MAINT Parameters validation for sklearn.datasets.load_files (#26203)

jiawei-zhang-a · jeremiedbb · web-flow · commit bc3a19dee944 · 2023-04-25T13:23:25.000Z
Co-authored-by: Jérémie du Boisberranger &lt;34657725+jeremiedbb@users.noreply.github.com&gt;
diff --git a/sklearn/datasets/_base.py b/sklearn/datasets/_base.py
@@ -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
 
@@ -104,6 +104,19 @@ 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,
     *,
diff --git a/sklearn/datasets/tests/test_base.py b/sklearn/datasets/tests/test_base.py
@@ -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"
diff --git a/sklearn/tests/test_public_functions.py b/sklearn/tests/test_public_functions.py
@@ -134,6 +134,7 @@ 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",
