MAINT Parameters validation for sklearn.datasets.get_data_home (#26260)

jiawei-zhang-a · jeremiedbb · web-flow · commit 363c63304f29 · 2023-04-25T13:24:17.000Z
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
@@ -35,6 +35,11 @@
 RemoteFileMetadata = namedtuple("RemoteFileMetadata", ["filename", "url", "checksum"])
 
 
+@validate_params(
+    {
+        "data_home": [str, os.PathLike, None],
+    }
+)
 def get_data_home(data_home=None) -> str:
     """Return the path of the scikit-learn data directory.
 
@@ -58,7 +63,7 @@ def get_data_home(data_home=None) -> str:
 
     Returns
     -------
-    data_home: str
+    data_home: str or path-like, default=None
         The path to scikit-learn data directory.
     """
     if data_home is None:
diff --git a/sklearn/datasets/_openml.py b/sklearn/datasets/_openml.py
@@ -903,7 +903,7 @@ def fetch_openml(
         data_home = None
     else:
         data_home = get_data_home(data_home=data_home)
-        data_home = join(data_home, "openml")
+        data_home = join(str(data_home), "openml")
 
     # check valid function arguments. data_id XOR (name, version) should be
     # provided
diff --git a/sklearn/tests/test_public_functions.py b/sklearn/tests/test_public_functions.py
@@ -131,6 +131,7 @@ def _check_function_param_validation(
     "sklearn.datasets.fetch_olivetti_faces",
     "sklearn.datasets.fetch_rcv1",
     "sklearn.datasets.fetch_species_distributions",
+    "sklearn.datasets.get_data_home",
     "sklearn.datasets.load_breast_cancer",
     "sklearn.datasets.load_diabetes",
     "sklearn.datasets.load_digits",
