for i in features[l2]:
characters[i] = 1.0
train.append((lex_col[lang1][l1], lex_col[lang2][l2], embedding, characters))
# test data
test = []
for (l1, l2) in test_keys:
embedding = E_dict[l2] if l2 in E_dict else zero
characters = np.zeros((len(features)))
for i in features[l2]:
characters[i] = 1.0
test.append((lex_col[lang1][l1], lex_col[lang2][l2], embedding, characters))
model.reset()
model.train = train
before = model.eval(test)[0:2]
#print size, experiment
C_best = 0
err, hmm, mistakes = float("inf"), float("inf"), None
# grid search
for C in [1.0]: #0.0, 0.1, 0.5, 1.0, 2.0, 3.0, 4.0]:
model.C = C
model.learn(disp=0)
err_tmp, hmm_tmp, mistakes_tmp = model.eval(test)
if hmm_tmp < hmm:
err, hmm, mistakes = err_tmp, hmm_tmp, mistakes_tmp
