Created
December 2, 2017 14:47
-
-
Save s-fujimoto/c8f84abdedd78745d350aa38536f0b02 to your computer and use it in GitHub Desktop.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
#!/usr/bin/env python | |
import twitter | |
import boto3 | |
import os | |
keyword = '#reinvent' | |
lang = 'en' | |
region = 'us-east-1' | |
size = 100 * 100 | |
def get_tweet_texts(): | |
api = twitter.Api(consumer_key=os.environ['consumer_key'], | |
consumer_secret=os.environ['consumer_secret'], | |
access_token_key=os.environ['access_token_key'], | |
access_token_secret=os.environ['access_token_secret'], | |
sleep_on_rate_limit=True) | |
maxid = None | |
corpus = [] | |
for i in range(int(size/100)): | |
results = api.GetSearch(term=keyword,result_type='recent',count=100,max_id=maxid,lang=lang) | |
maxid = min([result.id for result in results]) - 1 | |
corpus.extend(results) | |
return corpus | |
def detect_sentiment(corpus): | |
result = { | |
'Mixed': 0, | |
'Negative': 0, | |
'Neutral': 0, | |
'Positive': 0, | |
'MIXED': 0, | |
'NEGATIVE': 0, | |
'NEUTRAL': 0, | |
'POSITIVE': 0, | |
'MOST_NEGATIVE': {'score':0}, | |
'MOST_POSITIVE': {'score':0}, | |
} | |
comprehend = boto3.client('comprehend', region_name=region) | |
batch_size = 25 | |
for tweets in [corpus[i:i+batch_size] for i in range(0, len(corpus), batch_size)]: | |
sentiment_results = comprehend.batch_detect_sentiment( | |
TextList=[tweet.text for tweet in tweets], | |
LanguageCode=lang | |
) | |
for sentiment in sentiment_results['ResultList']: | |
result[sentiment['Sentiment']] += 1 | |
if sentiment['Sentiment'] == 'NEGATIVE' and sentiment['SentimentScore']['Negative'] > result['MOST_NEGATIVE']['score']: | |
result['MOST_NEGATIVE'] = {'score': sentiment['SentimentScore']['Negative'], 'tweet': tweets[sentiment['Index']]} | |
elif sentiment['Sentiment'] == 'POSITIVE' and sentiment['SentimentScore']['Positive'] > result['MOST_POSITIVE']['score']: | |
result['MOST_POSITIVE'] = {'score': sentiment['SentimentScore']['Positive'], 'tweet': tweets[sentiment['Index']]} | |
for key, score in sentiment['SentimentScore'].items(): | |
result[key] += score | |
return result | |
def stdout(result): | |
sum_score = sum([value for key, value in result.items() if key in ('Mixed', 'Negative', 'Neutral', 'Positive')]) | |
print('Positive : {:4d}件 : {:.1f}%'.format(result['POSITIVE'], round(result['Positive']/sum_score*100), 1)) | |
print('Negative : {:4d}件 : {:.1f}%'.format(result['NEGATIVE'], round(result['Negative']/sum_score*100), 1)) | |
print('Mixed : {:4d}件 : {:.1f}%'.format(result['MIXED'], round(result['Mixed']/sum_score*100), 1)) | |
print('Neutral : {:4d}件 : {:.1f}%'.format(result['NEUTRAL'], round(result['Neutral']/sum_score*100), 1)) | |
if result['MOST_POSITIVE'].get('tweet'): | |
print('Most positive tweet is "{}"'.format(result['MOST_POSITIVE']['tweet'].text)) | |
if result['MOST_NEGATIVE'].get('tweet'): | |
print('Most negative tweet is "{}"'.format(result['MOST_NEGATIVE']['tweet'].text)) | |
def main(): | |
corpus = get_tweet_texts() | |
result = detect_sentiment(corpus) | |
stdout(result) | |
if __name__ == '__main__': | |
main() |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment