def test_init_2(self):
mf = MatchingField()
seq = 'Hello, This is a test sequence for tokenizer.'
tok_seq = [
'Hello', ',', 'This', 'is', 'a', 'test', 'sequence', 'for', 'tokenizer', '.'
]
self.assertEqual(mf.tokenize(seq), tok_seq)
def test_preprocess_args_1(self):
mf = MatchingField()
arg_dict = mf.preprocess_args()
res_dict = {'sequential': True, 'init_token': None,
'eos_token': None, 'init_token': None,
'lower': False, 'preprocessing': None,
'sequential': True, 'tokenizer_arg': 'moses',
'unk_token': '<unk>'}
self.assertEqual(arg_dict, res_dict)
def test_init_1(self):
fields = [('left_a', MatchingField()), ('right_a', MatchingField())]
col_naming = {'id':'id', 'label':'label', 'left':'left',
'right':'right'}
path = os.path.join('.', 'test_datasets', 'sample_table_small.csv')
md = MatchingDataset(fields, col_naming, path=path)
self.assertEqual(md.id_field, 'id')
self.assertEqual(md.label_field, 'label')
self.assertEqual(md.all_left_fields, ['left_a'])
self.assertEqual(md.all_right_fields, ['right_a'])
self.assertEqual(md.all_text_fields, ['left_a', 'right_a'])
self.assertEqual(md.canonical_text_fields, ['_a'])
def test_extend_vectors_1(self):
vectors_cache_dir = '.cache'
if os.path.exists(vectors_cache_dir):
shutil.rmtree(vectors_cache_dir)
pathdir = os.path.abspath(os.path.join(test_dir_path, 'test_datasets'))
filename = 'fasttext_sample.vec'
file = os.path.join(pathdir, filename)
url_base = urljoin('file:', pathname2url(file))
vecs = Vectors(name=filename, cache=vectors_cache_dir, url=url_base)
self.assertIsInstance(vecs, Vectors)
vec_data = MatchingField._get_vector_data(vecs, vectors_cache_dir)
v = MatchingVocab(Counter())
v.vectors = torch.Tensor(1, vec_data[0].dim)
v.unk_init = torch.Tensor.zero_
tokens = {'hello', 'world'}
v.extend_vectors(tokens, vec_data)
self.assertEqual(len(v.itos), 4)
self.assertEqual(v.vectors.size(), torch.Size([4, 300]))
self.assertEqual(list(v.vectors[2][0:10]), [0.0] * 10)
self.assertEqual(list(v.vectors[3][0:10]), [0.0] * 10)
if os.path.exists(vectors_cache_dir):
shutil.rmtree(vectors_cache_dir)
def test_class_matching_dataset():
fields = [("left_a", MatchingField()), ("right_a", MatchingField())]
col_naming = {
"id": "id",
"label": "label",
"left": "left",
"right": "right"
}
path = os.path.join(test_dir_path, "test_datasets",
"sample_table_small.csv")
md = MatchingDataset(fields, col_naming, path=path)
assert md.id_field == "id"
assert md.label_field == "label"
assert md.all_left_fields == ["left_a"]
assert md.all_right_fields == ["right_a"]
assert md.all_text_fields == ["left_a", "right_a"]
assert md.canonical_text_fields == ["_a"]
def test_extend_vocab_1(self):
vectors_cache_dir = '.cache'
if os.path.exists(vectors_cache_dir):
shutil.rmtree(vectors_cache_dir)
mf = MatchingField()
lf = MatchingField(id=True, sequential=False)
fields = [('id', lf), ('left_a', mf), ('right_a', mf), ('label', lf)]
col_naming = {
'id': 'id',
'label': 'label',
'left': 'left_',
'right': 'right_'
}
pathdir = os.path.abspath(os.path.join(test_dir_path, 'test_datasets'))
filename = 'fasttext_sample.vec'
file = os.path.join(pathdir, filename)
url_base = urljoin('file:', pathname2url(file))
vecs = Vectors(name=filename, cache=vectors_cache_dir, url=url_base)
data_path = os.path.join(test_dir_path, 'test_datasets',
'sample_table_small.csv')
md = MatchingDataset(fields, col_naming, path=data_path)
mf.build_vocab()
mf.vocab.vectors = torch.Tensor(len(mf.vocab.itos), 300)
mf.extend_vocab(md, vectors=vecs)
self.assertEqual(len(mf.vocab.itos), 6)
self.assertEqual(mf.vocab.vectors.size(), torch.Size([6, 300]))
def _make_fields(header, id_attr, label_attr, ignore_columns, lower, tokenize,
include_lengths):
"""Create field metadata, i.e., attribute processing specification for each attribute.
This includes fields for label and ID columns.
Returns:
list(tuple(str, MatchingField)): A list of tuples containing column name
(e.g. "left_address") and corresponding :class:`~data.MatchingField` pairs,
in the same order that the columns occur in the CSV file.
"""
text_field = MatchingField(
lower=lower,
tokenize=tokenize,
init_token="<<<",
eos_token=">>>",
batch_first=True,
include_lengths=include_lengths,
)
numeric_field = MatchingField(sequential=False,
preprocessing=lambda x: int(x),
use_vocab=False)
id_field = MatchingField(sequential=False, use_vocab=False, id=True)
fields = []
for attr in header:
if attr == id_attr:
fields.append((attr, id_field))
elif attr == label_attr:
fields.append((attr, numeric_field))
elif attr in ignore_columns:
fields.append((attr, None))
else:
fields.append((attr, text_field))
return fields
def test_get_vector_data(self):
vectors_cache_dir = '.cache'
if os.path.exists(vectors_cache_dir):
shutil.rmtree(vectors_cache_dir)
pathdir = os.path.abspath(os.path.join('.', 'test_datasets'))
filename = 'fasttext_sample.vec'
file = os.path.join(pathdir, filename)
url_base = urljoin('file:', pathname2url(file))
vecs = Vectors(name=filename, cache=vectors_cache_dir, url=url_base)
self.assertIsInstance(vecs, Vectors)
vec_data = MatchingField._get_vector_data(vecs, vectors_cache_dir)
self.assertEqual(len(vec_data), 1)
if os.path.exists(vectors_cache_dir):
shutil.rmtree(vectors_cache_dir)
def test_init_1(self):
mf = MatchingField()
self.assertTrue(mf.sequential)
def test_reset_vector_cache_1(self):
mf = MatchingField()
reset_vector_cache()
self.assertDictEqual(mf._cached_vec_data, {})
def test_numericalize_2(self):
mf = MatchingField()
arr = [['a'], ['b'], ['c']]
mf.numericalize(arr)
def test_numericalize_1(self):
mf = MatchingField(id=True)
arr = [[1], [2], [3]]
mf.numericalize(arr)
self.assertEqual(arr, [[1], [2], [3]])
def test_build_vocab_3(self):
mf = MatchingField()
vector_file_name = 'fasttext.crawl_test.vec'
cache_dir = os.path.join(test_dir_path, 'test_datasets')
vec_data = mf.build_vocab(vectors=vector_file_name, cache=cache_dir)
self.assertIsNone(vec_data)
def test_build_vocab_2(self):
mf = MatchingField()
vector_file_name = 'fasttext.wiki_test.vec'
cache_dir = os.path.join(test_dir_path, 'test_datasets')
vec_data = mf.build_vocab(vectors=vector_file_name, cache=cache_dir)
def test_build_vocab_1(self):
mf = MatchingField()
mf.build_vocab()
def test_init_3(self):
mf = MatchingField(tokenize='random string')
