	# Enforce returning 1 when words are equal (would be 0 if synset not found)
	# NOTE: since EQUALS precomputes this feature, the assignment in the second
	#       if is double. It is mantained to keep the indipendence on the imple-
	#       mentation of EQUALS.
	if not score.is_feature_set[score.EQUALS]:
		c_equals(score,word_from,word_to)
	if score.features[score.EQUALS] == 1:
		score.set_feature(score.WN_MAX_PATH_SIMILARITY,1)
		return
	
	# Compute the actual distance
	_r = 0
	
	for ss_from in wn.synsets(word_from.text):
		for ss_to in wn.synsets(word_to.text):
			current_similarity = ss_to.path_similarity(ss_from)
			if current_similarity > _r:
				_r = current_similarity
	
	score.set_feature(score.WN_MAX_PATH_SIMILARITY,_r)

def CollectSemcorSupersenses():
  oracle_matrix = collections.defaultdict(WordSupersenses)
  for sent in semcor.tagged_sents(tag='both'):
    for chk in sent:
      if chk.node and len(chk.node)>3 and chk.node[-3]=='.' and chk.node[-2:].isdigit():
        if chk[0].node.startswith('N'):
          pos = "n"
        elif chk[0].node.startswith('V'):
          pos = "v"
        else:
          continue
        lemmas = chk.node[:-3]
        wnsn = int(chk.node[-2:])
        ssets = wn.synsets(lemmas, pos)
        sorted_ssets = sorted(ssets, key=lambda x: x.name)
        filtered_ssets = None
        for lemma in lemmas.split("_"):  
          if not filtered_ssets or len(filtered_ssets) == 0:
            filtered_ssets = filter(lambda x: lemma in x.name, sorted_ssets)
        if filtered_ssets and len(filtered_ssets) > 0:
          sorted_ssets = filtered_ssets
        try:
          supersense = sorted_ssets[wnsn-1].lexname # prints 'noun.group
        except:
          #print("."),
          continue
        for lemma in lemmas.split("_"):        
          ssets = wn.synsets(lemma, pos)
          if len(ssets) > 0:
            if lemma.isdigit():
              lemma = "0"
            oracle_matrix[lemma].Add(supersense, "semcor")  
  return oracle_matrix      

def generatesynsets(table):
    table2 = []
    table3 = {}
    for i in table:
        search1 = "N.*"
        search2 = "V.*"
        if re.findall(search1, i[1]):
            x = wns.synsets(i[0], pos=wns.NOUN)
        elif re.findall(search2, i[1]):
            x = wns.synsets(i[0], pos=wns.VERB)
        for z in range(len(x)):
            for y in x[z].lemma_names:
                syn = 'SYN'
                if y not in ['match', 'be', 'in', 'is']:
                    table2.append((y, syn))
    test = 0
    test += 1
    for i in table2:
        try:
            table3[i] += test

        except:
            table3[i] = test

    return table3

    def polar_values(self, positive_seeds, negative_seeds):
        self.values = []
        POS_tags = list(set(nltk.pos_tag(WordPunctTokenizer().tokenize(self.data))))
        words = []
        for (w, s) in POS_tags:
           w= w.lower()
           POS =  self.get_wordnet_pos(s)
           if POS =='' or re.match("^[\w]+$",w) == None:
               words.append('0')
           else:
               w+="."+POS
               w+=".01"
               words.append(w)
        negative_set = []
        for nw in negative_seeds:
            for s in wordnet.synsets(nw):
                negative_set.append(s)

        positive_set = []
        for pw in positive_seeds:
            for s in wordnet.synsets(pw):
                positive_set.append(s)

        self.eval_words(words, positive_set, negative_set)
        return self.values

def getSynonym(word, tag):
    pos_list = {"JJ":"ADJ","JJR":"ADJ", "JJS":"ADJ","NN":"NOUN","NNS":"NOUN","NPS":"NOUN","NP":"NOUN","RBR":"ADV","RBS":"ADV","RB":"ADV","VB":"VERB","VBD":"VERB","VBG":"VERB","VBN":"VERB","VBP":"VERB","VBZ":"VERB"};
    tag_list = pos_list.keys()
    li = {} 
    if tag in tag_list:
        dd = pos_list.get(tag)
        if dd == "VERB":
            tt =  wn.synsets(word,pos=wn.VERB)
            for key in tt:
                ss = key.lemma_names
                for s in ss:
                    li[s] = s
        if dd == "NOUN":
            tt =  wn.synsets(word,pos=wn.NOUN)
            for key in tt:
                ss = key.lemma_names
                for s in ss:
                    li[s] = s

