def get_sentiment(self, cumulative=False):
'''
Calculates the sentiment of the cluster. It returns
a list of tuples (date, value) where date value is the accumulated sentiment
of that date.
'''
emotional_rollercoaster = []
tsa = TwitterSemanticAnalyser()
for document in self.document_dict.values():
sentiment = tsa.extract_sentiment(' '.join(token for token in document.tokens))
emotional_rollercoaster.append( (document.date, sentiment) )
#It's important to sort this list otherwise itertools will npt work.
#The we group emotion scores by date. t[1][1] is the score of a document at time d.
x = sorted(emotional_rollercoaster)
grouped_emotions = [(d, sum([float(t[1][1]) for t in g])) for d, g in itertools.groupby(x, lambda x: x[0])]
return grouped_emotions
def get_sentiment(self, cumulative=False):
'''
Calculates the sentiment of the cluster. It returns
a list of tuples (date, value) where date value is the accumulated sentiment
of that date.
'''
emotional_rollercoaster = []
tsa = TwitterSemanticAnalyser()
for document in self.document_dict.values():
sentiment = tsa.extract_sentiment(' '.join(token for token in document.tokens))
emotional_rollercoaster.append( (document.date, sentiment) )
#It's important to sort this list otherwise itertools will npt work.
#The we group emotion scores by date. t[1][1] is the score of a document at time d.
x = sorted(emotional_rollercoaster)
grouped_emotions = [(d, sum([float(t[1][1]) for t in g])) for d, g in itertools.groupby(x, lambda x: x[0])]
return grouped_emotions
def test_analysing_multiple_docs(self):
tsa = TwitterSemanticAnalyser()
calculated = tsa.analyse_corpus(corpus)
expected = [([], ('positive', '0.0593345'), [
'Gheblawi Beyond belief', 'Egypt interesting discussion',
'religious history', 'make-up', 'interesting'
]), ([], ('negative', '-0.31492'), ['Messi', 'News']),
([('retweet', 'FieldTerminology')], ('neutral', 0), []),
([], ('positive', '0.060677'), [
'RT Beyond belief', 'Egypt interesting discussion',
'religious history', 'make-up', 'interesting'
]),
([('Bob Jones', 'Person'), ('Bob', 'Person'),
('Egypt', 'Country')], ('neutral', 0),
['Bob Jones', 'Egypt']),
([], ('negative', '-0.200008'), []),
([], ('positive', '0.61373'), ['happy'])]
self.assertEquals(expected, calculated)
def test_extract_keywords(self):
tsa = TwitterSemanticAnalyser()
calculated = tsa.extract_keywords(tweet5)
expected = ['Bob Jones', 'Egypt']
self.assertEqual(expected, calculated)
def test_sentiment_extraction(self):
tsa = TwitterSemanticAnalyser()
calculated_sad = tsa.extract_sentiment(tweet6)
calculated_happy = tsa.extract_sentiment(tweet7)
self.assertEqual(('negative', '-0.200008'), calculated_sad)
self.assertEqual(('positive', '0.61373'), calculated_happy)
def test_entity_extraction(self):
tsa = TwitterSemanticAnalyser()
calculated = tsa.extract_entities(tweet5)
expected = [('Bob Jones', 'Person'), ('Bob', 'Person'),
('Egypt', 'Country')]
self.assertEqual(expected, calculated)
def test_analysing_multiple_docs(self):
tsa = TwitterSemanticAnalyser()
calculated = tsa.analyse_corpus(corpus)
expected = [([], ('positive', '0.0593345'), ['Gheblawi Beyond belief', 'Egypt interesting discussion', 'religious history', 'make-up', 'interesting']), ([], ('negative', '-0.31492'), ['Messi', 'News']), ([('retweet', 'FieldTerminology')], ('neutral', 0), []), ([], ('positive', '0.060677'), ['RT Beyond belief', 'Egypt interesting discussion', 'religious history', 'make-up', 'interesting']), ([('Bob Jones', 'Person'), ('Bob', 'Person'), ('Egypt', 'Country')], ('neutral', 0), ['Bob Jones', 'Egypt']), ([], ('negative', '-0.200008'), []), ([], ('positive', '0.61373'), ['happy'])]
self.assertEquals(expected, calculated)
def test_extract_keywords(self):
tsa = TwitterSemanticAnalyser()
calculated = tsa.extract_keywords(tweet5)
expected = ['Bob Jones', 'Egypt']
self.assertEqual(expected, calculated)
def test_sentiment_extraction(self):
tsa = TwitterSemanticAnalyser()
calculated_sad = tsa.extract_sentiment(tweet6)
calculated_happy = tsa.extract_sentiment(tweet7)
self.assertEqual(('negative', '-0.200008'), calculated_sad)
self.assertEqual(('positive', '0.61373'), calculated_happy)
def test_entity_extraction(self):
tsa = TwitterSemanticAnalyser()
calculated = tsa.extract_entities(tweet5)
expected = [('Bob Jones', 'Person'), ('Bob', 'Person'), ('Egypt', 'Country')]
self.assertEqual(expected, calculated)
