Python textblob 模块，TextBlob() 实例源码

def analyzetweets(self, access_token, access_token_secret, mytweets=False, q=None):
    auth = tweepy.OAuthHandler(CONSUMER_KEY, CONSUMER_SECRET)
    auth.set_access_token(access_token, access_token_secret)
    api = tweepy.API(auth)
    sentimentlist = []
    subjectivitylist = []
    number = NUMBER_OF_TWEETS
    tweets = tweepy.Cursor(api.user_timeline).items() if mytweets else tweepy.Cursor(api.search, q=q).items(number)
    for index, tweet in enumerate(tweets):
        analysis = TextBlob(tweet.text).sentiment
        sentimentlist.append(analysis.polarity)
        subjectivitylist.append(analysis.subjectivity)
        self.update_state(state="RUNNING", meta={"current": index + 1, "total": number})
    sentimentavg = float(sum(sentimentlist) / max(len(sentimentlist), 1))
    subjectivityavg = float(sum(subjectivitylist) / max(len(subjectivitylist), 1))
    return {"current": number, "total": number, "subjectivityavg": subjectivityavg, "sentimentavg": sentimentavg}

def generate_html(paragraphs, title_text):
    doc = dominate.document(title='Summary: {}'.format(title_text))

    with doc.head:
        style("""\
            body {
                background-color: #F9F8F1;
                color: #2C232A;
                font-family: sans-serif;
                font-size: 1.2em;
            }

        """)

    with doc:
        div(id='header').add(h1(title_text))
        with div():
            attr(cls='body')
            for para in paragraphs:
                tb = TextBlob(para)
                with p():
                    for sentence in tb.sentences:
                        span(sentence, style="color: {}".format(get_polarity_color(sentence.polarity)))
    return doc

def getSentiment(api, key):
    public_tweets = api.search(key)
    AvgSentiment = 0
    noOfTweets = len(public_tweets)
    sum1 = 0
    for tweet in public_tweets:
        text = tweet.text
        cleanedtext = ' '.join([word for word in text.split(' ') if len(word) > 0 and word[0] != '@' and word[0] != '#' and 'http' not in word and word != 'RT'])
        #print(cleanedtext)
        analysis = TextBlob(cleanedtext)
        sentiment = analysis.sentiment.polarity
        sum1 += sentiment

        if sentiment == 0:
            #ignore since not a opinion, its a general statement
            noOfTweets -= 1
    if noOfTweets > 0:
        AvgSentiment = sum1/noOfTweets
    return AvgSentiment

def runmytfidf(completeComment, topNumber):
    commentList = []

    #preprocessing the comments
    for i in range(0,10):
        commentList.append(tb(preprocessing(completeComment[i])))

    returnList=[]
    #Obtaing the Top Key words for all the pages
    for i, page in enumerate(commentList):
        scores = {word: tfidf(word, page, commentList) for word in page.words}
        sorted_words = sorted(scores.items(), key=lambda x: x[1], reverse=True)
        topWords=[]
        for word, score in sorted_words[:topNumber]:
            topWords.append(word)
        returnList.append(topWords)

    return returnList

def read_line_eos_noums(self,
                            path):
        """
        Generator.
        Similar as the function read_line_eos from
        the text_mani module. The only diference here
        is that we keep track of all the noums.

        :type path: str
        """
        for line in open(path):
            if len(list(self.all_noums)) <= self.max_noums:
                blob = TextBlob(line)
                noums = set(blob.noun_phrases)
                self.all_noums = self.all_noums.union(noums)
            for word in line.split():
                yield word
            yield '<eos>'

def get_polarity(text):
    """Get the degree of polarity of text.

    Parameters
    ----------
    text : str
        The text to analyze.

    Returns
    -------
    float
        The polarity of the text.

