Merge branch 'main' into pr/1606

Author: fkiraly

.github/workflows/dist.yaml

@@ -27,7 +27,7 @@ jobs:
     - name: Setup Python
       uses: actions/setup-python@v5
       with:
-        python-version: 3.8
+        python-version: "3.10"
     - name: Build dist
       run: |
         pip install build

.github/workflows/docs.yaml

@@ -28,7 +28,7 @@ jobs:
       - name: Setup Python
         uses: actions/setup-python@v5
         with:
-          python-version: 3.8
+          python-version: "3.10"
       - name: Install dependencies
         run: |
           pip install -e .[docs,examples]

.github/workflows/test.yml

@@ -1,3 +1,4 @@
+---
 name: Tests
 
 on:
@@ -21,13 +22,13 @@ concurrency:
 
 jobs:
   test:
-    name: (${{ matrix.os }}, Py${{ matrix.python-version }}, sk${{ matrix.scikit-learn }}, sk-only:${{ matrix.sklearn-only }})
+    name: (${{ matrix.os }},Py${{ matrix.python-version }},sk${{ matrix.scikit-learn }},sk-only:${{ matrix.sklearn-only }})
     runs-on: ${{ matrix.os }}
 
     strategy:
       fail-fast: false
       matrix:
-        python-version: ["3.10", "3.11", "3.12", "3.13"]
+        python-version: ["3.10", "3.11", "3.12", "3.13", "3.14"]
         scikit-learn: ["1.3.*", "1.4.*", "1.5.*", "1.6.*", "1.7.*"]
         os: [ubuntu-latest]
         sklearn-only: ["true"]
@@ -38,8 +39,18 @@ jobs:
             scikit-learn: "1.3.*"
           - python-version: "3.13"
             scikit-learn: "1.4.*"
+          - python-version: "3.14"
+            scikit-learn: "1.3.*"
+          - python-version: "3.14"
+            scikit-learn: "1.4.*"
 
         include:
+          # Full test run on ubuntu, 3.14
+          - os: ubuntu-latest
+            python-version: "3.14"
+            scikit-learn: "1.7.*"
+            sklearn-only: "false"
+
           # Full test run on Windows
           - os: windows-latest
             python-version: "3.12"
@@ -87,9 +98,9 @@ jobs:
         fi
 
         if [ "${{ matrix.sklearn-only }}" = "true" ]; then
-          marks="sklearn and not production"
+          marks="sklearn and not production and not uses_test_server"
         else
-          marks="not production"
+          marks="not production and not uses_test_server"
         fi
 
         pytest -n 4 --durations=20 --dist load -sv $codecov -o log_cli=true -m "$marks"
@@ -102,17 +113,17 @@ jobs:
         fi
 
         if [ "${{ matrix.sklearn-only }}" = "true" ]; then
-          marks="sklearn and production"
+          marks="sklearn and production and not uses_test_server"
         else
-          marks="production"
+          marks="production and not uses_test_server"
         fi
 
         pytest -n 4 --durations=20 --dist load -sv $codecov -o log_cli=true -m "$marks"
 
     - name: Run tests on Windows
       if: matrix.os == 'windows-latest'
       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
+        pytest -n 4 --durations=20 --dist load -sv --reruns 5 --reruns-delay 1 -m "not uses_test_server"
 
     - name: Check for files left behind by test
       if: matrix.os != 'windows-latest' && always()

.gitignore

@@ -98,7 +98,17 @@ dmypy.sock
 
 # Tests
 .pytest_cache
+
+# Virtual environments
+oenv/
+venv/
+.env/
 .venv
+.venv/
+
+# Python cache
+__pycache__/
+*.pyc
 
 # Ruff
-.ruff-cache/
+.ruff-cache/

README.md

@@ -15,7 +15,7 @@
 ## The Python API for a World of Data and More :dizzy:
 
 [![Latest Release](https://img.shields.io/github/v/release/openml/openml-python)](https://github.com/openml/openml-python/releases)
-[![Python Versions](https://img.shields.io/badge/python-3.8%20%7C%203.9%20%7C%203.10%20%7C%203.11%20%7C%203.12%20%7C%203.13-blue)](https://pypi.org/project/openml/)
+[![Python Versions](https://img.shields.io/badge/python-3.10%20%7C%203.11%20%7C%203.12%20%7C%203.13%20%7C%203.14-blue)](https://pypi.org/project/openml/)
 [![Downloads](https://static.pepy.tech/badge/openml)](https://pepy.tech/project/openml)
 [![License](https://img.shields.io/badge/License-BSD%203--Clause-blue.svg)](https://opensource.org/licenses/BSD-3-Clause)
 <!-- Add green badges for CI and precommit -->
@@ -60,7 +60,7 @@ for task_id in suite.tasks:
 
 ## :magic_wand: Installation
 
-OpenML-Python is supported on Python 3.8 - 3.13 and is available on Linux, MacOS, and Windows.
+OpenML-Python is supported on Python 3.10 - 3.14 and is available on Linux, MacOS, and Windows.
 
