def main():
data_folder = 'data/sources/wikipedia'
models_folder = 'classifier/models'
save_loc = 'site/wikiclassify/wiki'
if not os.path.exists(data_folder):
os.makedirs(data_folder)
if next(os.walk(data_folder))[1]:
retrain = False
if retrain:
input, target, classes = data.sample(data_folder)
model = classifier.build(input.shape, target.shape)
classifier.train(model, input, target)
classifier.save(models_folder, model, classes)
else:
model, classes = classifier.load(models_folder, sorted(os.listdir(models_folder))[-1])
for root, dirs, files in os.walk(data_folder):
for file in files:
if not file.startswith('.'):
with open(root+'/'+file) as f:
input = data.str2mat(f.read())
output = classifier.run(model, input)
def retrieve_tweets():
classif = train()
# called when a new tweets is retrieved from streaming
@receiver(streamer.tweet_retrieved)
def my_callback(sender, **kwargs):
tweet = kwargs['tweet']
if tweet['coordinates']:
tweet_id = tweet['id']
user = tweet['user']['name'].encode('utf-8')
lat = tweet['coordinates']['coordinates'][1]
lng = tweet['coordinates']['coordinates'][0]
text = tweet['text'].encode('utf-8')
if tweet_id and user and lat and lng and text:
# classify tweets (tourism or nontourism)
classification = classif.classify(feature_extractor_lda_tripadvisor_top_words_weights(text))
# for tourism-related tweets, classify as being positive or negative
if classification == 'tourism':
sentiment = sentiment_analyzer.classify(feature_extractor(tweet))
print 'Label: {} || Tweet: {}'.format(sentiment, text)
# create Tweet object and save to db
tweet_obj = Tweet.objects.create(tweet_id=tweet_id, user=user,
lat=lat, lng=lng, text=text,
classification=classification,
sentiment=sentiment)
tweet_obj.save()
# call streamer
streamer.stream()
return None
def retrieve_tweets():
classif = train()
# called when a new tweets is retrieved from streaming
@receiver(streamer.tweet_retrieved)
def my_callback(sender, **kwargs):
tweet = kwargs['tweet']
if tweet['coordinates']:
tweet_id = tweet['id']
user = tweet['user']['name'].encode('utf-8')
lat = tweet['coordinates']['coordinates'][1]
lng = tweet['coordinates']['coordinates'][0]
text = tweet['text'].encode('utf-8')
if tweet_id and user and lat and lng and text:
# classify tweets (tourism or nontourism)
classification = classif.classify(
feature_extractor_lda_tripadvisor_top_words_weights(text))
# for tourism-related tweets, classify as being positive or negative
if classification == 'tourism':
sentiment = sentiment_analyzer.classify(
feature_extractor(tweet))
print 'Label: {} || Tweet: {}'.format(sentiment, text)
# create Tweet object and save to db
tweet_obj = Tweet.objects.create(
tweet_id=tweet_id,
user=user,
lat=lat,
lng=lng,
text=text,
classification=classification,
sentiment=sentiment)
tweet_obj.save()
# call streamer
streamer.stream()
return None