Merge branch 'main' into studies-migration

Author: rohansen856

.github/workflows/test.yml

@@ -22,7 +22,7 @@ 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${{ matrix.scikit-learn }}${{ matrix.pandas-version != '' && format(',pd:{0}', matrix.pandas-version) || '' }},sk-only:${{ matrix.sklearn-only }})
     runs-on: ${{ matrix.os }}
 
     strategy:
@@ -64,6 +64,14 @@ jobs:
             sklearn-only: "false"
             code-cov: true
 
+          # Pandas 2 run
+          - os: ubuntu-latest
+            python-version: "3.12"
+            scikit-learn: "1.5.*"
+            sklearn-only: "false"
+            pandas-version: "2.*"
+            code-cov: false
+
     steps:
     - uses: actions/checkout@v6
       with:
@@ -74,10 +82,16 @@ jobs:
       with:
         python-version: ${{ matrix.python-version }}
 
-    - name: Install test dependencies and scikit-learn
+    - name: Install test dependencies, scikit-learn, and optional pandas
+      shell: bash
       run: |
         python -m pip install --upgrade pip
         pip install -e .[test] scikit-learn==${{ matrix.scikit-learn }}
+        
+        if [ "${{ matrix.pandas-version }}" != "" ]; then
+          echo "Installing specific pandas version: ${{ matrix.pandas-version }}"
+          pip install "pandas==${{ matrix.pandas-version }}"
+        fi
 
     - name: Store repository status
       id: status-before

openml/cli.py

@@ -10,6 +10,7 @@
 from urllib.parse import urlparse
 
 from openml import config
+from openml.__version__ import __version__
 
 
 def is_hex(string_: str) -> bool:
@@ -331,6 +332,13 @@ def main() -> None:
     subroutines = {"configure": configure}
 
     parser = argparse.ArgumentParser()
+    # Add a global --version flag to display installed version and exit
+    parser.add_argument(
+        "--version",
+        action="version",
+        version=f"%(prog)s {__version__}",
+        help="Show the OpenML version and exit",
+    )
     subparsers = parser.add_subparsers(dest="subroutine")
 
     parser_configure = subparsers.add_parser(

openml/datasets/dataset.py

@@ -488,7 +488,7 @@ def _parse_data_from_arff(  # noqa: C901, PLR0912, PLR0915
                 try:
                     # checks if the strings which should be the class labels
                     # can be encoded into integers
-                    pd.factorize(type_)[0]
+                    pd.factorize(np.array(type_))[0]
                 except ValueError as e:
                     raise ValueError(
                         "Categorical data needs to be numeric when using sparse ARFF."

tests/test_datasets/test_dataset.py

@@ -102,21 +102,24 @@ def test_get_data_pandas(self):
         assert isinstance(data, pd.DataFrame)
         assert data.shape[1] == len(self.titanic.features)
         assert data.shape[0] == 1309
+        # Dynamically detect what this version of Pandas calls string columns.
+        str_dtype = data["name"].dtype.name
+
         col_dtype = {
             "pclass": "uint8",
             "survived": "category",
-            "name": "object",
+            "name": str_dtype,
             "sex": "category",
             "age": "float64",
             "sibsp": "uint8",
             "parch": "uint8",
-            "ticket": "object",
+            "ticket": str_dtype,
             "fare": "float64",
-            "cabin": "object",
+            "cabin": str_dtype,
             "embarked": "category",
-            "boat": "object",
+            "boat": str_dtype,
             "body": "float64",
-            "home.dest": "object",
+            "home.dest": str_dtype,
         }
         for col_name in data.columns:
             assert data[col_name].dtype.name == col_dtype[col_name]
@@ -357,7 +360,7 @@ def setUp(self):
     def test_get_sparse_dataset_dataframe_with_target(self):
         X, y, _, attribute_names = self.sparse_dataset.get_data(target="class")
         assert isinstance(X, pd.DataFrame)
-        assert isinstance(X.dtypes[0], pd.SparseDtype)
+        assert isinstance(X.dtypes.iloc[0], pd.SparseDtype)
         assert X.shape == (600, 20000)
 
         assert isinstance(y, pd.Series)

tests/test_flows/test_flow_functions.py

@@ -41,8 +41,9 @@ def _check_flow(self, flow):
         assert isinstance(flow["full_name"], str)
         assert isinstance(flow["version"], str)
         # There are some runs on openml.org that can have an empty external version
+        ext_version = flow["external_version"]
         ext_version_str_or_none = (
-            isinstance(flow["external_version"], str) or flow["external_version"] is None
+            isinstance(ext_version, str) or ext_version is None or pd.isna(ext_version)
         )
         assert ext_version_str_or_none
 
@@ -338,7 +339,6 @@ def test_get_flow_reinstantiate_model_no_extension(self):
         reason="Requires scikit-learn!=0.19.1, because target flow is from that version.",
     )
     @pytest.mark.production()
-    @pytest.mark.xfail(reason="failures_issue_1544", strict=False)
     def test_get_flow_with_reinstantiate_strict_with_wrong_version_raises_exception(self):
         self.use_production_server()
         flow = 8175

tests/test_openml/test_cli.py

@@ -0,0 +1,44 @@
+# License: BSD 3-Clause
+from __future__ import annotations
+
+import shutil
+import subprocess
+import sys
+
+import openml
+import pytest
+
+
+def test_cli_version_prints_package_version():
+    # Invoke the CLI via module to avoid relying on console script installation
+    result = subprocess.run(
+        [sys.executable, "-m", "openml.cli", "--version"],
+        stdout=subprocess.PIPE,
+        stderr=subprocess.PIPE,
+        text=True,
+        check=False,
+    )
+
+    # Ensure successful exit and version present in stdout only
+    assert result.returncode == 0
+    assert result.stderr == ""
+    assert openml.__version__ in result.stdout
+
+
+def test_console_script_version_prints_package_version():
+    # Try to locate the console script; skip if not installed in PATH
+    console = shutil.which("openml")
+    if console is None:
+        pytest.skip("'openml' console script not found in PATH")
+
+    result = subprocess.run(
+        [console, "--version"],
+        stdout=subprocess.PIPE,
+        stderr=subprocess.PIPE,
+        text=True,
+        check=False,
+    )
+
+    assert result.returncode == 0
+    assert result.stderr == ""
+    assert openml.__version__ in result.stdout