Add/1034 (#1352) dataset lazy loading default

* Towards lazy-by-default for dataset loading

* Isolate lazy behavior to pytest function outside of class

* Solve concurrency issue where test would use same cache

* Ensure metadata is downloaded to verify dataset is processed

* Clean up to reflect new defaults and tests

* Fix oversight from 1335

* Download data as was 0.14 behavior

* Restore test

* Formatting

* Test obsolete, replaced by test_get_dataset_lazy_behavior

Author: PGijsbers

openml/datasets/functions.py

@@ -416,8 +416,8 @@ def _name_to_id(
 
 def get_datasets(
     dataset_ids: list[str | int],
-    download_data: bool = True,  # noqa: FBT001, FBT002
-    download_qualities: bool = True,  # noqa: FBT001, FBT002
+    download_data: bool = False,  # noqa: FBT001, FBT002
+    download_qualities: bool = False,  # noqa: FBT001, FBT002
 ) -> list[OpenMLDataset]:
     """Download datasets.
 
@@ -450,14 +450,14 @@ def get_datasets(
 
 
 @openml.utils.thread_safe_if_oslo_installed
-def get_dataset(  # noqa: C901, PLR0912, PLR0915
+def get_dataset(  # noqa: C901, PLR0912
     dataset_id: int | str,
-    download_data: bool | None = None,  # Optional for deprecation warning; later again only bool
+    download_data: bool = False,  # noqa: FBT002, FBT001
     version: int | None = None,
     error_if_multiple: bool = False,  # noqa: FBT002, FBT001
     cache_format: Literal["pickle", "feather"] = "pickle",
-    download_qualities: bool | None = None,  # Same as above
-    download_features_meta_data: bool | None = None,  # Same as above
+    download_qualities: bool = False,  # noqa: FBT002, FBT001
+    download_features_meta_data: bool = False,  # noqa: FBT002, FBT001
     download_all_files: bool = False,  # noqa: FBT002, FBT001
     force_refresh_cache: bool = False,  # noqa: FBT001, FBT002
 ) -> OpenMLDataset:
@@ -485,7 +485,7 @@ def get_dataset(  # noqa: C901, PLR0912, PLR0915
     ----------
     dataset_id : int or str
         Dataset ID of the dataset to download
-    download_data : bool (default=True)
+    download_data : bool (default=False)
         If True, also download the data file. Beware that some datasets are large and it might
         make the operation noticeably slower. Metadata is also still retrieved.
         If False, create the OpenMLDataset and only populate it with the metadata.
@@ -499,12 +499,12 @@ def get_dataset(  # noqa: C901, PLR0912, PLR0915
         Format for caching the dataset - may be feather or pickle
         Note that the default 'pickle' option may load slower than feather when
         no.of.rows is very high.
-    download_qualities : bool (default=True)
+    download_qualities : bool (default=False)
         Option to download 'qualities' meta-data in addition to the minimal dataset description.
         If True, download and cache the qualities file.
         If False, create the OpenMLDataset without qualities metadata. The data may later be added
         to the OpenMLDataset through the `OpenMLDataset.load_metadata(qualities=True)` method.
-    download_features_meta_data : bool (default=True)
+    download_features_meta_data : bool (default=False)
         Option to download 'features' meta-data in addition to the minimal dataset description.
         If True, download and cache the features file.
         If False, create the OpenMLDataset without features metadata. The data may later be added
@@ -523,28 +523,6 @@ def get_dataset(  # noqa: C901, PLR0912, PLR0915
     dataset : :class:`openml.OpenMLDataset`
         The downloaded dataset.
     """
-    # TODO(0.15): Remove the deprecation warning and make the default False; adjust types above
-    #   and documentation. Also remove None-to-True-cases below
-    if any(
-        download_flag is None
-        for download_flag in [download_data, download_qualities, download_features_meta_data]
-    ):
-        warnings.warn(
-            "Starting from Version 0.15 `download_data`, `download_qualities`, and `download_featu"
-            "res_meta_data` will all be ``False`` instead of ``True`` by default to enable lazy "
-            "loading. To disable this message until version 0.15 explicitly set `download_data`, "
-            "`download_qualities`, and `download_features_meta_data` to a bool while calling "
-            "`get_dataset`.",
-            FutureWarning,
-            stacklevel=2,
-        )
-
-    download_data = True if download_data is None else download_data
-    download_qualities = True if download_qualities is None else download_qualities
-    download_features_meta_data = (
-        True if download_features_meta_data is None else download_features_meta_data
-    )
-
     if download_all_files:
         warnings.warn(
             "``download_all_files`` is experimental and is likely to break with new releases.",

openml/testing.py

@@ -56,7 +56,7 @@ class TestBase(unittest.TestCase):
     logger = logging.getLogger("unit_tests_published_entities")
     logger.setLevel(logging.DEBUG)
 
-    def setUp(self, n_levels: int = 1) -> None:
+    def setUp(self, n_levels: int = 1, tmpdir_suffix: str = "") -> None:
         """Setup variables and temporary directories.
 
         In particular, this methods:
@@ -92,7 +92,7 @@ def setUp(self, n_levels: int = 1) -> None:
         self.static_cache_dir = static_cache_dir
         self.cwd = Path.cwd()
         workdir = Path(__file__).parent.absolute()
-        tmp_dir_name = self.id()
+        tmp_dir_name = self.id() + tmpdir_suffix
         self.workdir = workdir / tmp_dir_name
         shutil.rmtree(self.workdir, ignore_errors=True)