Python sentiwordnet.senti_synsets函数代码示例

def analiseSentimento(resposta):
	texto = resposta['corpo']
	frases = sentencesTokenizer.tokenize(texto)
	palavras = []
	for frase in frases:
		palavras.extend(wordsTokenizer.tokenize(frase))
	posTags = pos_tag(palavras)
	positivo = 0
	negativo = 0
	for palavra, tag in posTags:
		synsets = None
		if tag.startswith('J'):
			synsets = sentiwordnet.senti_synsets(palavra, wordnet.ADJ)
		elif tag.startswith('V'):
			synsets = sentiwordnet.senti_synsets(palavra, wordnet.VERB)
		elif tag.startswith('N'):
			synsets = sentiwordnet.senti_synsets(palavra, wordnet.NOUN)
		elif tag.startswith('R'):
			synsets = sentiwordnet.senti_synsets(palavra, wordnet.ADV)
		else:
			synsets = sentiwordnet.senti_synsets(palavra, '')
		if synsets != None:
			synsets = list(synsets)
			if len(synsets) > 0:
				synset = synsets[0]
				positivo = positivo + synset.pos_score()
				negativo = negativo + synset.neg_score()
	if positivo > negativo:
		return (resposta, 'positivo')
	elif negativo > positivo:
		return (resposta, 'negativo')
	else:
		return (resposta, 'neutro')

def getting_sentiment(word,pos):
    flag = 0
    if 'NN' in pos:
        tag = 'n'
    elif 'JJ' in pos:
        tag = 'a'
        if pos == 'JJS':
            flag = 1
    elif 'VB' in pos:
        tag = 'v'
    elif 'RB' in pos:
        tag = 'r'
    else:
        tag = ''
    stemmer = WordNetLemmatizer()
    if tag != '':
        x = stemmer.lemmatize(word,tag)
    else:
        x = stemmer.lemmatize(word)

    try:
        score = float(score_dic[x]) #* float(m1)
    except KeyError:
        if len(swn.senti_synsets(x,tag)) > 0:
            score = swn.senti_synsets(x,tag)[0].pos_score() * 5
        else:
            score = 100

    if flag == 1 and score != -100 and score < 4:
        score = score + 1
    elif flag == 1 and score != -100 and score > -4 and score < 0:
        score = score - 1
    print word + '--->' + str(score)
    return score

def get_score(adjective):
    if adjective not in d: 
	scores = swn.senti_synsets(adjective)
    	pos_scores = [i.pos_score() for i in scores]
    	neg_scores = [i.neg_score() for i in scores]
    	obj_scores = [i.obj_score() for i in scores]
    	pos_score = maxi(pos_scores)
    	neg_score = maxi(neg_scores)
    	obj_score = maxi(obj_scores)
        if len(scores) == 0:
            d[adjective] = (-1,-1,-1,-1,-1,-1)
            return (-1,-1,-1,-1,-1,-1)

    	scores_ad = swn.senti_synsets(adjective,pos='ar')
    	pos_scores_ad = [i.pos_score() for i in scores_ad]
    	neg_scores_ad = [i.neg_score() for i in scores_ad]
    	obj_scores_ad = [i.obj_score() for i in scores_ad]
    	pos_score_ad = maxi(pos_scores_ad)
    	neg_score_ad = maxi(neg_scores_ad)
    	obj_score_ad = maxi(obj_scores_ad)
    	d[adjective] = (pos_score,neg_score,obj_score,pos_score_ad,neg_score_ad,obj_score_ad)
    else:
	 (pos_score,neg_score,obj_score,pos_score_ad,neg_score_ad,obj_score_ad) = d[adjective]
    if pos_score == -1:
        return -100
    if pos_score_ad > neg_score_ad:
    	return pos_score_ad 
    elif pos_score_ad < neg_score_ad:
       	return -neg_score_ad 
    elif pos_score > neg_score:
        return pos_score
    elif pos_score < neg_score:
        return -neg_score
    else:
        return 0

