def train(results):
# get files
vocab_file = results.vocab
labels_file = results.labels
train_file = results.train
step = results.step
iterations = results.iter
if not step:
step = 0.01
if not iterations:
iterations = 10
logger.debug( 'Started training with options:' + "\n" +
'training file: ' + str(train_file) + "\n" +
'step size: ' + str(step) + "\n" +
'no. of iter: ' + str(iterations) + "\n" +
'vocab file: ' + str(vocab_file) + "\n" +
'labels file: ' + str(labels_file) + "\n")
if not os.path.exists('model/meta_data'):
meta_data_instance = MetaData(vocab_file,labels_file)
meta_data = meta_data_instance.get_meta_data()
logger.info("Writing meta data file")
write_obj(meta_data,'meta_data')
else:
logger.info("meta data file already exists ... loading")
meta_data = read_obj('meta_data')
if not os.path.exists('model/train.feats'):
train_feats = extract_feats(meta_data,train_file)
logger.info("Writing extracted feats for training files to train.feats")
write_obj(train_feats,'train.feats')
else:
logger.info("train.feats already exists ... loading.")
train_feats = read_obj('train.feats')
if not os.path.exists('model/model'):
classifier = Perceptron(meta_data)
classifier.train(train_feats,step,iterations)
logger.info("Done Training, model is written in model file")
model = classifier.get_theta()
write_obj(model, 'model')
else:
logger.info('model already exists, nothing to do!')
