from model import StringFeatures
feats = StringFeatures()
assert len(feats) == 0
assert len(feats.get_attributes("running")) == 8
feats.get_attributes("running", True)
assert len(feats.get_attributes("cattable", True)) == 8
assert len(feats.attributes) == 16
feats.store("running")
print feats["cattable"]
#print len(feats)
test_keys_set = set(test)
for (l1, l2) in test_keys:
embedding = E_dict[l2] if l2 in E_dict else zero
test.append((lex_col[lang1][l1], lex_col[lang2][l2], embedding))
entry1 = lex_col[lang1].pp(l1)
entry2 = lex_col[lang2].pp(l2)
#if "num=PL" in entry2[1]:
# print l2, entry2[1]
for size in [100]: #sizes:
train_keys = sample_from_d(d, size, lex_col[lang1], lex_col[lang2], test_keys_set)
train = []
features = StringFeatures()
for (l1, l2) in train_keys:
features.store(l2)
for (l1, l2) in test_keys:
features.store(l2)
model = RRBM(lex_col.N, 64, len(features), [], C=0.1)
# training data
for (l1, l2) in train_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