MAINT Parameters validation for sklearn.datasets.fetch_kddcup99 (#25463)

pm155 · glemaitre · web-flow · commit 7671e54b8b1c · 2023-02-07T16:53:09.000+01:00
Co-authored-by: Guillaume Lemaitre &lt;g.lemaitre58@gmail.com&gt;
diff --git a/sklearn/datasets/_kddcup99.py b/sklearn/datasets/_kddcup99.py
@@ -22,6 +22,7 @@
 from . import get_data_home
 from ._base import RemoteFileMetadata
 from ._base import load_descr
+from ..utils._param_validation import StrOptions, validate_params
 from ..utils import Bunch
 from ..utils import check_random_state
 from ..utils import shuffle as shuffle_method
@@ -46,6 +47,18 @@
 logger = logging.getLogger(__name__)
 
 
+@validate_params(
+    {
+        "subset": [StrOptions({"SA", "SF", "http", "smtp"}), None],
+        "data_home": [str, None],
+        "shuffle": ["boolean"],
+        "random_state": ["random_state"],
+        "percent10": ["boolean"],
+        "download_if_missing": ["boolean"],
+        "return_X_y": ["boolean"],
+        "as_frame": ["boolean"],
+    }
+)
 def fetch_kddcup99(
     *,
     subset=None,
diff --git a/sklearn/tests/test_public_functions.py b/sklearn/tests/test_public_functions.py
@@ -103,6 +103,7 @@ def _check_function_param_validation(
     "sklearn.covariance.empirical_covariance",
     "sklearn.covariance.shrunk_covariance",
     "sklearn.datasets.fetch_california_housing",
+    "sklearn.datasets.fetch_kddcup99",
     "sklearn.datasets.make_classification",
     "sklearn.datasets.make_sparse_coded_signal",
     "sklearn.decomposition.sparse_encode",