 You can install OpenML-Python with:
 

openml/evaluations/evaluation.py

@@ -1,15 +1,16 @@
 # License: BSD 3-Clause
 from __future__ import annotations
 
+from dataclasses import asdict, dataclass
+
 import openml.config
 import openml.datasets
 import openml.flows
 import openml.runs
 import openml.tasks
 
 
-# TODO(eddiebergman): A lot of this class is automatically
-# handled by a dataclass
+@dataclass
 class OpenMLEvaluation:
     """
     Contains all meta-information about a run / evaluation combination,
@@ -48,55 +49,23 @@ class OpenMLEvaluation:
         (e.g., in case of precision, auroc, recall)
     """
 
-    def __init__(  # noqa: PLR0913
-        self,
-        run_id: int,
-        task_id: int,
-        setup_id: int,
-        flow_id: int,
-        flow_name: str,
-        data_id: int,
-        data_name: str,
-        function: str,
-        upload_time: str,
-        uploader: int,
-        uploader_name: str,
-        value: float | None,
-        values: list[float] | None,
-        array_data: str | None = None,
-    ):
-        self.run_id = run_id
-        self.task_id = task_id
-        self.setup_id = setup_id
-        self.flow_id = flow_id
-        self.flow_name = flow_name
-        self.data_id = data_id
-        self.data_name = data_name
-        self.function = function
-        self.upload_time = upload_time
-        self.uploader = uploader
-        self.uploader_name = uploader_name
-        self.value = value
-        self.values = values
-        self.array_data = array_data
+    run_id: int
+    task_id: int
+    setup_id: int
+    flow_id: int
+    flow_name: str
+    data_id: int
+    data_name: str
+    function: str
+    upload_time: str
+    uploader: int
+    uploader_name: str
+    value: float | None
+    values: list[float] | None
+    array_data: str | None = None
 
     def _to_dict(self) -> dict:
-        return {
-            "run_id": self.run_id,
-            "task_id": self.task_id,
-            "setup_id": self.setup_id,
-            "flow_id": self.flow_id,
-            "flow_name": self.flow_name,
-            "data_id": self.data_id,
-            "data_name": self.data_name,
-            "function": self.function,
-            "upload_time": self.upload_time,
-            "uploader": self.uploader,
-            "uploader_name": self.uploader_name,
-            "value": self.value,
-            "values": self.values,
-            "array_data": self.array_data,
-        }
+        return asdict(self)
 
     def __repr__(self) -> str:
         header = "OpenML Evaluation"
@@ -119,11 +88,12 @@ def __repr__(self) -> str:
         }
 
         order = [
-            "Uploader Date",
+            "Upload Date",
             "Run ID",
             "OpenML Run URL",
             "Task ID",
-            "OpenML Task URL" "Flow ID",
+            "OpenML Task URL",
+            "Flow ID",
             "OpenML Flow URL",
             "Setup ID",
             "Data ID",

pyproject.toml

@@ -21,7 +21,7 @@ dependencies = [
   "pyarrow",
   "tqdm",  # For MinIO download progress bars
 ]
-requires-python = ">=3.8"
+requires-python = ">=3.10,<3.15"    
 maintainers = [
   { name = "Pieter Gijsbers", email="p.gijsbers@tue.nl"},
   { name = "Lennart Purucker"},

tests/test_datasets/test_dataset.py

@@ -278,6 +278,7 @@ def test_equality_comparison(self):
         self.assertNotEqual(self.titanic, "Wrong_object")
 
 
+@pytest.mark.uses_test_server()
 def test_tagging():
     dataset = openml.datasets.get_dataset(125, download_data=False)
 
@@ -294,7 +295,7 @@ def test_tagging():
     datasets = openml.datasets.list_datasets(tag=tag)
     assert datasets.empty
 
-@pytest.mark.xfail(reason="failures_issue_1544")
+@pytest.mark.uses_test_server()
 def test_get_feature_with_ontology_data_id_11():
     # test on car dataset, which has built-in ontology references
     dataset = openml.datasets.get_dataset(11)
@@ -303,13 +304,15 @@ def test_get_feature_with_ontology_data_id_11():
     assert len(dataset.features[2].ontologies) >= 1
     assert len(dataset.features[3].ontologies) >= 1   
 
+@pytest.mark.uses_test_server()
 def test_add_remove_ontology_to_dataset():
     did = 1
     feature_index = 1
     ontology = "https://www.openml.org/unittest/" + str(time())
     openml.datasets.functions.data_feature_add_ontology(did, feature_index, ontology)
     openml.datasets.functions.data_feature_remove_ontology(did, feature_index, ontology)    
 
+@pytest.mark.uses_test_server()
 def test_add_same_ontology_multiple_features():
     did = 1
     ontology = "https://www.openml.org/unittest/" + str(time())
@@ -318,6 +321,7 @@ def test_add_same_ontology_multiple_features():
         openml.datasets.functions.data_feature_add_ontology(did, i, ontology)    
 
 
+@pytest.mark.uses_test_server()
 def test_add_illegal_long_ontology():
     did = 1
     ontology = "http://www.google.com/" + ("a" * 257)
@@ -329,6 +333,7 @@ def test_add_illegal_long_ontology():
 
 
 
+@pytest.mark.uses_test_server()
 def test_add_illegal_url_ontology():
     did = 1
     ontology = "not_a_url" + str(time())
@@ -400,6 +405,7 @@ def test_get_sparse_categorical_data_id_395(self):
         assert len(feature.nominal_values) == 25
 
 
+@pytest.mark.uses_test_server()
 def test__read_features(mocker, workdir, static_cache_dir):
     """Test we read the features from the xml if no cache pickle is available.
     This test also does some simple checks to verify that the features are read correctly
@@ -431,6 +437,7 @@ def test__read_features(mocker, workdir, static_cache_dir):
     assert pickle_mock.dump.call_count == 1
 
 
+@pytest.mark.uses_test_server()
 def test__read_qualities(static_cache_dir, workdir, mocker):
     """Test we read the qualities from the xml if no cache pickle is available.
     This test also does some minor checks to ensure that the qualities are read correctly.