victormurcia

def lemmatize_sentence(tokens):
    lemmatizer = WordNetLemmatizer()
    lemmatized_sentence = []
    for word, tag in pos_tag(tokens):
        if tag.startswith('NN'):
            pos = 'n'
        elif tag.startswith('VB'):
            pos = 'v'
        else:
            pos = 'a'

victormurcia

stop_words = stopwords.words('english')

def remove_noise(tokens, stop_words = ()):

    cleaned_tokens = []

    for token, tag in pos_tag(tokens):

        if tag.startswith("NN"):
            pos = 'n'

victormurcia

def get_chapters_for_model(cleaned_tokens_list):
    for tokens in cleaned_tokens_list:
        yield dict([tokens, True] for token in tokens)

victormurcia

print(classifier.classify(dict([token, True] for token in tokens_for_model)))

victormurcia

def book_sentiment_wrapper(book_dir, book_id,stop_words):
    
    #Start by splitting book into chapters and saving them into textfiles
    chapter_list = split_book_into_chapters(book_dir, book_id)
    num_chapters = len(chapter_list)
    
    #Initialize sentiment array
    book_sentiment = []
    chapter_num = 0
    for chapter_num in range(num_chapters):

victormurcia

chap_list = []
for i in range(len(cleaned_chaps)):
    chap_elem = ' '.join(cleaned_chaps[i])
    chap_list.append(chap_elem)

#Make pandas dataframe. Each row is a chapter
df_pos = pd.DataFrame(chap_list, columns=['chapter_contents'])

#Add column with Chapter names. 
chapter_names = ['Prelude']

victormurcia

sid = SentimentIntensityAnalyzer()
df_pos['compound'] = [sid.polarity_scores(x)['compound'] for x in df_pos['chapter_contents']]
df_pos['neg']      = [sid.polarity_scores(x)['neg'] for x in      df_pos['chapter_contents']]
df_pos['neu']      = [sid.polarity_scores(x)['neu'] for x in      df_pos['chapter_contents']]
df_pos['pos']      = [sid.polarity_scores(x)['pos'] for x in      df_pos['chapter_contents']]

victormurcia

df_pos['joy']          = [NRCLex(x).raw_emotion_scores['joy']          for x in df_pos['chapter_contents']]
df_pos['positive']     = [NRCLex(x).raw_emotion_scores['positive']     for x in df_pos['chapter_contents']]
df_pos['anticipation'] = [NRCLex(x).raw_emotion_scores['anticipation'] for x in df_pos['chapter_contents']]
df_pos['sadness']      = [NRCLex(x).raw_emotion_scores['sadness']      for x in df_pos['chapter_contents']]
df_pos['surprise']     = [NRCLex(x).raw_emotion_scores['surprise']     for x in df_pos['chapter_contents']]
df_pos['negative']     = [NRCLex(x).raw_emotion_scores['negative']     for x in df_pos['chapter_contents']]
df_pos['anger']        = [NRCLex(x).raw_emotion_scores['anger']        for x in df_pos['chapter_contents']]
df_pos['disgust']      = [NRCLex(x).raw_emotion_scores['disgust']      for x in df_pos['chapter_contents']]
df_pos['trust']        = [NRCLex(x).raw_emotion_scores['trust']        for x in df_pos['chapter_contents']]
df_pos['fear']         = [NRCLex(x).raw_emotion_scor

victormurcia

def build_service(api_key):
    '''
    To build the YT API service
    '''    
    key = api_key
    YOUTUBE_API_SERVICE_NAME = "youtube"    
    YOUTUBE_API_VERSION = "v3"    
    return build(YOUTUBE_API_SERVICE_NAME, YOUTUBE_API_VERSION, developerKey = key)

victormurcia

def get_id(url):
    '''
    To get the video id from the video url, example: 
    'https://www.youtube.com/watch?v=wfAPXlFu8', videoId = wfAPXlFu8
    '''   
    u_pars = urlparse(url)    
    quer_v = parse_qs(u_pars.query).get('v')    
    if quer_v:        
        return quer_v[0]    
    pth = u_pars.path.split('/')