Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Fix STSB and WikiTexts tests #1737

Merged
merged 3 commits into from
May 23, 2022
Merged

Fix STSB and WikiTexts tests #1737

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
7d103f8
Fix STSB and WikiTexts tests
parmeet May 23, 2022
549222e
fix lint
parmeet May 23, 2022
56ee85b
Merge branch 'main' of github.com:pytorch/text into fix_inconsistent_…
parmeet May 23, 2022
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 1 addition & 1 deletion test/datasets/test_stsb.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -21,7 +21,7 @@ def _get_mock_dataset(root_dir):

seed = 1
mocked_data = defaultdict(list)
for file_name, name in zip(["sts-train.csv", "sts-dev.csv" "sts-test.csv"], ["train", "dev", "test"]):
for file_name, name in zip(["sts-train.csv", "sts-dev.csv", "sts-test.csv"], ["train", "dev", "test"]):
txt_file = os.path.join(temp_dataset_dir, file_name)
with open(txt_file, "w", encoding="utf-8") as f:
for i in range(5):
Expand Down
10 changes: 6 additions & 4 deletions test/datasets/test_wikitexts.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -25,28 +25,30 @@ def _get_mock_dataset(root_dir, base_dir_name):
file_names = ("wiki.train.tokens", "wiki.valid.tokens", "wiki.test.tokens")
for file_name in file_names:
csv_file = os.path.join(temp_dataset_dir, file_name)
mocked_lines = mocked_data[os.path.splitext(file_name)[0]]
mocked_lines = mocked_data[file_name.split(".")[1]]
with open(csv_file, "w", encoding="utf-8") as f:
for i in range(5):
rand_string = get_random_unicode(seed)
dataset_line = rand_string
f.write(f"{rand_string}\n")
dataset_line = f"{rand_string}\n"
f.write(dataset_line)

# append line to correct dataset split
mocked_lines.append(dataset_line)
seed += 1

if base_dir_name == WikiText103.__name__:
compressed_file = "wikitext-103-v1"
arcname_folder = "wikitext-103"
else:
compressed_file = "wikitext-2-v1"
arcname_folder = "wikitext-2"

compressed_dataset_path = os.path.join(base_dir, compressed_file + ".zip")
# create zip file from dataset folder
with zipfile.ZipFile(compressed_dataset_path, "w") as zip_file:
for file_name in file_names:
txt_file = os.path.join(temp_dataset_dir, file_name)
zip_file.write(txt_file, arcname=compressed_file)
zip_file.write(txt_file, arcname=os.path.join(arcname_folder, file_name))

return mocked_data

Expand Down