        if dd == "ADV":
            tt =  wn.synsets(word,pos=wn.ADV)
            for key in tt:
                ss = key.lemma_names
                for s in ss:
                    li[s] = s
        if dd == "ADJ":
            tt =  wn.synsets(word,pos=wn.ADJ)
            for key in tt:
                ss = key.lemma_names
                for s in ss:
                    li[s] = s
    return li.keys()

def xhyper(words)->[str]:
    '''returns the highest order x hypernyms'''
    x = UI.request_x()
    print("\nNote: this program will use the first parallel synset if there are any")
    print("\nGathering data...")
    result = [x]
    hyp = lambda w: w.hypernyms()
    #This would pick up the deepest branch's depth -> valueAt returns None -> returns None
    #depth = lambda L: isinstance(L, list) and max(map(depth, L))+1
    for i in range(len(words)):
        synsets = wordnet.synsets(words[i]) 
        if len(synsets) > 0:
            for s in range(len(synsets)):
                hyper = wordnet.synsets(words[i])[s].tree(hyp)
                if (hyper[0].pos() in ['a','s','r']):
                    result.append([words[i], 'None', 'None', [None]])
                    continue
                d = first_depth(hyper) - 1
                xhyper = []
                for j in range(x):
                    xhyper.append(valueAt(d - j, hyper))
                    if xhyper[-1] is None:
                        break
                result.append([words[i], pos_redef(hyper[0].pos()), hyper[0], xhyper])
        else:
            result.append([words[i], 'None', 'None', [None]])
    return result

def userEnteredWordSensor(user_input):
	#what stage are we currently in ? -- whether AS,IM or WI ?
	#what response did user enter ?
	if exactly_right: 
			#save our total action plan.	
			cursor.executeQuery("insert into path values('',session['uid'],session['wordid']")
			pathid=cursor.executeQuery("select pathid from path where wordid = session['wordid']")	
			cursor.executeQuery("insert into waypoint values('',pathid,session['type'],session['waypoint_info'])")
			#LOG the path
			#procede to the next word.
			perform()
			pass;
	elif nearly_right:
			#nearly right means -->
				#one of the tags
				wid=cursor.executeQuery("Select wordid from words where word like 'session['word']'")
				tags=cursor.executeQuery("Select tags from words where wordid=wid")
				for tag in tags:
					if ( tag == word )
						#perform action sequence for NEXT
						break;
					#its synonym
					for s in wn.synsets('session['word']'):
								if( s == user_input )
									#perform action sequence for NEXT
									break;
					else:
					#tags's synonym...?	
							for s in wn.synsets('tag'):
								if( s == user_input )
									#perform action sequence for NEXT
									break;

def wndist(fs):
    """
    Distance between NP1 and NP2 in WordNet (using the first sense only)
    """

    wndist=-100000

    i_pos=__get_pos__(fs.article,fs.sentence,fs.offset_begin,fs.offset_end)
    j_pos=__get_pos__(fs.article,fs.sentence_ref,fs.offset_begin_ref,fs.offset_end_ref)

    #print "Orig:", fs.token, '\t', fs.token_ref

    if i_pos.startswith('NN') and j_pos.startswith('NN') and not i_pos.endswith('P') and not j_pos.endswith('P'):
        # considering only common nouns
        lemmatizer = nltk.WordNetLemmatizer()
        i=lemmatizer.lemmatize(fs.i_cleaned, pos='n')
        j=lemmatizer.lemmatize(fs.j_cleaned, pos='n')
        synsets_i=wn.synsets(i)
        synsets_j=wn.synsets(j)
        if len(synsets_i)>0 and len(synsets_j)>0:
            wn_sense1_i=synsets_i[0]
            wn_sense1_j=synsets_j[0]
            wn_pos_i=str(wn_sense1_i).split('.')[1]
            wn_pos_j=str(wn_sense1_j).split('.')[1]
            if wn_pos_i==wn_pos_j:
                wndist=wn_sense1_i.lch_similarity(wn_sense1_j)
                wndist=(ceil(wndist * 100) / 100.0)
                #print "Lemmatized:", i, '\t', j, '\t', str(wndist)

    #print
    #print

    return "wndist={}".format(wndist)