def train_wrapper(seed_fn, source_fn, target_fn, reverse=False, mx_path=None,
train_size=5000):
logging.info("Training...")
seed_trans = read_dict(seed_fn, reverse=reverse)
#we only need to load the vectors for the words in the training data
#semantic spaces contain additional words
source_words = set(seed_trans.iterkeys())
target_words = set().union(*seed_trans.itervalues())
source_sp = Space.build(source_fn, lexicon=source_words)
source_sp.normalize()
target_sp = Space.build(target_fn, lexicon=target_words)
target_sp.normalize()
logging.info("Learning the translation matrix")
tm, used_for_train = train_tm(source_sp, target_sp, seed_trans, train_size)
mx_path = default_output_fn(mx_path, seed_fn, source_fn, target_fn,)
logging.info("Saving the translation matrix to {}".format(mx_path))
np.save('{}.npy'.format(mx_path), tm)
pickle.dump(used_for_train, open('{}.train_wds'.format(mx_path),
mode='w'))
return tm, used_for_train
def load_tr_mx(self):
if self.args.mx_path:
if self.tr_mx or self.exclude_from_test:
raise Exception(
"Translation mx or training words specified amibiguously.")
else:
self.args.mx_path = default_output_fn(
self.args.mx_path, self.args.seed_fn, self.args.source_fn,
self.args.target_fn)
logging.info("Loading from {}".format(self.args.mx_path))
self.exclude_from_test = pickle.load(open(
'{}.train_wds'.format(self.args.mx_path)))
self.tr_mx = np.load('{}.npy'.format(self.args.mx_path))
elif self.tr_mx is None or not self.exclude_from_test:
raise Exception('Translation matrix or training words unspecified')