def processoFeatures(resposta):
    frases = tokenizerFrases.tokenize(resposta["corpo"])
    palavras = []
    palavrasTexto = {}
    for frase in frases:
        palavrasTemp = tokenizerPalavras.tokenize(frase)
        for palavra in palavrasTemp:
            palavrasTexto[palavra] = True
    posTags = pos_tag(palavras)
    positivo = 0
    negativo = 0
    for palavra, tag in posTags:
        synsets = None
        if tag.startswith("J"):
            synsets = sentiwordnet.senti_synsets(palavra, wordnet.ADJ)
        elif tag.startswith("V"):
            synsets = sentiwordnet.senti_synsets(palavra, wordnet.VERB)
        elif tag.startswith("N"):
            synsets = sentiwordnet.senti_synsets(palavra, wordnet.NOUN)
        elif tag.startswith("R"):
            synsets = sentiwordnet.senti_synsets(palavra, wordnet.ADV)
        else:
            synsets = sentiwordnet.senti_synsets(palavra, "")
        if synsets != None:
            synsets = list(synsets)
            if len(synsets) > 0:
                synset = synsets[0]
                positivo = positivo + synset.pos_score()
                negativo = negativo + synset.neg_score()
    if positivo > negativo:
        return (palavrasTexto, "positivo")
    elif negativo > positivo:
        return (palavrasTexto, "negativo")
    else:
        return (palavrasTexto, "neutro")

def sentiwordnetSentimentWordsPresenceFeatures(wordsTagged):
    features = {}
    for word, tag in wordsTagged:
        wordnetTag = translateFromNltkToWordnetTag(tag)
        wordNegated = isWordNegated(word)
        word = stripNegation(word)
        if wordnetTag:
            synsets = list(sentiwordnet.senti_synsets(word, wordnetTag))
            if not synsets:
                synsets = list(sentiwordnet.senti_synsets(word))
        else:
            synsets = list(sentiwordnet.senti_synsets(word))
        if len(synsets) > 0:
            synset = synsets[0]
            if synset.pos_score() > 0.5:
                if wordNegated:
                    features["neg_word_presence"] = True
                else:
                    features["pos_word_presence"] = True
            if synset.neg_score() > 0.5:
                if wordNegated:
                    features["pos_word_presence"] = True
                else:
                    features["neg_word_presence"] = True
    return features

def senti_analisys(tokens):
    #print tokens
    scorePosTot = 0
    scoreNegTot = 0
    scoreObjTot = 0
    scoreObjNorm = scoreNegNorm = scorePosNorm = 0
    count = 0
    for token,part in tokens:

        if part.startswith("JJ") or part.startswith("NN") or part.startswith("VB"):

            scorePos = 0
            scoreNeg = 0
            scoreObj = 0
            #print swn.senti_synsets(token)
            #if token == "wonderful":
             #   print "i'm "+token,swn.senti_synsets(token)
            if swn.senti_synsets(token) != []:
                list_synset = list(swn.senti_synsets(token))
                dim_synset = list_synset.__len__()

                for i in list_synset:
                    scorePos += i.pos_score()
                    scoreNeg += i.neg_score()
                    scoreObj += i.obj_score()

                scorePos = scorePos / dim_synset
                scoreNeg = scoreNeg / dim_synset
                scoreObj = scoreObj / dim_synset

                #print "The token is: "+token + "\n\tscore pos: "+str(round(scorePos,2)) + "\n\tscore neg: "+str(round(scoreNeg,2))+\
                      #"\n\tscore obj: " + str(round(scoreObj,2))


                scorePosTot += scorePos
                scoreNegTot += scoreNeg
                scoreObjTot += scoreObj
            count += 1

    if count != 0:
        scorePosNorm = scorePosTot / count
        scoreNegNorm = scoreNegTot / count
        scoreObjNorm = scoreObjTot / count

