model = load_word2vec_model(model_file, mmap='r')
lr_entity_model = EntityModel.load(lr_entity_file, mmap='r')
centroid_entity_model = EntityModel.load(centroid_entity_file, mmap='r')
norm_entities = [(entity.lower(), entity)
for entity in lr_entity_model.entities]
while True:
try:
line = raw_input('> ').strip()
except EOFError:
break
words, entities = parse_query(norm_entities, line)
lr_top = top_entities(model, lr_entity_model, entities, words)
centroid_top = top_entities(model, centroid_entity_model, entities,
words)
for (lr_score, lr_ent), (centroid_score,
centroid_ent) in zip(lr_top, centroid_top):
print '%-50s%10.3f | %-50s%10.3f' % (lr_ent, lr_score,
centroid_ent, centroid_score)
if __name__ == '__main__':
np.random.seed(1729)
logging.basicConfig(format='%(asctime)s : %(levelname)s : %(message)s',
level=logging.INFO)
baker.run()
('q', q),
('pred_bps', float(pred_bps)),
('avg_zeros', float(avg_zeros)),
('avg_err', float(avg_err)),
]))
def load_quant_data(json_filename):
import pandas as pd
with open(json_filename) as fin:
data = []
decoder = json.JSONDecoder(object_pairs_hook=OrderedDict)
for line in fin:
row = decoder.decode(line)
accuracy = row['accuracy'][-1]
assert accuracy['section'] == 'total' # XXX
acc_percentage = float(accuracy['correct']) / (accuracy['correct'] + accuracy['incorrect'])
row['accuracy'] = acc_percentage
data.append(row)
return pd.DataFrame(data)
if __name__ == '__main__':
logging.basicConfig(format='%(asctime)s : %(levelname)s : %(message)s',
level=logging.INFO)
baker.run()