Fixes some tests

Author: JATAYU000

openml/_api/clients/http.py

@@ -12,6 +12,7 @@
 from requests import Response
 
 from openml.__version__ import __version__
+from openml.exceptions import OpenMLHashException
 
 if TYPE_CHECKING:
     from openml._api.config import DelayMethod
@@ -132,7 +133,7 @@ def request(
         *,
         use_cache: bool = False,
         use_api_key: bool = False,
-        md5_checksum: str | None,
+        md5_checksum: str | None = None,
         **request_kwargs: Any,
     ) -> Response:
         url = urljoin(self.server, urljoin(self.base_url, path))
@@ -178,7 +179,10 @@ def _verify_checksum(self, response: Response, md5_checksum: str) -> None:
         # ruff sees hashlib.md5 as insecure
         actual = hashlib.md5(response.content).hexdigest()  # noqa: S324
         if actual != md5_checksum:
-            raise ValueError(f"MD5 checksum mismatch: expected {md5_checksum}, got {actual}")
+            raise OpenMLHashException(
+                "Checksum of downloaded file is unequal to the expected checksum {md5_checksum} "
+                f"when downloading {response.url}.",
+            )
 
     def get(
         self,

openml/datasets/dataset.py

@@ -992,7 +992,8 @@ def _to_dict(self) -> dict[str, dict]:
         }
 
 
-def _read_features(features_file: Path) -> dict[int, OpenMLDataFeature]:
+def _read_features(features_file: str | Path) -> dict[int, OpenMLDataFeature]:
+    features_file = Path(features_file)
     features_pickle_file = Path(_get_features_pickle_file(str(features_file)))
     try:
         with features_pickle_file.open("rb") as fh_binary:
@@ -1001,7 +1002,12 @@ def _read_features(features_file: Path) -> dict[int, OpenMLDataFeature]:
     except:  # noqa: E722
         from openml._api import api_context
 
-        return api_context.backend.datasets.parse_features_file(features_file, features_pickle_file)
+        features = api_context.backend.datasets.parse_features_file(
+            features_file, features_pickle_file
+        )
+        with features_pickle_file.open("wb") as fh_binary:
+            pickle.dump(features, fh_binary)
+        return features
 
 
 # TODO(eddiebergman): Should this really exist?
@@ -1025,6 +1031,9 @@ def _read_qualities(qualities_file: str | Path) -> dict[str, float]:
     except:  # noqa: E722
         from openml._api import api_context
 
-        return api_context.backend.datasets.parse_qualities_file(
+        qualities = api_context.backend.datasets.parse_qualities_file(
             qualities_file, qualities_pickle_file
         )
+        with qualities_pickle_file.open("wb") as fh_binary:
+            pickle.dump(qualities, fh_binary)
+        return qualities

openml/datasets/functions.py

@@ -1005,7 +1005,6 @@ def _get_dataset_arff(
 
 # TODO remove cache dir
 def _get_dataset_features_file(
-    did_cache_dir: str | Path | None,  # noqa: ARG001
     dataset_id: int,
 ) -> Path:
     """API call to load dataset features. Loads from cache or downloads them.
@@ -1035,7 +1034,6 @@ def _get_dataset_features_file(
 
 # TODO remove cache dir
 def _get_dataset_qualities_file(
-    did_cache_dir: str | Path | None,  # noqa: ARG001
     dataset_id: int,
 ) -> Path | None:
     """Get the path for the dataset qualities file, or None if no qualities exist.

tests/test_api/test_datasets.py

@@ -0,0 +1,21 @@
+from __future__ import annotations
+
+import pytest
+import pandas as pd
+import requests
+from openml.testing import TestBase
+from openml._api import api_context
+from openml._api.resources.datasets import DatasetsV1, DatasetsV2
+
+class TestDatasetsEndpoints(TestBase):
+    def setUp(self):
+        super().setUp()
+        self.v1_api = DatasetsV1(
+            api_context.backend.datasets._http,
+            api_context.backend.datasets._minio
+        )
+        self.v2_api = DatasetsV2(
+            api_context.backend.datasets._http,
+            api_context.backend.datasets._minio
+        )
+    

tests/test_datasets/test_dataset.py

@@ -466,16 +466,3 @@ def test__read_qualities(static_cache_dir, workdir, mocker):
     assert pickle_mock.dump.call_count == 1
 
 
-
-def test__check_qualities():
-    qualities = [{"oml:name": "a", "oml:value": "0.5"}]
-    qualities = openml.datasets.dataset._check_qualities(qualities)
-    assert qualities["a"] == 0.5
-
-    qualities = [{"oml:name": "a", "oml:value": "null"}]
-    qualities = openml.datasets.dataset._check_qualities(qualities)
-    assert qualities["a"] != qualities["a"]
-
-    qualities = [{"oml:name": "a", "oml:value": None}]
-    qualities = openml.datasets.dataset._check_qualities(qualities)
-    assert qualities["a"] != qualities["a"]

tests/test_datasets/test_dataset_functions.py

@@ -441,8 +441,8 @@ def test__getarff_md5_issue(self):
 
         self.assertRaisesRegex(
             OpenMLHashException,
-            "Checksum of downloaded file is unequal to the expected checksum abc when downloading "
-            "https://www.openml.org/data/download/61. Raised when downloading dataset 5.",
+            "Checksum of downloaded file is unequal to the expected checksum abc "
+            "when downloading https://www.openml.org/data/download/61.",
             _get_dataset_arff,
             description,
         )
@@ -451,17 +451,15 @@ def test__getarff_md5_issue(self):
 
     @pytest.mark.uses_test_server()
     def test__get_dataset_features(self):
-        features_file = _get_dataset_features_file(self.workdir, 2)
+        features_file = _get_dataset_features_file(2)
         assert isinstance(features_file, Path)
-        features_xml_path = self.workdir / "features.xml"
-        assert features_xml_path.exists()
+        assert features_file.exists()
 
     @pytest.mark.uses_test_server()
     def test__get_dataset_qualities(self):
-        qualities = _get_dataset_qualities_file(self.workdir, 2)
+        qualities = _get_dataset_qualities_file(2)
         assert isinstance(qualities, Path)
-        qualities_xml_path = self.workdir / "qualities.xml"
-        assert qualities_xml_path.exists()
+        assert qualities.exists()
 
     @pytest.mark.uses_test_server()
     def test_get_dataset_force_refresh_cache(self):
@@ -565,7 +563,7 @@ def test__retrieve_class_labels(self):
         labels = openml.datasets.get_dataset(2).retrieve_class_labels(
             target_name="product-type",
         )
-        assert labels == ["C", "H", "G"]
+        assert labels == ["C", "G", "H"]
 
         # Test workaround for string-typed class labels
         custom_ds = openml.datasets.get_dataset(2)