How to use the textblob.TextBlob function in textblob

def test_upper(self):
        blob = tb.TextBlob('lorem ipsum')
        assert_true(is_blob(blob.upper()))
        assert_equal(blob.upper(), tb.TextBlob('LOREM IPSUM'))

def test_sentiment_of_emoticons(self):
        b1 = tb.TextBlob("Faces have values =)")
        b2 = tb.TextBlob("Faces have values")
        assert_true(b1.sentiment[0] > b2.sentiment[0])

def test_senences_with_space_before_punctuation(self):
        text = "Uh oh. This sentence might cause some problems. : Now we're ok."
        b = tb.TextBlob(text)
        assert_equal(len(b.sentences), 3)

def sentiment(str):
		blob = TextBlob(str)
		return blob.sentiment.polarity

print("A value>0 is positive, close to 0 slightly positive")
print("A value<0 is negative, close to 0 slightly negative","\n")

myview=TextBlob("I hate movie 1. It was too violent ")
print(myview,":","\n",myview.sentiment,"\n")
dialog=TextBlob("I hate movie 1. It was too violent ")

myview=TextBlob("I like autumn. It reminds me of some sad music ")
print(myview,":","\n",myview.sentiment,"\n")
dialog=dialog+myview

myview=TextBlob("The love story was cool too. A bit mushy but cool ")
print(myview,":","\n",myview.sentiment,"\n")
dialog=dialog+myview

myview=TextBlob("I would like to get out of here and see other horizons ")
print(myview,":","\n",myview.sentiment,"\n")
dialog=dialog+myview
     
#Parse noun phrases
print("Parse noun phrases to find potential key words:") 
print(dialog.noun_phrases)
  

m=input("Press ENTER if you agree to complete X's profiling dataset with some images")
print("The AI program will now enter social networks again and pick up KEY images")
print("that X commented with TAGS that fit the KEYWORDS found","\n")
print("CRL-MM Representation Learning Meta Model(see next section in book)")
print("The following image is a sample of the dataset of X. ")


take_images=input("Press ENTER to Continue")

def preprocess(self, textString):
        text = TextBlob(textString.lower())
        words = text.words.singularize()
        words = [self.preprocessDigits(word)
                 for word in words]
        words = [self.preprocessMonths(word)
                 for word in words]
        newWordList = []
        newWordList.append('')
        newWordList.extend(words)
        newWordList.append('')
        grams = [gram for gram in nltk.trigrams(
            newWordList) if len(set(gram) - self.stopWords) > 0]
        grams.extend([gram for gram in nltk.bigrams(newWordList)
                      if len(set(gram) - self.stopWords) > 0])
        grams.extend([word for word in words
                      if word not in self.stopWords])
        return grams

def translateMessage(self, text):
        translateKeyword = 'translate to'
        translateSep = '-'
        textSeperator = 'and send to'
        
        text = text.lower()

        langStart = text.index(translateKeyword)
        langEnd = text.index(translateSep)
        textEnd = text.index(textSeperator)

        langDetect = text[langStart+13:langEnd].strip()
        textDetect = text[langEnd+1:textEnd].strip()
        contactDetect = text[textEnd+11:].strip()

        blob = TextBlob(textDetect)
        translatedText = str(blob.translate(to=self._ISOlanguage[langDetect.strip()]))

        self.send_to_whatsapp_id(contactDetect,translatedText)
        self._translateContacts.append(contactDetect)

def read_job_description(file_path):
    """Reads a text file with the job title on the first line and description following
    
    Args:
        file_path (str): path to text file (.txt format) containing job title and description
        
    Returns:
        dictionary containing job title and job description as a TextBlob
    """
    job_data = {}
    with open(file_path) as file:
        job_data['title'] = unicode(file.readline(), errors='ignore').replace('\n', '')
        description = unicode(file.read(), errors='ignore')
        job_data['description'] = TextBlob(description.decode('utf8').encode('ascii','ignore'))
    job_data['keywords'] = extract_keywords(job_data['description'])
    job_data['value_sentences'] = extract_value_sentences(job_data['description'])
    job_data['actions'] = extract_actions(job_data['description'])
    job_data['acronyms'] = extract_acronyms(job_data['description'])
    return job_data

def read_resume(file_path):
    with open(file_path) as file:
        content = unicode(file.read(), errors='ignore')

    return TextBlob(content.decode('utf8').encode('ascii', 'ignore'))