def predict(self, features):
''' Predict importances '''
features = self.norm.transform(features[:,0:self.n_comp])
results = self.svr.predict(features)
#print results[0:100:5]
results = self.std_scaler_i.inverse_transform(results)
#print results[0:100:5]
return results
if __name__ == '__main__':
import corpus, featureExtractor
from featureExtractor import FeatureExtractor
print 'Loading corpus ...'
corpus = corpus.TwitterCorpus()
tweets = corpus.all_tweets()
importances = np.array([featureExtractor.tweet_importance(t) for t in tweets])
# try to load feature vectors
try: v = joblib.load('data/cache/vectors.joblib')
except:
print 'FeatureExtractor fit transform ...'
feat = FeatureExtractor()
v = feat.train(tweets, importances)
joblib.dump(v, 'data/cache/vectors.joblib')
print 'HotTweets train ...'
ht = HotTweets()
ht.train(v[0:1000], importances[0:1000])
