From 20e37a2d30f182695a10fea50a887cd67e24cd0c Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Franz=20Kir=C3=A1ly?= <fkiraly@gcos.ai>
Date: Wed, 31 Dec 2025 02:06:06 +0100
Subject: [PATCH 1/2] experimental model framework

---
 openml/__init__.py                           |   2 +
 openml/_get.py                               |   9 ++
 openml/base/__init__.py                      |   6 +
 openml/{base.py => base/_base.py}            |   3 +-
 openml/base/_base_pkg.py                     | 120 +++++++++++++++++++
 openml/models/__init__.py                    |   5 +
 openml/models/_get.py                        |  63 ++++++++++
 openml/models/apis/__init__.py               |   5 +
 openml/models/apis/_classifier.py            |  24 ++++
 openml/models/base/__init__.py               |   5 +
 openml/models/base/_base.py                  |  41 +++++++
 openml/models/classification/__init__.py     |   1 +
 openml/models/classification/auto_sklearn.py |  14 +++
 openml/models/classification/xgboost.py      |  14 +++
 pyproject.toml                               |   1 +
 15 files changed, 311 insertions(+), 2 deletions(-)
 create mode 100644 openml/_get.py
 create mode 100644 openml/base/__init__.py
 rename openml/{base.py => base/_base.py} (98%)
 create mode 100644 openml/base/_base_pkg.py
 create mode 100644 openml/models/__init__.py
 create mode 100644 openml/models/_get.py
 create mode 100644 openml/models/apis/__init__.py
 create mode 100644 openml/models/apis/_classifier.py
 create mode 100644 openml/models/base/__init__.py
 create mode 100644 openml/models/base/_base.py
 create mode 100644 openml/models/classification/__init__.py
 create mode 100644 openml/models/classification/auto_sklearn.py
 create mode 100644 openml/models/classification/xgboost.py

diff --git a/openml/__init__.py b/openml/__init__.py
index c49505eb9..f93cbb5d3 100644
--- a/openml/__init__.py
+++ b/openml/__init__.py
@@ -48,6 +48,7 @@
     OpenMLSupervisedTask,
     OpenMLTask,
 )
+from openml._get import get
 
 
 def populate_cache(
@@ -120,4 +121,5 @@ def populate_cache(
     "utils",
     "_api_calls",
     "__version__",
+    "get",
 ]
diff --git a/openml/_get.py b/openml/_get.py
new file mode 100644
index 000000000..b576668db
--- /dev/null
+++ b/openml/_get.py
@@ -0,0 +1,9 @@
+"""Global get dispatch utility."""
+
+# currently just a forward to models
+# to discuss and possibly
+# todo: add global get utility here
+# in general, e.g., datasets will not have same name as models etc
+from openml.models import get
+
+__all__ = ["get"]
diff --git a/openml/base/__init__.py b/openml/base/__init__.py
new file mode 100644
index 000000000..76a88c42b
--- /dev/null
+++ b/openml/base/__init__.py
@@ -0,0 +1,6 @@
+"""Module of base classes."""
+
+from openml.base._base import OpenMLBase
+from openml.base._base_pkg import _BasePkg
+
+__all__ = ["_BasePkg", "OpenMLBase"]
diff --git a/openml/base.py b/openml/base/_base.py
similarity index 98%
rename from openml/base.py
rename to openml/base/_base.py
index fbfb9dfc8..de2b387bf 100644
--- a/openml/base.py
+++ b/openml/base/_base.py
@@ -10,8 +10,7 @@
 
 import openml._api_calls
 import openml.config
-
-from .utils import _get_rest_api_type_alias, _tag_openml_base
+from openml.utils import _get_rest_api_type_alias, _tag_openml_base
 
 
 class OpenMLBase(ABC):
diff --git a/openml/base/_base_pkg.py b/openml/base/_base_pkg.py
new file mode 100644
index 000000000..9f5d6005e
--- /dev/null
+++ b/openml/base/_base_pkg.py
@@ -0,0 +1,120 @@
+"""Base Packager class."""
+
+import inspect
+from pathlib import Path
+import sys
+import textwrap
+
+from skbase.base import BaseObject
+from skbase.utils.dependencies import _check_estimator_deps
+
+
+class _BasePkg(BaseObject):
+
+    _tags = {
+        "python_dependencies": None,
+        "python_version": None,
+        # package register and manifest
+        "pkg_id": None,  # object id contained, "__multiple" if multiple
+        "pkg_obj": "reference",  # or "code"
+        "pkg_obj_type": None,  # openml API type
+        "pkg_compression": "zlib",  # compression
+    }
+
+    def __init__(self):
+        super().__init__()
+
+    def materialize(self):
+        try:
+            _check_estimator_deps(obj=self)
+        except ModuleNotFoundError as e:
+            # prettier message, so the reference is to the pkg_id
+            # currently, we cannot simply pass the object name to skbase
+            # in the error message, so this is a hack
+            # todo: fix this in scikit-base
+            msg = str(e)
+            if len(msg) > 11:
+                msg = msg[11:]
+            raise ModuleNotFoundError(msg) from e
+
+        return self._materialize()
+
+    def _materialize(self):
+        raise RuntimeError("abstract method")
+
+    def serialize(self):
+        cls_str = class_to_source(type(self))
+        compress_method = self.get_tag("pkg_compression")
+        if compress_method in [None, "None"]:
+            return cls_str
+
+        cls_str = cls_str.encode("utf-8")
+        exec(f"import {compress_method}")
+        compressed_str = eval(f"{compress_method}.compress(cls_str)")
+
+        return compressed_str
+
+
+def _has_source(obj) -> bool:
+    """
+    Return True if inspect.getsource(obj) should succeed.
+    """
+    module_name = getattr(obj, "__module__", None)
+    if not module_name or module_name not in sys.modules:
+        return False
+
+    module = sys.modules[module_name]
+    file = getattr(module, "__file__", None)
+    if not file:
+        return False
+
+    return Path(file).suffix == ".py"
+
+
+def class_to_source(cls) -> str:
+    """Return full source definition of python class as string.
+
+    Parameters
+    ----------
+    cls : class to serialize
+
+    Returns
+    -------
+    str : complete definition of cls, as str.
+        Imports are not contained or serialized.
+    """""
+
+    # Fast path: class has retrievable source
+    if _has_source(cls):
+        source = inspect.getsource(cls)
+        return textwrap.dedent(source)
+
+    # Fallback for dynamically created classes
+    lines = []
+
+    bases = [base.__name__ for base in cls.__bases__ if base is not object]
+    base_str = f"({', '.join(bases)})" if bases else ""
+    lines.append(f"class {cls.__name__}{base_str}:")
+
+    body_added = False
+
+    for name, value in cls.__dict__.items():
+        if name.startswith("__") and name.endswith("__"):
+            continue
+
+        if inspect.isfunction(value):
+            if _has_source(value):
+                method_src = inspect.getsource(value)
+                method_src = textwrap.indent(textwrap.dedent(method_src), "    ")
+                lines.append(method_src)
+            else:
+                lines.append(f"    def {name}(self): ...")
+            body_added = True
+        else:
+            lines.append(f"    {name} = {repr(value)}")
+            body_added = True
+
+    if not body_added:
+        lines.append("    pass")
+
+    return "\n".join(lines)
diff --git a/openml/models/__init__.py b/openml/models/__init__.py
new file mode 100644
index 000000000..ae833fc63
--- /dev/null
+++ b/openml/models/__init__.py
@@ -0,0 +1,5 @@
+"""Module with packaging adapters."""
+
+from openml.models._get import get
+
+__all__ = ["get"]
diff --git a/openml/models/_get.py b/openml/models/_get.py
new file mode 100644
index 000000000..b270ec0b6
--- /dev/null
+++ b/openml/models/_get.py
@@ -0,0 +1,63 @@
+
+"""Model retrieval utility."""
+
+from functools import lru_cache
+
+
+def get(id: str):
+    """Retrieve model object with unique identifier.
+
+    Parameter
+    ---------
+    id : str
+        unique identifier of object to retrieve
+
+    Returns
+    -------
+    class
+        retrieved object
+
+    Raises
+    ------
+    ModuleNotFoundError
+        if dependencies of object to retrieve are not satisfied
+    """
+
+    id_lookup = _id_lookup()
+    obj = id_lookup.get(id)
+    if obj is None:
+        raise ValueError(
+            f"Error in openml.get, object with package id {id} "
+            "does not exist."
+        )
+    return obj().materialize()
+
+
+# todo: need to generalize this later to more types
+# currently intentionally retrieves only classifiers
+# todo: replace this, optionally, by database backend
