def split_train_test(train_dir, vocab_dir, test_size, n_labeled, wordslength):
#train_dir = './data/labeled1.txt'
#vocab_dir = './data/vocab_yinan_test_rnn4.txt'
if not os.path.exists(vocab_dir):
build_vocab(train_dir, vocab_dir, 1000)
categories, cat_to_id = read_category()
words, word_to_id = read_vocab(vocab_dir)
x, y = process_file(train_dir, word_to_id, cat_to_id, wordslength)
# x_rnn, y_rnn = process_file_rnn(train_dir, word_to_id, cat_to_id, 600)
listy = []
for i in range(np.shape(y)[0]):
for j in range(np.shape(y)[1]):
if y[i][j] == 1:
listy.append(j)
listy = np.array(listy)
X_train, X_test, y_train, y_test = \
train_test_split(x, listy, test_size=test_size)
# X_train = X_train[:(n_labeled + 24)]
trn_ds = Dataset(
X_train,
np.concatenate(
[y_train[:n_labeled], [None] * (len(y_train) - n_labeled)]))
# trn_ds = Dataset(X_train, np.concatenate(
# [y_train[:n_labeled], [None] * (len(y_train) - n_labeled)]))
fully_tst_ds = Dataset(X_test, y_test)
X_val, X_real_test, y_val, y_real_test = \
train_test_split(X_test, y_test, test_size=0.5)
tst_ds = Dataset(X_real_test, y_real_test)
val_ds = Dataset(X_val, y_val)
fully_labeled_trn_ds = Dataset(X_train, y_train)
# print (fully_labeled_trn_ds.get_entries()[0])
return trn_ds, tst_ds, y_train, fully_labeled_trn_ds, fully_tst_ds, val_ds
def split_train_test_rnn(train_dir, vocab_dir, vocab_size, test_size, val_size,
n_labeled, wordslength, categories_class):
if not os.path.exists(vocab_dir):
build_vocab(train_dir, vocab_dir, vocab_size)
categories, cat_to_id = read_category(categories_class)
words, word_to_id = read_vocab(vocab_dir)
data_id, label_id = process_file_rnn(train_dir, word_to_id, cat_to_id,
wordslength)
# x_rnn, y_rnn = process_file_rnn(train_dir, word_to_id, cat_to_id, 600)
y = kr.utils.to_categorical(label_id, num_classes=len(cat_to_id))
listy = []
for i in range(np.shape(y)[0]):
for j in range(np.shape(y)[1]):
if y[i][j] == 1:
listy.append(j)
listy = np.array(listy)
X_train, X_test, y_train, y_test = \
train_test_split(data_id, listy, test_size=test_size)
X_train_al = []
X_test_al = []
res = []
for i in X_train:
for j in range(wordslength):
a = i.count(j)
if a > 0:
res.append(a)
else:
res.append(0)
X_train_al.append(res)
res = []
for i in X_test:
for j in range(wordslength):
a = i.count(j)
if a > 0:
res.append(a)
else:
res.append(0)
X_test_al.append(res)
res = []
X_train_al = np.array(X_train_al)
X_test_al = np.array(X_test_al)
trn_ds_al = Dataset(
X_train_al,
np.concatenate(
[y_train[:n_labeled], [None] * (len(y_train) - n_labeled)]))
tst_ds_al = Dataset(X_test_al, y_test)
X_train_rnn = kr.preprocessing.sequence.pad_sequences(X_train, wordslength)
X_test_rnn = kr.preprocessing.sequence.pad_sequences(X_test, wordslength)
X_train_rnn, X_val_rnn, y_train_rnn, y_val_rnn = \
train_test_split(X_train_rnn, y_train, test_size=val_size)
trn_ds_rnn = Dataset(
X_train_rnn,
np.concatenate(
[y_train_rnn[:n_labeled],
[None] * (len(y_train_rnn) - n_labeled)]))
val_ds_rnn = Dataset(X_val_rnn, y_val_rnn)
tst_ds_rnn = Dataset(X_test_rnn, y_test)
fully_labeled_trn_ds_al = Dataset(X_train_al, y_train)
fully_labeled_trn_ds_rnn = Dataset(X_train_rnn, y_train_rnn)
return trn_ds_al, tst_ds_al, y_train_rnn, fully_labeled_trn_ds_al, \
trn_ds_rnn, tst_ds_rnn, fully_labeled_trn_ds_rnn, val_ds_rnn
