def setUp(self):
super(TestClassifierWorker, self).setUp()
self.cls = nltk.NaiveBayesClassifier.train([({'a': 'a', 'b': 'b'}, 'positive')])
self.data = []
for i in range(5):
d = RawStreamQueue()
d.source = 'test'
d.original = {}
d.text = "this is a test"
self.data.append(d)
ClassifiedStream.drop_collection()
def save(self, raw_data):
assert isinstance(raw_data, RawStreamQueue)
row = ClassifiedStream()
row.source = raw_data.source
row.original = raw_data.original
row.text = raw_data.text
row.tokens = list(self.tokenizer.getSearchTokens(row.text))
row.polarity = self.get_classifications(row.text)
row.save()
self.logger.debug('ClassifiedStream saved %s', row.id)
def setUp(self):
super(TestClassifierWorker, self).setUp()
self.cls = nltk.NaiveBayesClassifier.train([({
'a': 'a',
'b': 'b'
}, 'positive')])
self.data = []
for i in range(5):
d = RawStreamQueue()
d.source = 'test'
d.original = {}
d.text = "this is a test"
self.data.append(d)
ClassifiedStream.drop_collection()
def test_find_tokens(self):
s1 = ClassifiedStream()
s1.tokens = ['a', 'b', 'c']
s1.text = 'ab'
s1.source = 't'
s1.save()
s2 = ClassifiedStream()
s2.tokens = ['b', 'c']
s2.text = 'bs'
s2.source = 't'
s2.save()
s3 = ClassifiedStream()
s3.tokens = ['b', 'c']
s3.text = 'bs'
s3.source = 't'
s3.save()
self.assertEquals(1, len(ClassifiedStream.find_tokens(['a', 'b'])))
self.assertEquals(1, len(ClassifiedStream.find_tokens(['a'])))
self.assertEquals(1,
len(ClassifiedStream.find_tokens(['c', 'b'], s2.id)))
self.assertEquals(3, len(ClassifiedStream.find_tokens(['c', 'b'])))
def tearDown(self):
ClassifiedStream.drop_collection()
def tearDown(self):
ClassifiedStream.drop_collection()
RawStreamQueue.drop_collection()
def test_find_tokens(self):
s1 = ClassifiedStream()
s1.tokens = ['a', 'b', 'c']
s1.text = 'ab'
s1.source = 't'
s1.save()
s2 = ClassifiedStream()
s2.tokens = ['b', 'c']
s2.text = 'bs'
s2.source = 't'
s2.save()
s3 = ClassifiedStream()
s3.tokens = ['b', 'c']
s3.text = 'bs'
s3.source = 't'
s3.save()
self.assertEquals(1, len(ClassifiedStream.find_tokens(['a', 'b'])))
self.assertEquals(1, len(ClassifiedStream.find_tokens(['a'])))
self.assertEquals(1, len(ClassifiedStream.find_tokens(['c', 'b'], s2.id)))
self.assertEquals(3, len(ClassifiedStream.find_tokens(['c', 'b'])))