+def _id_lookup(obj_type=None):
+    return _id_lookup_cached(obj_type=obj_type).copy()
+
+
+@lru_cache
+def _id_lookup_cached(obj_type=None):
+    all_objs = _all_objects(obj_type=obj_type)
+
+    # todo: generalize that pkg can contain more than one object
+    lookup_dict = {obj.get_class_tag("pkg_id"): obj for obj in all_objs}
+
+    return lookup_dict
+
+
+@lru_cache
+def _all_objects(obj_type=None):
+    from skbase.lookup import all_objects
+
+    from openml.models.apis._classifier import _ModelPkgClassifier
+
+    clses = all_objects(
+        object_types=_ModelPkgClassifier, package_name="openml", return_names=False
+    )
+
+    return clses
diff --git a/openml/models/apis/__init__.py b/openml/models/apis/__init__.py
new file mode 100644
index 000000000..f560dcf6f
--- /dev/null
+++ b/openml/models/apis/__init__.py
@@ -0,0 +1,5 @@
+"""Module with packaging adapters."""
+
+from openml.models.apis._classifier import _ModelPkgClassifier
+
+__all__ = ["_ModelPkgClassifier"]
diff --git a/openml/models/apis/_classifier.py b/openml/models/apis/_classifier.py
new file mode 100644
index 000000000..a6d75b967
--- /dev/null
+++ b/openml/models/apis/_classifier.py
@@ -0,0 +1,24 @@
+"""Base package for sklearn classifiers."""
+
+from openml.models.base import _OpenmlModelPkg
+
+
+class _ModelPkgClassifier(_OpenmlModelPkg):
+
+    _tags = {
+        # tags specific to API type
+        "pkg_obj_type": "classifier",
+    }
+
+    def get_obj_tags(self):
+        """Return tags of the object as a dictionary."""
+        return {}  # this needs to be implemented
+
+    def get_obj_param_names(self):
+        """Return parameter names of the object as a list.
+
+        Returns
+        -------
+        list: names of object parameters
+        """
+        return list(self.materialize()().get_params().keys())
diff --git a/openml/models/base/__init__.py b/openml/models/base/__init__.py
new file mode 100644
index 000000000..a60e1e404
--- /dev/null
+++ b/openml/models/base/__init__.py
@@ -0,0 +1,5 @@
+"""Module with packaging adapters."""
+
+from openml.models.base._base import _OpenmlModelPkg
+
+__all__ = ["_OpenmlModelPkg"]
diff --git a/openml/models/base/_base.py b/openml/models/base/_base.py
new file mode 100644
index 000000000..4384e754c
--- /dev/null
+++ b/openml/models/base/_base.py
@@ -0,0 +1,41 @@
+"""Base model package class."""
+
+from openml.base import _BasePkg
+
+
+class _OpenmlModelPkg(_BasePkg):
+
+    _obj = None
+
+    def _materialize(self):
+        pkg_obj = self.get_tag("pkg_obj")
+
+        _obj = self._obj
+
+        if _obj is None:
+            raise ValueError(
+                "Error in materialize."
+                "Either _materialize must be implemented, or"
+                "the _obj attribute must be not None."
+            )
+
+        if pkg_obj == "reference":
+            from skbase.utils.dependencies import _safe_import
+
+            obj = _safe_import(self._obj)
+            return obj
+
+        elif pkg_obj == "code":
+            exec(self._obj)
+
+            return obj
+
+        # elif pkg_obj == "craft":
+        #    identify and call appropriate craft method
+
+        else:
+            raise ValueError(
+                'Error in package tag "pkg_obj", '
+                'must be one of "reference", "code", "craft", '
+                f'but found value {pkg_obj}, of type {type(pkg_obj)}'
+            )
diff --git a/openml/models/classification/__init__.py b/openml/models/classification/__init__.py
new file mode 100644
index 000000000..e547a50cf
--- /dev/null
+++ b/openml/models/classification/__init__.py
@@ -0,0 +1 @@
+"""Sklearn classification models."""
diff --git a/openml/models/classification/auto_sklearn.py b/openml/models/classification/auto_sklearn.py
new file mode 100644
index 000000000..0be641394
--- /dev/null
+++ b/openml/models/classification/auto_sklearn.py
@@ -0,0 +1,14 @@
+"""Auto-sklearn classifier."""
+
+
+from openml.models.apis import _ModelPkgClassifier
+
+
+class OpenmlPkg__AutoSklearnClassifier(_ModelPkgClassifier):
+
+    _tags = {
+        "pkg_id": "AutoSklearnClassifier",
+        "python_dependencies": "auto-sklearn",
+    }
+
+    _obj = "autosklearn.classification.AutoSklearnClassifier"
diff --git a/openml/models/classification/xgboost.py b/openml/models/classification/xgboost.py
new file mode 100644
index 000000000..44f3173fe
--- /dev/null
+++ b/openml/models/classification/xgboost.py
@@ -0,0 +1,14 @@
+"""Xgboost classifier."""
+
+
+from openml.models.apis import _ModelPkgClassifier
+
+
+class OpenmlPkg__XGBClassifier(_ModelPkgClassifier):
+
+    _tags = {
+        "pkg_id": "XGBClassifier",
+        "python_dependencies": "xgboost",
+    }
+
+    _obj = "xgboost.XGBClassifier"
diff --git a/pyproject.toml b/pyproject.toml
index 2bf762b09..83b62554d 100644
--- a/pyproject.toml
+++ b/pyproject.toml
@@ -20,6 +20,7 @@ dependencies = [
   "minio",
   "pyarrow",
   "tqdm",  # For MinIO download progress bars
+  "scikit-base",
 ]
 requires-python = ">=3.8"
 maintainers = [

