def test_imdb(self):
from torchtext.experimental.datasets import IMDB
from torchtext.vocab import Vocab
# smoke test to ensure imdb works properly
train_dataset, test_dataset = IMDB()
self._helper_test_func(
len(train_dataset), 25000, train_dataset[0][1][:10],
[13, 1568, 13, 246, 35468, 43, 64, 398, 1135, 92])
self._helper_test_func(len(test_dataset), 25000,
test_dataset[0][1][:10],
[13, 125, 1051, 5, 246, 1652, 8, 277, 66, 20])
# Test API with a vocab input object
old_vocab = train_dataset.get_vocab()
new_vocab = Vocab(counter=old_vocab.freqs, max_size=2500)
new_train_data, new_test_data = IMDB(vocab=new_vocab)
# Add test for the subset of the standard datasets
train_dataset, = IMDB(data_select=('train'))
self._helper_test_func(
len(train_dataset), 25000, train_dataset[0][1][:10],
[13, 1568, 13, 246, 35468, 43, 64, 398, 1135, 92])
train_iter, test_iter = torchtext.experimental.datasets.raw.IMDB()
self._helper_test_func(len(train_iter), 25000,
next(iter(train_iter))[1][:25],
'I rented I AM CURIOUS-YEL')
self._helper_test_func(len(test_iter), 25000,
next(iter(test_iter))[1][:25],
'I love sci-fi and am will')
del train_iter, test_iter
def test_imdb(self):
from torchtext.experimental.datasets import IMDB
from torchtext.vocab import Vocab
# smoke test to ensure imdb works properly
train_dataset, test_dataset = IMDB()
self.assertEqual(len(train_dataset), 25000)
self.assertEqual(len(test_dataset), 25000)
assert_allclose(
train_dataset[0][1][:10],
torch.tensor([13, 1568, 13, 246, 35468, 43, 64, 398, 1135,
92]).long())
assert_allclose(
train_dataset[-1][1][:10],
torch.tensor([2, 71, 4555, 194, 3328, 15144, 42, 227, 148,
8]).long())
assert_allclose(
test_dataset[0][1][:10],
torch.tensor([13, 125, 1051, 5, 246, 1652, 8, 277, 66, 20]).long())
assert_allclose(
test_dataset[-1][1][:10],
torch.tensor([13, 1035, 14, 21, 28, 2, 1051, 1275, 1008,
3]).long())
# Test API with a vocab input object
old_vocab = train_dataset.get_vocab()
new_vocab = Vocab(counter=old_vocab.freqs, max_size=2500)
new_train_data, new_test_data = IMDB(vocab=new_vocab)
def test_imdb(self):
from torchtext.experimental.datasets import IMDB
from torchtext.vocab import Vocab
# smoke test to ensure imdb works properly
train_dataset, test_dataset = IMDB()
self.assertEqual(len(train_dataset), 25000)
self.assertEqual(len(test_dataset), 25000)
# Test API with a vocab input object
old_vocab = train_dataset.get_vocab()
new_vocab = Vocab(counter=old_vocab.freqs, max_size=2500)
new_train_data, new_test_data = IMDB(vocab=new_vocab)
# Delete the dataset after we're done to save disk space on CI
datafile = os.path.join(self.project_root, ".data", "imdb")
conditional_remove(datafile)
datafile = os.path.join(self.project_root, ".data", "aclImdb")
conditional_remove(datafile)
datafile = os.path.join(self.project_root, ".data",
"aclImdb_v1.tar.gz")
conditional_remove(datafile)
def init(config):
''' Loads the GloVe embeddings for the words
which occur in the IMDB train set vocab
and uses that vocab to create train, validation
and test sets for the IMDB dataset. Extracts the
pad_id token.
'''
import os
if not os.path.isdir('.data'):
os.mkdir('.data')
# Extract the initial vocab from the IMDB dataset
vocab = IMDB(data_select='train')[0].get_vocab()
# Create GloVe embeddings based on original vocab
# word freqs
glove_vocab = torchtext.vocab.Vocab(
counter=vocab.freqs,
max_size=MAX_VOCAB_SIZE,
min_freq=MIN_FREQ,
vectors=torchtext.vocab.GloVe(name='6B'))
# Acquire 'Spacy' tokenizer for the vocab words
tokenizer = get_tokenizer('spacy', 'en_core_web_sm')
# Acquire train and test IMDB sets with previously created
# GloVe vocab and 'Spacy' tokenizer
train_set, test_set = IMDB(tokenizer=tokenizer, vocab=glove_vocab)
# Extract the vocab of the acquired train set
vocab = train_set.get_vocab()
# Extract the token used for padding
pad_id = vocab['<pad>']
# Split the train set into train and validation sets
train_set, valid_set = split_train_val(train_set)
config['train'] = train_set
config['val'] = valid_set
config['test'] = test_set
config['vocab'] = vocab
config['pad_id'] = pad_id
def test_imdb(self):
from torchtext.experimental.datasets import IMDB
from torchtext.vocab import Vocab
# smoke test to ensure imdb works properly
train_dataset, test_dataset = IMDB()
self.assertEqual(len(train_dataset), 25000)
self.assertEqual(len(test_dataset), 25000)
assert_allclose(
train_dataset[0][1][:10],
torch.tensor([13, 1568, 13, 246, 35468, 43, 64, 398, 1135,
92]).long())
assert_allclose(
train_dataset[-1][1][:10],
torch.tensor([2, 71, 4555, 194, 3328, 15144, 42, 227, 148,
8]).long())
assert_allclose(
test_dataset[0][1][:10],
torch.tensor([13, 125, 1051, 5, 246, 1652, 8, 277, 66, 20]).long())
assert_allclose(
test_dataset[-1][1][:10],
torch.tensor([13, 1035, 14, 21, 28, 2, 1051, 1275, 1008,
3]).long())
# Test API with a vocab input object
old_vocab = train_dataset.get_vocab()
new_vocab = Vocab(counter=old_vocab.freqs, max_size=2500)
new_train_data, new_test_data = IMDB(vocab=new_vocab)
# Delete the dataset after we're done to save disk space on CI
datafile = os.path.join(self.project_root, ".data", "imdb")
conditional_remove(datafile)
datafile = os.path.join(self.project_root, ".data", "aclImdb")
conditional_remove(datafile)
datafile = os.path.join(self.project_root, ".data",
"aclImdb_v1.tar.gz")
conditional_remove(datafile)