Skip to content

MAINT parameter validation for sklearn.datasets.fetch_lfw_people #25735

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

Closed
wants to merge 3 commits into from
Closed

MAINT parameter validation for sklearn.datasets.fetch_lfw_people #25735

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
0a15321
add parameter validation to dump_svmlight_file
Shivachauhan17 Feb 28, 2023
2873f24
add parameter validation to fetch_lfw_people
Shivachauhan17 Mar 1, 2023
2253c44
lint
Shivachauhan17 Mar 1, 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: 13 additions & 2 deletions sklearn/datasets/_lfw.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -10,7 +10,7 @@

from os import listdir, makedirs, remove
from os.path import join, exists, isdir

from ..utils._param_validation import validate_params,HasMethods
import logging

import numpy as np
Expand Down Expand Up @@ -230,7 +230,18 @@ def _fetch_lfw_people(
faces, target = faces[indices], target[indices]
return faces, target, target_names


@validate_params(
{
"data_home":[str,None],
"funneled":["boolean"],
"resize":[float,None],
"min_faces_per_person":[int,None],
"color":["boolean"],
"slice":["tuple of slice",(slice(0, 250), slice(0, 250))],
"download_if_missing":["boolean"],
"return_X_y":["boolean"],
}
)
def fetch_lfw_people(
*,
data_home=None,
Expand Down
11 changes: 10 additions & 1 deletion sklearn/datasets/_svmlight_format_io.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -25,6 +25,7 @@
from .. import __version__

from ..utils import check_array, IS_PYPY
from ..utils._param_validation import validate_params,StrOptions

if not IS_PYPY:
from ._svmlight_format_fast import (
Expand Down Expand Up @@ -403,7 +404,15 @@ def _dump_svmlight(X, y, f, multilabel, one_based, comment, query_id):
y_is_sp,
)


@validate_params({
"X":["array-like","sparse matrix"],
"y":["array-like","sparse matrix"],
"f":[str,StrOptions({"file"})],
"zero_based":[bool,True],
"comment":[str,None],
"query_id":["array-like",None],
"multilabel":[bool,False],
})
def dump_svmlight_file(
X,
y,
Expand Down
2 changes: 2 additions & 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 @@ -107,6 +107,8 @@ def _check_function_param_validation(
"sklearn.datasets.make_classification",
"sklearn.datasets.make_friedman1",
"sklearn.datasets.make_sparse_coded_signal",
"sklearn.datasets.dump_svmlight_file",
"sklearn.datasets.fetch_lfw_people",
"sklearn.decomposition.sparse_encode",
"sklearn.feature_extraction.grid_to_graph",
"sklearn.feature_extraction.img_to_graph",
Expand Down