    #print "NORM: "+ "\n\tscorePOS: "+str(round(scorePosNorm,2)) + "\n\tscoreNEG: "+str(round(scoreNegNorm,2)) \
          #+ "\n\tscoreOBJ: "+str(round(scoreObjNorm,2))
    if scoreNegNorm < scorePosNorm :
        #print "POSITIVE"
        return 1,scorePosNorm
    elif scoreNegNorm > scorePosNorm:
        #print "NEGATIVE"
        return -1,-scoreNegNorm
    else:
        #print "OBJECTIVE"
        return 0,0

def get_net_pos_neg(word):
    netPos = 0
    netNeg = 0

    if len(list(swn.senti_synsets(word))) != 0:
        sentisyn = list(swn.senti_synsets(word))
        for item in sentisyn:
            netPos += item.pos_score()
            netNeg += item.neg_score()

    return netPos, netNeg

def strip_proppers_POS(text, search):
    text = text.decode('utf-8', 'ignore')
    tokens = nltk.word_tokenize(text.lower())
    tagged = nltk.tag._pos_tag(tokens, tagset, tagger)
    res = []

    search_index = [i for i, val in enumerate(tokens)
                    if (p.singular_noun(val) == search or
                    (not p.singular_noun(val) and val == search))
                    ]

    words = [(word, pos) for word, pos in tagged if (pos[0] == "J") and
             len(word) > 2 and
             word not in stop and
             not p.singular_noun(word) and
             eng_check.check(word) and
             not any(ccc.isdigit() for ccc in word)]

    adj_count = 0
    for a in range(0, len(tagged)):
        if tagged[a] in words:
            if tagged[a][1][0] == "J":
                adj = tagged[a][0]
                dist = min([abs(a-s) for s in search_index])
                score = 0
                adj_synset = swn.senti_synsets(adj, 'a')
                if len(adj_synset) <= 0:
                    adj_synset = swn.senti_synsets(adj, 'v')
                if len(adj_synset) <= 0:
                    synonyms = []
                    for ss in wn.synsets(adj):
                        for j in ss.lemma_names():
                            synonyms.append(j)
                    if len(synonyms) > 1:
                        synonym_count = 0
                        for s in range(0, len(synonyms)):
                            if synonym_count < 2 and synonyms[s] != adj:
                                w1 = synonyms[s]
                                adj_synset1 = swn.senti_synsets(w1, 'a')
                                if len(adj_synset1) > 0:
                                    score += adj_synset1[0].pos_score()\
                                        - adj_synset1[0].neg_score()
                                    synonym_count += 1
                        score = score/2
                else:
                    score = adj_synset[0].pos_score() \
                        - adj_synset[0].neg_score()
                try:
                    res.append((adj, score/(pow(dist, 2))))
                    adj_count += 1
                except:
                    pass
    return (res, adj_count)

    def getNumberOfAppearances(self,tokens):
        total = 0
        for token in tokens:
            if len(s.senti_synsets(token)) > 0:
                total += 1

        return total

def main():
    # str=['s','a','f','e','v','i','w','j','k','x','k']
    # for i in str:
    #     for j in str:
    #
    i = raw_input("Length:")
    str = raw_input("Letter sequence:")
    f = open("combinations.txt",'w')
    k = list(itertools.permutations(str,int(i)))

    for i in k:
        for l in i:
            f.write(l)
        f.write('\n')
    f.close()

    h = []
    with open('combinations.txt') as hai:
        h = [word.lower().strip() for word in hai ]

    dic = {}
    for o in h:
        if o not in dic:
            dic [o]= 0
        else:
            dic[o] += 1

    m = open("out.txt",'w')

    for l in dic:
        v= list(swn.senti_synsets(l))
        if v:
            m.write(l)
            m.write('\n')

 def getSentimentOfWord(self, word):
     try:
         sentSet = list(swn.senti_synsets(word))
     except:
         #print("swn.senti_synsets(word) threw an error")
         return 0
     
     #if not found, assume objective word
     if len(sentSet) == 0:
         #print('empty sentSet for word '+word)
         return 0
     #else:
         #print('non empty sentSet for word '+word)
         
     totalPos = 0
     totalNeg = 0
     totalObj = 0
     for sentiword in sentSet:
         totalPos += sentiword.pos_score()
         totalNeg += sentiword.neg_score()
         totalObj += sentiword.obj_score()
     
     totalPos = totalPos / len(sentSet)
     totalNeg = totalNeg / len(sentSet)
     totalObj = totalObj / len(sentSet)
         