From d79fbe52dceca77b70b1c46a7b32aceecef2aa71 Mon Sep 17 00:00:00 2001
From: "pre-commit-ci[bot]"
 <66853113+pre-commit-ci[bot]@users.noreply.github.com>
Date: Wed, 31 Dec 2025 01:22:05 +0000
Subject: [PATCH 2/2] [pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci
---
 openml/__init__.py                           |  3 ++-
 openml/_get.py                               |  2 ++
 openml/base/_base_pkg.py                     | 17 +++++++----------
 openml/models/_get.py                        | 19 +++++--------------
 openml/models/apis/_classifier.py            |  3 ++-
 openml/models/base/_base.py                  | 19 +++++++++----------
 openml/models/classification/auto_sklearn.py |  2 +-
 openml/models/classification/xgboost.py      |  2 +-
 8 files changed, 29 insertions(+), 38 deletions(-)

diff --git a/openml/__init__.py b/openml/__init__.py
index f93cbb5d3..7eb077057 100644
--- a/openml/__init__.py
+++ b/openml/__init__.py
@@ -18,6 +18,8 @@
 # License: BSD 3-Clause
 from __future__ import annotations
 
+from openml._get import get
+
 from . import (
     _api_calls,
     config,
@@ -48,7 +50,6 @@
     OpenMLSupervisedTask,
     OpenMLTask,
 )
-from openml._get import get
 
 
 def populate_cache(
diff --git a/openml/_get.py b/openml/_get.py
index b576668db..0c5e9739e 100644
--- a/openml/_get.py
+++ b/openml/_get.py
@@ -4,6 +4,8 @@
 # to discuss and possibly
 # todo: add global get utility here
 # in general, e.g., datasets will not have same name as models etc
+from __future__ import annotations
+
 from openml.models import get
 
 __all__ = ["get"]
diff --git a/openml/base/_base_pkg.py b/openml/base/_base_pkg.py
index 9f5d6005e..690b93a86 100644
--- a/openml/base/_base_pkg.py
+++ b/openml/base/_base_pkg.py
@@ -1,16 +1,17 @@
 """Base Packager class."""
 
+from __future__ import annotations
+
 import inspect
-from pathlib import Path
 import sys
 import textwrap
+from pathlib import Path
 
 from skbase.base import BaseObject
 from skbase.utils.dependencies import _check_estimator_deps
 
 
 class _BasePkg(BaseObject):
-
     _tags = {
         "python_dependencies": None,
         "python_version": None,
@@ -50,15 +51,11 @@ def serialize(self):
 
         cls_str = cls_str.encode("utf-8")
         exec(f"import {compress_method}")
-        compressed_str = eval(f"{compress_method}.compress(cls_str)")
-
-        return compressed_str
+        return eval(f"{compress_method}.compress(cls_str)")
 
 
 def _has_source(obj) -> bool:
-    """
-    Return True if inspect.getsource(obj) should succeed.
-    """
+    """Return True if inspect.getsource(obj) should succeed."""
     module_name = getattr(obj, "__module__", None)
     if not module_name or module_name not in sys.modules:
         return False
@@ -82,7 +79,7 @@ def class_to_source(cls) -> str:
     -------
     str : complete definition of cls, as str.
         Imports are not contained or serialized.
-    """""
+    """ ""
 
     # Fast path: class has retrievable source
     if _has_source(cls):
@@ -111,7 +108,7 @@ def class_to_source(cls) -> str:
                 lines.append(f"    def {name}(self): ...")
             body_added = True
         else:
-            lines.append(f"    {name} = {repr(value)}")
+            lines.append(f"    {name} = {value!r}")
             body_added = True
 
     if not body_added:
diff --git a/openml/models/_get.py b/openml/models/_get.py
index b270ec0b6..75b807ca7 100644
--- a/openml/models/_get.py
+++ b/openml/models/_get.py
@@ -1,6 +1,7 @@
-
 """Model retrieval utility."""
 
