def on_data(self, data):
global i
global big_d
if (i > 1000):
exit()
f = open('file.txt', 'a+')
j = json.loads(data)
s = j['text'].encode('utf-8')
f.write(s)
print('\n' + s)
f.truncate()
simple = {}
j['score'], j['magnitude'] = sentiment_analysis.analyze('file.txt')
simple['score']=j['score']
simple['timestamp_ms']=j['timestamp_ms']
f = open('file.txt', 'r+')
tweet_id = 'tweet' + str(i+1)
big_d[tweet_id] = simple
os.remove('result.json')
result = open('result.json', 'a+')
json.dump(big_d, result)
i += 1
f.close()
#os.system("gsutil cp result.json gs://tweet_bucket/")
return True
def get_tweets(query, start_date, end_date, get_sentiment=True):
tweet_criteria = got.manager.TweetCriteria().setQuerySearch(
query).setSince(start_date).setUntil(end_date).setTopTweets(
True).setMaxTweets(10)
overall_sentiment_score = 0.0
for tweet in got.manager.TweetManager.getTweets(tweet_criteria):
try:
sentiment = sentiment_analysis.analyze(tweet.text)[0]
category = content_classification.classify(tweet.text)
if category == "News/Politics" or category == "/Finance/Investing":
sentiment.score *= 1.5
overall_sentiment_score += sentiment.score
print(f"{tweet.text}: {category} {sentiment.score}\n")
except Exception as e:
print(f"Exception: {e}")
pass
if get_sentiment:
return overall_sentiment_score
else:
return got.manager.TweetManager.getTweets(tweet_criteria)
def analyze_url(url):
article = Article(url)
article.download()
article.parse()
result = sentiment_analysis.analyze(article.text)
return result[0].score
def index():
choice = request.form['option']
# First Long-term Analysis
twitter_sentiment_analysis.get_tweets(choice, 50)
result1 = sentiment_analysis.analyze("tweet.text")
# Second Short-term analysis
twitter_sentiment_analysis.get_tweets(choice, 10)
result2 = sentiment_analysis.analyze("tweet.text")
# Overall Score
overall_reliability = overall_scorer.isReliable(result1, result2)
overall_score = overall_scorer.scorer(result1, result2)
return render_template('result.html',
choice=choice,
overall_reliability=overall_reliability,
overall_score=overall_score)
def index():
if request.method == "POST":
req = request.form
text = req.get('text')
if text:
analysis = analyze(text)
return render_template('index.html', analysis=analysis, text=text)
else:
feedback = "Text to Analyze cannot be empty. Please fill it out."
return render_template('index.html', feedback=feedback)
return render_template('index.html')
def get_tweets(screen_name):
# Twitter only allows access to a users most recent 3240 tweets with this method
# authorize twitter, initialize tweepy
auth = tweepy.OAuthHandler(consumer_key, consumer_secret)
auth.set_access_token(access_token, access_secret)
api = tweepy.API(auth)
# initialize a list to hold all the tweepy Tweets
alltweets = []
# make initial request for most recent tweets (200 is the maximum allowed count)
new_tweets = api.user_timeline(screen_name=screen_name, count=20)
# save most recent tweets
alltweets.extend(new_tweets)
# save the id of the oldest tweet less one
oldest = alltweets[-1].id - 1
# keep grabbing tweets until there are no tweets left to grab
while len(new_tweets) > 0:
# all subsiquent requests use the max_id param to prevent duplicates
new_tweets = api.user_timeline(screen_name=screen_name, count=200, max_id=oldest)
# save most recent tweets
alltweets.extend(new_tweets)
# update the id of the oldest tweet less one
oldest = alltweets[-1].id - 1
# transform the tweepy tweets into a 2D array that will populate the csv
outtweets = [tweet.text.encode("utf-8") for tweet in alltweets]
# write the csv
print(outtweets)
sad_score_list = analyze(outtweets)
return sad_score_list
pass
def test_neg(resource, capsys):
analyze(resource('neg.txt'))
out, err = capsys.readouterr()
score = float(re.search('score of (.+?) with', out).group(1))
magnitude = float(re.search('magnitude of (.+?)', out).group(1))
assert score * magnitude < 0
def test_neutral(capsys):
analyze(os.path.join(RESOURCES, "neutral.txt"))
out, err = capsys.readouterr()
magnitude = float(re.search("magnitude of (.+?)", out).group(1))
assert magnitude <= 2.0
def test_mixed(capsys):
analyze(os.path.join(RESOURCES, "mixed.txt"))
out, err = capsys.readouterr()
score = float(re.search("score of (.+?) with", out).group(1))
assert score <= 0.3
assert score >= -0.3
def test_neg(capsys):
analyze(os.path.join(RESOURCES, "neg.txt"))
out, err = capsys.readouterr()
score = float(re.search("score of (.+?) with", out).group(1))
magnitude = float(re.search("magnitude of (.+?)", out).group(1))
assert score * magnitude < 0
def test_mixed(capsys):
analyze(os.path.join(RESOURCES, 'mixed.txt'))
out, err = capsys.readouterr()
score = float(re.search('score of (.+?) with', out).group(1))
assert score <= 0.3
assert score >= -0.3
def test_neg(capsys):
analyze(os.path.join(RESOURCES, 'neg.txt'))
out, err = capsys.readouterr()
score = float(re.search('score of (.+?) with', out).group(1))
magnitude = float(re.search('magnitude of (.+?)', out).group(1))
assert score * magnitude < 0
def test_pos(capsys):
analyze(os.path.join(RESOURCES, 'pos.txt'))
out, err = capsys.readouterr()
score = float(re.search('score of (.+?) with', out).group(1))
magnitude = float(re.search('magnitude of (.+?)', out).group(1))
assert score * magnitude > 0
def test_mixed(resource, capsys):
analyze(resource('mixed.txt'))
out, err = capsys.readouterr()
score = float(re.search('score of (.+?) with', out).group(1))
assert score <= 0.3
assert score >= -0.3
def test_neutral(capsys):
analyze(os.path.join(RESOURCES, 'neutral.txt'))
out, err = capsys.readouterr()
magnitude = float(re.search('magnitude of (.+?)', out).group(1))
assert magnitude <= 2.0
def test_neutral(resource, capsys):
analyze(resource('neutral.txt'))
out, err = capsys.readouterr()
magnitude = float(re.search('magnitude of (.+?)', out).group(1))
assert magnitude <= 2.0
def test_analyze():
assert not sa.analyze(filename)