    """
    cleaned_text = clean_text(text)
    analysis = TextBlob(cleaned_text)
    return analysis.sentiment.polarity

def findSentiment(keywords):

    k_aux = {}
    for k in keywords:
        blob = TextBlob(k)
        k_aux[k] = {}

        if blob.sentiment.polarity < 0:
            k_aux[k]['word'] = 'negative'
        elif blob.sentiment.polarity > 0:
            k_aux[k]['word'] = 'positive'
        else:
            k_aux[k]['word'] = 'neutral'

        k_aux[k]['sentiment'] = blob.sentiment.polarity
        k_aux[k]['subjectivity'] = blob.sentiment.subjectivity
    keywords = k_aux

    return keywords

def get_toot_sentiment(toot):
        '''
        Utility function to classify sentiment of passed toots
        using textblob's sentiment method
        '''
        # create TextBlob object of passed toot text
        analysis = TextBlob(toot)
        # set sentiment
        if analysis.sentiment.polarity > 0:
            return 'positive'
        elif analysis.sentiment.polarity == 0:
            return 'neutral'
        else:
            return 'negative'

def run(self):
        while 1: 
            msg=self.queue_in.get() # get() is blocking
            chat_id=msg.get_chat_id()
            if re.search(r'^(?:/|!)translate ', msg.get_text().lower()) and len(msg.get_text().split(" "))>=2:
                foreign=msg.get_text().split(" ",1)[1]
                try:
                    b=textblob.TextBlob(foreign)
                    reply="{}".format(b.translate(to="de"))
                except textblob.exceptions.NotTranslated:
                    reply="Error while translation. (Are there smileys in some words?)"
                self.bot.sendMessage(chat_id,reply)

def fix_typos(self):
        self.user_input = TextBlob(self.user_input.lower()).tags
        # Fix lazy user typos, or slang
        words = list()
        for i in self.user_input:
            words.append(i[0])

        for part in range(len(words)):
            if words[part] in slang_typo_dict.keys():
                words[part] = slang_typo_dict[words[part]]
        self.user_input = ' '.join(words)
        return False  # Returns false to move on to help_check

def check_phrase_similarity(self):
        self.user_input = TextBlob(self.user_input.lower()).tags
        self.input_len = len(self.user_input)
        for phrase_type in PHRASE_TYPES:
            for phrase in getattr(keywords, phrase_type):
                score = float()
                for word in self.user_input:
                    for n in phrase:
                        if word and n not in unimportant_words:
                            score += liquidmetal.score(n, word[0]) / self.input_len
                if score >= 0.7:  # Could be increased/ decreased through testing to find more optimal value
                    self.response = random.choice(getattr(responses, phrase_type))
                    return True
        return False

def polarity(text):
    """Return the text's sentiment polarity (-1 negative, 1 positive)"""
    return TextBlob(text).sentiment.polarity

def subjectivity(text):
    """Return the text's sentiment subjectivity (0 objective, 1 subjective)"""
    return TextBlob(text).sentiment.subjectivity

# Calculated metrics: name, function that calculates them, and chart's color

def read_resume(file_path):
    resume_data = {}
    resume_data['content'] = TextBlob(read_file(file_path))
    resume_data['skills'] = extract_skills(str(resume_data['content']))
    resume_data['actions'] = extract_actions(resume_data['content'])

    return resume_data

def read_job(file_path):
    """Reads a text file with the job title on the first line and description following"""
    job_data = {}
    job_data['description'] = TextBlob(read_file(file_path))
    job_data['title'] = str(job_data['description']).split('\n')[0]
    job_data['skills'] = extract_skills(str(job_data['description']))
    job_data['noun_phrases'] = extract_nouns(job_data['description'])
    job_data['actions'] = extract_actions(job_data['description'])
    job_data['acronyms'] = extract_acronyms(job_data['description'])
    job_data['value_sentences'] = extract_value_sentences(job_data['description'])

    return job_data

def buscarTermo(termo):
    lista = list()
    bons = 0
    ruins = 0
    medios = 0
    analysis = None
    twitts = twitter.buscar(termo)
    for twitt in twitts:
        palavras = texto.limparTexto(twitt.text)
        lista = lista + palavras.split()
        analysis = tb(twitt.text)
        if analysis.sentiment.polarity > 0:
            bons += 1
        else:          
            ruins +=1
    count  = Counter(lista)

