Merge branch 'main' into enhance-docstrings

Author: fkiraly

.github/workflows/test.yml

@@ -106,6 +106,8 @@ jobs:
 
     - name: Run tests on Ubuntu Test
       if: matrix.os == 'ubuntu-latest'
+      env:
+        OPENML_TEST_SERVER_ADMIN_KEY: ${{ secrets.OPENML_TEST_SERVER_ADMIN_KEY }}
       run: |
         if [ "${{ matrix.code-cov }}" = "true" ]; then
           codecov="--cov=openml --long --cov-report=xml"
@@ -121,6 +123,8 @@ jobs:
 
     - name: Run tests on Ubuntu Production
       if: matrix.os == 'ubuntu-latest'
+      env:
+        OPENML_TEST_SERVER_ADMIN_KEY: ${{ secrets.OPENML_TEST_SERVER_ADMIN_KEY }}
       run: |
         if [ "${{ matrix.code-cov }}" = "true" ]; then
           codecov="--cov=openml --long --cov-report=xml"
@@ -136,6 +140,8 @@ jobs:
 
     - name: Run tests on Windows
       if: matrix.os == 'windows-latest'
+      env:
+        OPENML_TEST_SERVER_ADMIN_KEY: ${{ secrets.OPENML_TEST_SERVER_ADMIN_KEY }}
       run: |  # we need a separate step because of the bash-specific if-statement in the previous one.
         pytest -n 4 --durations=20 --dist load -sv --reruns 5 --reruns-delay 1 -m "not uses_test_server"
 

CONTRIBUTING.md

@@ -96,6 +96,17 @@ To test your new contribution, add [unit tests](https://github.com/openml/openml
 * Please ensure that the example is run on the test server by beginning with the call to `openml.config.start_using_configuration_for_example()`, which is done by default for tests derived from `TestBase`.
 * Add the `@pytest.mark.sklearn` marker to your unit tests if they have a dependency on scikit-learn.
 
+#### Running Tests That Require Admin Privileges
+
+Some tests require admin privileges on the test server and will be automatically skipped unless you provide an admin API key. For regular contributors, the tests will skip gracefully. For core contributors who need to run these tests locally, you can set up the key by exporting the variable as below before running the tests:
+
+```bash
+# For windows
+$env:OPENML_TEST_SERVER_ADMIN_KEY = "admin-key"
+# For linux/mac
+export OPENML_TEST_SERVER_ADMIN_KEY="admin-key"
+```
+
 ### Pull Request Checklist
 
 You can go to the `openml-python` GitHub repository to create the pull request by [comparing the branch](https://github.com/openml/openml-python/compare) from your fork with the `develop` branch of the `openml-python` repository. When creating a pull request, make sure to follow the comments and structured provided by the template on GitHub.

openml/config.py

@@ -25,6 +25,7 @@
 
 OPENML_CACHE_DIR_ENV_VAR = "OPENML_CACHE_DIR"
 OPENML_SKIP_PARQUET_ENV_VAR = "OPENML_SKIP_PARQUET"
+OPENML_TEST_SERVER_ADMIN_KEY_ENV_VAR = "OPENML_TEST_SERVER_ADMIN_KEY"
 _TEST_SERVER_NORMAL_USER_KEY = "normaluser"
 
 

openml/testing.py

@@ -48,7 +48,7 @@ class TestBase(unittest.TestCase):
     }
     flow_name_tracker: ClassVar[list[str]] = []
     test_server = "https://test.openml.org/api/v1/xml"
-    admin_key = "abc"
+    admin_key = os.environ.get(openml.config.OPENML_TEST_SERVER_ADMIN_KEY_ENV_VAR)
     user_key = openml.config._TEST_SERVER_NORMAL_USER_KEY
 
     # creating logger for tracking files uploaded to test server

openml/utils.py

@@ -2,12 +2,20 @@
 from __future__ import annotations
 
 import contextlib
+import re
 import shutil
 import warnings
-from collections.abc import Callable, Mapping, Sized
+from abc import ABC, abstractmethod
+from collections.abc import Callable, Iterable, Mapping, Sequence, Sized
 from functools import wraps
 from pathlib import Path
-from typing import TYPE_CHECKING, Any, Literal, TypeVar, overload
+from typing import (
+    TYPE_CHECKING,
+    Any,
+    Literal,
+    TypeVar,
+    overload,
+)
 from typing_extensions import ParamSpec
 
 import numpy as np
@@ -470,3 +478,57 @@ def update(self, length: int) -> None:
         self._progress_bar.update(length)
         if self._progress_bar.total <= self._progress_bar.n:
             self._progress_bar.close()
+
+
+class ReprMixin(ABC):
+    """A mixin class that provides a customizable string representation for OpenML objects.
+
+    This mixin standardizes the __repr__ output format across OpenML classes.
+    Classes inheriting from this mixin should implement the
+    _get_repr_body_fields method to specify which fields to display.
+    """
+
+    def __repr__(self) -> str:
+        body_fields = self._get_repr_body_fields()
+        return self._apply_repr_template(body_fields)
+
+    @abstractmethod
+    def _get_repr_body_fields(self) -> Sequence[tuple[str, str | int | list[str] | None]]:
+        """Collect all information to display in the __repr__ body.
+
+        Returns
+        -------
+        body_fields : List[Tuple[str, Union[str, int, List[str]]]]
+            A list of (name, value) pairs to display in the body of the __repr__.
+            E.g.: [('metric', 'accuracy'), ('dataset', 'iris')]
+            If value is a List of str, then each item of the list will appear in a separate row.
+        """
+        # Should be implemented in the base class.
+
+    def _apply_repr_template(
+        self,
+        body_fields: Iterable[tuple[str, str | int | list[str] | None]],
+    ) -> str:
+        """Generates the header and formats the body for string representation of the object.
+
+        Parameters
+        ----------
+        body_fields: List[Tuple[str, str]]
+           A list of (name, value) pairs to display in the body of the __repr__.
+        """
+        # We add spaces between capitals, e.g. ClassificationTask -> Classification Task
+        name_with_spaces = re.sub(
+            r"(\w)([A-Z])",
+            r"\1 \2",
+            self.__class__.__name__[len("OpenML") :],
+        )
+        header_text = f"OpenML {name_with_spaces}"
+        header = f"{header_text}\n{'=' * len(header_text)}\n"
+
+        _body_fields: list[tuple[str, str | int | list[str]]] = [
+            (k, "None" if v is None else v) for k, v in body_fields
+        ]
+        longest_field_name_length = max(len(name) for name, _ in _body_fields)
+        field_line_format = f"{{:.<{longest_field_name_length}}}: {{}}"
+        body = "\n".join(field_line_format.format(name, value) for name, value in _body_fields)
+        return header + body

tests/test_datasets/test_dataset_functions.py

@@ -599,6 +599,10 @@ def _assert_status_of_dataset(self, *, did: int, status: str):
         assert len(result) == 1
         assert result[did]["status"] == status
 
+    @pytest.mark.skipif(
+        not os.environ.get(openml.config.OPENML_TEST_SERVER_ADMIN_KEY_ENV_VAR),
+        reason="Test requires admin key. Set OPENML_TEST_SERVER_ADMIN_KEY environment variable.",
+    )
     @pytest.mark.flaky()
     @pytest.mark.uses_test_server()
     def test_data_status(self):