     #determine sentiment
     if (totalPos >= totalObj) and (totalPos >= totalNeg):
         return 1
     if (totalNeg >= totalObj) and (totalNeg >= totalPos):
         return -1
     if (totalObj >= totalPos) and (totalObj >= totalNeg):
         return 0

def get_sentiment_score(ls):
    '''
    input type sentence
    this method estimate a score for the sentence based on the swn model 
    '''
    from nltk.tokenize import word_tokenize
    import re
    word_list = word_tokenize(ls.content)
    punctuation = re.compile(r'[-.?!,":;()|0-9]') # remove these punctuations and number 
    word_list = [punctuation.sub("", word) for word in word_list]  
    word_list = filter(None, word_list) #filters empty         
    ls.tokens = word_list

    pos_score = 0.0
    neg_score = 0.0
    num_valid_word = 0.1
    for w in word_list:
        try:
            res = swn.senti_synsets(w)
            pos_score += res[0]._pos_score
            neg_score += res[0]._neg_score
            num_valid_word += 1
        except:
            pass
            
    ls.score = (pos_score - neg_score)/num_valid_word
    
    """

def main():
	args = sys.argv
	if(len(args) != 2):
		print('usage: python proj filename')
		return -1
	lines = []
	values = []
	data = open(args[1], 'r')
	for line in data:
		temp = line.split('.')
		for sen in temp:
			tokens = word_tokenize(sen.strip('\n').strip(',').strip('-'))
			if tokens != []:
				lines.append(tokens)
	total_pos = 0
	total_neg = 0

	for line in lines:
		pos = 0.0
		neg = 0.0
		pcount = 0
		ncount = 0
		for word in line:
			sp = 0
			sn = 0
			sub_pos = 0
			sub_neg = 0
			x = swn.senti_synsets(word)
			
			for a in x:
				if(a.pos_score() > 0):
					sub_pos += 1
					sp += a.pos_score()
				if a.neg_score() > 0:
					sub_neg += 1
					sn += a.neg_score()
	#		if(sub_pos != 0):
	#			sp /= sub_pos
	#		if(sub_neg != 0):
	#			sn /= sub_neg
			pos += sp
			neg += sn
			if sp > 0:
				pcount += 1
			if sn > 0:
				ncount += 1
		
		if(pos == 0) or (neg == 0):
			values.append((pos, neg))
			total_pos += pos
			total_neg += neg

		else:	
			values.append((pos/(pos+neg), neg/(pos+neg)))
			total_pos += (pos/(pos+neg))
			total_neg += (neg/(pos+neg))
	print(str(total_pos / len(values)) + ',' + str(total_neg / len(values)))
	for x in range(0, len(lines)):
	#	print('sentence: ' + str(lines[x]))
		print(str(values[x][0]) + ',' + str(values[x][1]))

def sentiwordnetSentimentScoreFeatures(wordsTagged):
    posScoreSum = 0.0
    negScoreSum = 0.0
    for word, tag in wordsTagged:
        wordnetTag = translateFromNltkToWordnetTag(tag)
        word = stripNegation(word)
        if wordnetTag:
            synsets = list(sentiwordnet.senti_synsets(word, wordnetTag))
        else:
            synsets = list(sentiwordnet.senti_synsets(word))
        if len(synsets) > 0:
            synset = synsets[0]
            posScoreSum = synset.pos_score()
            negScoreSum = synset.neg_score()

    return {"pos_neg_score": posScoreSum - negScoreSum}

 def score(self, tokens):
     pos_value = 0.0
     neg_value = 0.0
     obj_value = 0.0
     
     #TODO disambiguation via POS tagging using nps_chat or Brown Corpus
    
         
     nltk_tagged = nltk.pos_tag(tokens)
     
     
     #print(nltk_tagged)
     
     lengthOfData = 0
     for word in nltk_tagged:
         
         meanings = list(swn.senti_synsets(word[0], self.get_wordnet_pos(word[1])))
         
         if len(meanings) > 0:
             wordSynset0 = meanings[0]
             pos_value += wordSynset0.pos_score()
             neg_value += wordSynset0.neg_score()
             obj_value += wordSynset0.obj_score()
             lengthOfData += 1
             
     if lengthOfData > 0:
         pos_value = pos_value
         neg_value = neg_value
         obj_value = obj_value/lengthOfData
         
     return [ pos_value , neg_value, obj_value]