sentiment.py

PUNC_LIST = [".", "!", "?", ",", ";", ":", "-", "'", "\"",
             "!!", "!!!", "??", "???", "?!?", "!?!", "?!?!", "!?!?"]
NEGATE = \
["aint", "arent", "cannot", "cant", "couldnt", "darent", "didnt", "doesnt",
 "ain't", "aren't", "can't", "couldn't", "daren't", "didn't", "doesn't",
 "dont", "hadnt", "hasnt", "havent", "isnt", "mightnt", "mustnt", "neither",
 "don't", "hadn't", "hasn't", "haven't", "isn't", "mightn't", "mustn't",
 "neednt", "needn't", "never", "none", "nope", "nor", "not", "nothing", "nowhere",
 "oughtnt", "shant", "shouldnt", "uhuh", "wasnt", "werent",
 "oughtn't", "shan't", "shouldn't", "uh-uh", "wasn't", "weren't",
 "without", "wont", "wouldnt", "won't", "wouldn't", "rarely", "seldom", "despite"]

# booster/dampener 'intensifiers' or 'degree adverbs'
# http://en.wiktionary.org/wiki/Category:English_degree_adverbs

BOOSTER_DICT = \
{"absolutely": B_INCR, "amazingly": B_INCR, "awfully": B_INCR, "completely": B_INCR, "considerably": B_INCR,
 "decidedly": B_INCR, "deeply": B_INCR, "effing": B_INCR, "enormously": B_INCR,
 "entirely": B_INCR, "especially": B_INCR, "exceptionally": B_INCR, "extremely": B_INCR,
 "fabulously": B_INCR, "flipping": B_INCR, "flippin": B_INCR,
 "fricking": B_INCR, "frickin": B_INCR, "frigging": B_INCR, "friggin": B_INCR, "fully": B_INCR, "fucking": B_INCR,
 "greatly": B_INCR, "hella": B_INCR, "highly": B_INCR, "hugely": B_INCR, "incredibly": B_INCR,
 "intensely": B_INCR, "majorly": B_INCR, "more": B_INCR, "most": B_INCR, "particularly": B_INCR,
 "purely": B_INCR, "quite": B_INCR, "really": B_INCR, "remarkably": B_INCR,
 "so": B_INCR, "substantially": B_INCR,
 "thoroughly": B_INCR, "totally": B_INCR, "tremendously": B_INCR,
 "uber": B_INCR, "unbelievably": B_INCR, "unusually": B_INCR, "utterly": B_INCR,
 "very": B_INCR,
 "almost": B_DECR, "barely": B_DECR, "hardly": B_DECR, "just enough": B_DECR,
 "kind of": B_DECR, "kinda": B_DECR, "kindof": B_DECR, "kind-of": B_DECR,
 "less": B_DECR, "little": B_DECR, "marginally": B_DECR, "occasionally": B_DECR, "partly": B_DECR,
 "scarcely": B_DECR, "slightly": B_DECR, "somewhat": B_DECR,
 "sort of": B_DECR, "sorta": B_DECR, "sortof": B_DECR, "sort-of": B_DECR}


class SentimentIntensityAnalyzer(object):
    def __init__(self, lexicon_file="vader_lexicon.txt"):
        self.lexicon_file = nltk.data.load(lexicon_file)
        self.lexicon = self.make_lex_dict()

    def _sift_sentiment_scores(self, sentiments):
        # want separate positive versus negative sentiment scores
        pos_sum = 0.0
        neg_sum = 0.0
        neu_count = 0
        for sentiment_score in sentiments:
            if sentiment_score > 0:
                pos_sum += (float(sentiment_score) +1) # compensates for neutral words that are counted as 1
            if sentiment_score < 0:
                neg_sum += (float(sentiment_score) -1) # when used with math.fabs(), compensates for neutrals
            if sentiment_score == 0:
                neu_count += 1
        return pos_sum, neg_sum, neu_count

    def score_valence(self, sentiments, text):
        if sentiments:
            sum_s = float(sum(sentiments))
            # compute and add emphasis from punctuation in text
            punct_emph_amplifier = self._punctuation_emphasis(sum_s, text)
            if sum_s > 0:
                sum_s += punct_emph_amplifier
            elif  sum_s < 0:
                sum_s -= punct_emph_amplifier

            compound = normalize(sum_s)
            # discriminate between positive, negative and neutral sentiment scores
            pos_sum, neg_sum, neu_count = self._sift_sentiment_scores(sentiments)

            if pos_sum > math.fabs(neg_sum):
                pos_sum += (punct_emph_amplifier)
            elif pos_sum < math.fabs(neg_sum):
                neg_sum -= (punct_emph_amplifier)

            total = pos_sum + math.fabs(neg_sum) + neu_count
            pos = math.fabs(pos_sum / total)
            neg = math.fabs(neg_sum / total)
            neu = math.fabs(neu_count / total)

        else:
            compound = 0.0
            pos = 0.0
            neg = 0.0
            neu = 0.0

        sentiment_dict = \
            {"neg" : round(neg, 3),
             "neu" : round(neu, 3),
             "pos" : round(pos, 3),
             "compound" : round(compound, 4)}

        return sentiment_dict


    def polarity_scores(self, text):
        """
        Return a float for sentiment strength based on the input text.
        Positive values are positive valence, negative value are negative
        valence.
        """
        sentitext = SentiText(text)
        #text, words_and_emoticons, is_cap_diff = self.preprocess(text)

        sentiments = []
        words_and_emoticons = sentitext.words_and_emoticons
        for item in words_and_emoticons:
            valence = 0
            i = words_and_emoticons.index(item)
            if (i < len(words_and_emoticons) - 1 and item.lower() == "kind" and \
                words_and_emoticons[i+1].lower() == "of") or \
                item.lower() in BOOSTER_DICT:
                sentiments.append(valence)
                continue

            sentiments = self.sentiment_valence(valence, sentitext, item, i, sentiments)

        sentiments = self._but_check(words_and_emoticons, sentiments)

        return self.score_valence(sentiments, text)

    def _words_plus_punc(self):
        """
        Returns mapping of form:
        {
            'cat,': 'cat',
            ',cat': 'cat',
        }
        """
        no_punc_text = REGEX_REMOVE_PUNCTUATION.sub('', self.text)
        # removes punctuation (but loses emoticons & contractions)
        words_only = no_punc_text.split()
        # remove singletons
        words_only = set( w for w in words_only if len(w) > 1 )
        # the product gives ('cat', ',') and (',', 'cat')
        punc_before = {''.join(p): p[1] for p in product(PUNC_LIST, words_only)}
        punc_after = {''.join(p): p[0] for p in product(words_only, PUNC_LIST)}
        words_punc_dict = punc_before
        words_punc_dict.update(punc_after)
        return words_punc_dict