    listagem = list()
    sentimento = list()
    sentimento.append({'bons':bons,'ruins':ruins,'media':np.mean(analysis.sentiment.polarity)})

    for item in count:
        listagem.append({'text':item,"size":count[item],"repeticao":count[item]})
    id = mongo.salvar(termo,listagem,sentimento)
    rd.salvar(termo,id)
    retorno = {'resultados':listagem,'sentimento':sentimento}
    return retorno

def sentiment_analysis(sentence):
    sentence = tb(sentence)
    if (sentence.sentiment.polarity < -0.3):
        return 'neg'
    elif (sentence.sentiment.polarity > -0.3 and sentence.sentiment.polarity < 0.3):
        return 'neutral'
    else:
        return 'pos'

def sentiment(data):
    try:
        blob = TextBlob(data)
        sentiment_value = round(blob.sentiment.polarity, 2)
    except Exception as err:
        print("At sentiment {}".format(err))
        sentiment_value = None

    return sentiment_value

def delete_negative_comment(insta_username):
    # Function Logic to Delete Negative Comments..
    media_id = get_post_id(insta_username)
    request_url = (BASE_URL + 'media/%s/comments/?access_token=%s') % (media_id, APP_ACCESS_TOKEN)
    print 'GET request url : %s\n' % (request_url)
    comment_info = requests.get(request_url).json()

    if comment_info['meta']['code'] == 200:     #Check if the
        # re are Negative Comments Using textblob.sentiments Library
        if len(comment_info['data']):
            for x in range(0, len(comment_info['data'])):
                comment_id = comment_info['data'][x]['id']
                comment_text = comment_info['data'][x]['text']
                blob = TextBlob(comment_text, analyzer=NaiveBayesAnalyzer())
                if (blob.sentiment.p_neg > blob.sentiment.p_pos):
                    print '\t(-)Negative comment : %s' % (comment_text)
                    delete_url = (BASE_URL + 'media/%s/comments/%s/?access_token=%s') % (
                    media_id, comment_id, APP_ACCESS_TOKEN)
                    print 'DELETE request url : %s' % (delete_url)
                    delete_info = requests.delete(delete_url).json()

                    if delete_info['meta']['code'] == 200:      #Check if negative comments are deleted or not
                        print '\t\t\t*****Comment successfully deleted!*****\n'
                    else:
                        print '\t\t\t*****Unable to delete comment!*****\n'
        else:
            print '\n\t\t\t*****There are no existing comments on the post!*****'
    else:       #if Page Not Found
         print '\n\t\t\t*****Status code other than 200 received!*****'

def run(text):
    return sentiment_polarity(TextBlob(text))

def run(text):
    return sentiment_polarity(TextBlob(text))

def run(text):
    return sentiment_polarity(TextBlob(text))

def run(text):
    return sentiment_polarity(TextBlob(text))

def run(text):
    return sentiment_polarity(TextBlob(text))

def run(text):
    return sentiment_polarity(TextBlob(text))

def run(text):
    return sentiment_polarity(TextBlob(text))

def run(text):
    return sentiment_polarity(TextBlob(text))

def run(text):
    return sentiment_polarity(TextBlob(text))

def run(text):
    return sentiment_polarity(TextBlob(text))

def run(text):
    return sentiment_polarity(TextBlob(text))

def run(text):
    return sentiment_polarity(TextBlob(text))

def run(text):
    return sentiment_polarity(TextBlob(text))

def run(text):
    return sentiment_polarity(TextBlob(text))

def run(text):
    return sentiment_polarity(TextBlob(text))

def run(text):
    return sentiment_polarity(TextBlob(text))

def run(text):
    return sentiment_polarity(TextBlob(text))

def run(text):
    return sentiment_polarity(TextBlob(text))

def run(text):
    return sentiment_polarity(TextBlob(text))

def run(text):
    return sentiment_polarity(TextBlob(text))

def run(text):
    return sentiment_polarity(TextBlob(text))