def test_feature_vector(self):
tweet = {}
tweet[
'text'] = "This is a test #bla @rkempter Sommerferien and Lorem Ipsum"
tweet['entities'] = {}
tweet['entities']['hashtags'] = [{"text": "bla"}, {"text": "blu"}]
tweet['entities']['urls'] = [{
"expanded_url": "http://www.twitter.com"
}]
tweet['entities']['user_mentions'] = [{"id": "1111"}, {"id": "2222"}]
tweet['user'] = {"str_id": "1111"}
trainer = AdaptiveTweetClassifierTrainer(self.q)
trainer.query_set = {}
trainer.query_set['keyword'] = ["Sommerferien", "blu", "empty", "leer"]
trainer.query_set['user'] = ["2222", "3333"]
vector = trainer.get_feature_vector(tweet)
real_vector = [1.0, 1.0, 0.0, 0.0, 1.0, 0.0, 0.2222222222222222]
self.assertEqual(vector, real_vector)
def test_feature_vector(self):
tweet = {}
tweet["text"] = "This is a test #bla @rkempter Sommerferien and Lorem Ipsum"
tweet["entities"] = {}
tweet["entities"]["hashtags"] = [{"text": "bla"}, {"text": "blu"}]
tweet["entities"]["urls"] = [{"expanded_url": "http://www.twitter.com"}]
tweet["entities"]["user_mentions"] = [{"id": "1111"}, {"id": "2222"}]
tweet["user"] = {"str_id": "1111"}
trainer = AdaptiveTweetClassifierTrainer(self.q)
trainer.query_set = {}
trainer.query_set["keyword"] = ["Sommerferien", "blu", "empty", "leer"]
trainer.query_set["user"] = ["2222", "3333"]
vector = trainer.get_feature_vector(tweet)
real_vector = [1.0, 1.0, 0.0, 0.0, 1.0, 0.0, 0.2222222222222222]
self.assertEqual(vector, real_vector)
cursor.close()
self.connection.commit()
except Exception as inst:
print type(inst) # the exception instance
print inst.args # arguments stored in .args
print inst # __str__ allows args to printed directly
if not self.queue.empty():
self.classifier = self.queue.get()
return False # force a restart of the stream
else:
return True
def on_error(self, status):
print status
if __name__ == '__main__':
query_set = dict()
query_set['keyword'] = ['obama', 'usa']
query_set['user'] = ['326698989', '326802887', '314575095', '16573941', '15033883']
queue = Queue.Queue()
trainer = AdaptiveTweetClassifierTrainer(queue)
l = TweetStreamListener(trainer, queue)
auth = OAuthHandler(CONSUMER_KEY, CONSUMER_SECRET)
auth.set_access_token(ACCESS_TOKEN, ACCESS_TOKEN_SECRET)
stream = Stream(auth, l)
while True:
stream.filter(follow=query_set['user'], track=query_set['keyword'])
query_set = trainer.get_query_set()
print "Model loading"