sentiment.py

## Sentiment analysis for whole dataset; get sentiment mean score for every movie
from nltk.sentiment.vader import SentimentIntensityAnalyzer
import pandas as pd
import math

def get_sentiment_score():
    sid = SentimentIntensityAnalyzer()
    sentiment_review = []
    sentiment_mean = []
    for i in range(0, len(reviews)):
        sentence = reviews[i]
        ss = sid.polarity_scores(str(sentence))
    #     for k in sorted(ss):
    #         print '{0}: {1}, '.format(k, ss[k])
    #     sentiment_review.append(str(sentence))
        ss['review_detail'] = sentence[0]
        ss['movie_name'] = sentence[1]
        sentiment_review.append(ss)
    # print pd.DataFrame(sentiment_review)
    sentiment_review = pd.DataFrame(sentiment_review)
    sentiment_review.to_csv('sentiment_reviews.csv', index = False)
    for i in list(set(list(sentiment_review['movie_name']))):
        sentiment_mean.append([i, sentiment_review[\
                        sentiment_review['movie_name'] == i]['compound'].mean()])
    sentiment_mean = pd.DataFrame(sentiment_mean)
    sentiment_mean.columns = ['movie_name', 'sentiment_mean']
    sentiment_review.to_csv('sentiment_mean.csv', index = False)

    return sentiment_review, sentiment_mean