+from __future__ import annotations
+
 from functools import lru_cache
 
 
@@ -22,14 +23,10 @@ def get(id: str):
     ModuleNotFoundError
         if dependencies of object to retrieve are not satisfied
     """
-
     id_lookup = _id_lookup()
     obj = id_lookup.get(id)
     if obj is None:
-        raise ValueError(
-            f"Error in openml.get, object with package id {id} "
-            "does not exist."
-        )
+        raise ValueError(f"Error in openml.get, object with package id {id} " "does not exist.")
     return obj().materialize()
 
 
@@ -45,9 +42,7 @@ def _id_lookup_cached(obj_type=None):
     all_objs = _all_objects(obj_type=obj_type)
 
     # todo: generalize that pkg can contain more than one object
-    lookup_dict = {obj.get_class_tag("pkg_id"): obj for obj in all_objs}
-
-    return lookup_dict
+    return {obj.get_class_tag("pkg_id"): obj for obj in all_objs}
 
 
 @lru_cache
@@ -56,8 +51,4 @@ def _all_objects(obj_type=None):
 
     from openml.models.apis._classifier import _ModelPkgClassifier
 
-    clses = all_objects(
-        object_types=_ModelPkgClassifier, package_name="openml", return_names=False
-    )
-
-    return clses
+    return all_objects(object_types=_ModelPkgClassifier, package_name="openml", return_names=False)
diff --git a/openml/models/apis/_classifier.py b/openml/models/apis/_classifier.py
index a6d75b967..c1198ee32 100644
--- a/openml/models/apis/_classifier.py
+++ b/openml/models/apis/_classifier.py
@@ -1,10 +1,11 @@
 """Base package for sklearn classifiers."""
 
+from __future__ import annotations
+
 from openml.models.base import _OpenmlModelPkg
 
 
 class _ModelPkgClassifier(_OpenmlModelPkg):
-
     _tags = {
         # tags specific to API type
         "pkg_obj_type": "classifier",
diff --git a/openml/models/base/_base.py b/openml/models/base/_base.py
index 4384e754c..6b3fa2a92 100644
--- a/openml/models/base/_base.py
+++ b/openml/models/base/_base.py
@@ -1,10 +1,11 @@
 """Base model package class."""
 
+from __future__ import annotations
+
 from openml.base import _BasePkg
 
 
 class _OpenmlModelPkg(_BasePkg):
-
     _obj = None
 
     def _materialize(self):
@@ -22,10 +23,9 @@ def _materialize(self):
         if pkg_obj == "reference":
             from skbase.utils.dependencies import _safe_import
 
-            obj = _safe_import(self._obj)
-            return obj
+            return _safe_import(self._obj)
 
-        elif pkg_obj == "code":
+        if pkg_obj == "code":
             exec(self._obj)
 
             return obj
@@ -33,9 +33,8 @@ def _materialize(self):
         # elif pkg_obj == "craft":
         #    identify and call appropriate craft method
 
-        else:
-            raise ValueError(
-                'Error in package tag "pkg_obj", '
-                'must be one of "reference", "code", "craft", '
-                f'but found value {pkg_obj}, of type {type(pkg_obj)}'
-            )
+        raise ValueError(
+            'Error in package tag "pkg_obj", '
+            'must be one of "reference", "code", "craft", '
+            f"but found value {pkg_obj}, of type {type(pkg_obj)}"
+        )
diff --git a/openml/models/classification/auto_sklearn.py b/openml/models/classification/auto_sklearn.py
index 0be641394..1d29044da 100644
--- a/openml/models/classification/auto_sklearn.py
+++ b/openml/models/classification/auto_sklearn.py
@@ -1,11 +1,11 @@
 """Auto-sklearn classifier."""
 
+from __future__ import annotations
 
 from openml.models.apis import _ModelPkgClassifier
 
 
 class OpenmlPkg__AutoSklearnClassifier(_ModelPkgClassifier):
-
     _tags = {
         "pkg_id": "AutoSklearnClassifier",
         "python_dependencies": "auto-sklearn",
diff --git a/openml/models/classification/xgboost.py b/openml/models/classification/xgboost.py
index 44f3173fe..5b91e647c 100644
--- a/openml/models/classification/xgboost.py
+++ b/openml/models/classification/xgboost.py
@@ -1,11 +1,11 @@
 """Xgboost classifier."""
 
+from __future__ import annotations
 
 from openml.models.apis import _ModelPkgClassifier
 
 
 class OpenmlPkg__XGBClassifier(_ModelPkgClassifier):
-
     _tags = {
         "pkg_id": "XGBClassifier",
         "python_dependencies": "xgboost",