Skip to content

MAINT Parameters validation for sklearn.datasets.load_files #26203

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

Merged
merged 12 commits into from
Apr 25, 2023
Merged

MAINT Parameters validation for sklearn.datasets.load_files #26203

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
12 commits
Select commit Hold shift + click to select a range
2dff9b0
sklearn.datasets.load_files
jiawei-zhang-a Apr 17, 2023
9a3c715
fix the Path probmlem on Windows
jiawei-zhang-a Apr 19, 2023
500d50c
delete paxios path
jiawei-zhang-a Apr 19, 2023
9b1a173
resolve conflict
jiawei-zhang-a Apr 19, 2023
1b33f23
try to fix the problem on windows
jiawei-zhang-a Apr 20, 2023
f3d17a6
Update sklearn/datasets/tests/test_base.py
jiawei-zhang-a Apr 20, 2023
90687a0
Update sklearn/datasets/tests/test_base.py
jiawei-zhang-a Apr 20, 2023
c178494
Update sklearn/datasets/tests/test_base.py
jiawei-zhang-a Apr 20, 2023
dfd8777
Update sklearn/datasets/_base.py
jiawei-zhang-a Apr 20, 2023
111ac4f
local test
jiawei-zhang-a Apr 20, 2023
eaaa61a
import stroptions
jiawei-zhang-a Apr 20, 2023
9e5946a
revert unrelated
jeremiedbb Apr 25, 2023
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
15 changes: 14 additions & 1 deletion sklearn/datasets/_base.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -22,7 +22,7 @@
from ..utils import check_random_state
from ..utils import check_pandas_support
from ..utils.fixes import _open_binary, _open_text, _read_text, _contents
from ..utils._param_validation import validate_params, Interval
from ..utils._param_validation import validate_params, Interval, StrOptions

import numpy as np

Expand Down Expand Up @@ -99,6 +99,19 @@ def _convert_data_dataframe(
return combined_df, X, y


@validate_params(
{
"container_path": [str, os.PathLike],
"description": [str, None],
"categories": [list, None],
"load_content": ["boolean"],
"shuffle": ["boolean"],
"encoding": [str, None],
"decode_error": [StrOptions({"strict", "ignore", "replace"})],
"random_state": ["random_state"],
"allowed_extensions": [list, None],
}
)
def load_files(
container_path,
*,
Expand Down
5 changes: 3 additions & 2 deletions sklearn/datasets/tests/test_base.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -98,10 +98,11 @@ def test_default_load_files(test_category_dir_1, test_category_dir_2, load_files
def test_load_files_w_categories_desc_and_encoding(
test_category_dir_1, test_category_dir_2, load_files_root
):
category = os.path.abspath(test_category_dir_1).split("/").pop()
category = os.path.abspath(test_category_dir_1).split(os.sep).pop()
res = load_files(
load_files_root, description="test", categories=category, encoding="utf-8"
load_files_root, description="test", categories=[category], encoding="utf-8"
)

assert len(res.filenames) == 1
assert len(res.target_names) == 1
assert res.DESCR == "test"
Expand Down
1 change: 1 addition & 0 deletions sklearn/tests/test_public_functions.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -133,6 +133,7 @@ def _check_function_param_validation(
"sklearn.datasets.load_breast_cancer",
"sklearn.datasets.load_diabetes",
"sklearn.datasets.load_digits",
"sklearn.datasets.load_files",
"sklearn.datasets.load_iris",
"sklearn.datasets.load_linnerud",
"sklearn.datasets.load_svmlight_file",
Expand Down