0

I have a df that looks like this:

       text
0   Thanks, I’ll have a read!
1   Am I too late

How do I apply TextBlob tokenization to every word in sentence and average the polarity scores of every word in each sentence?

for example, I can do this with a single sentence in a variable:

from textblob import TextBlob
import import statistics as s

#tokenize word in sentence
a = TextBlob("""Thanks, I'll have a read!""")
print a.words

    WordList(['Thanks', 'I', "'ll", 'have', 'a', 'read'])

#get polarity of every word
    for i in a.words:
        print( a.sentiment.polarity)

    0.25
    0.25
    0.25
    0.25
    0.25
    0.25


#calculating the mean of the scores
c=[]
for i in a.words: 
    c.append(a.sentiment.polarity)
    d = s.mean(c)
    print (d)

0.25

How do I apply the a.words to every row of dataframe column for sentence?

New df:

      text                        score
0   Thanks, I’ll have a read!      0.25
1   Am I too late                  0.24

closet I come is that I can get polarity of every sentence using this function on the dataframe:

def sentiment_calc(text):
    try:
        return TextBlob(text).sentiment.polarity
    except:
        return None

df_sentences['sentiment'] = df_sentences['text'].apply(sentiment_calc)

Thank you in advance.

RustyShackleford
  • 3,462
  • 9
  • 40
  • 81

0 Answers0