[ENH] Migration: set up core/base structure

openml/_api/__init__.py

@@ -0,0 +1,8 @@
+from openml._api.runtime.core import APIContext
+
+
+def set_api_version(version: str, *, strict: bool = False) -> None:
+    api_context.set_version(version=version, strict=strict)
+
+
+api_context = APIContext()

openml/_api/config.py

@@ -0,0 +1,5 @@
+from __future__ import annotations
+
+API_V1_SERVER = "https://www.openml.org/api/v1/xml"
+API_V2_SERVER = "http://127.0.0.1:8001"
+API_KEY = "..."

openml/_api/http/__init__.py

@@ -0,0 +1,3 @@
+from openml._api.http.client import HTTPClient
+
+__all__ = ["HTTPClient"]

openml/_api/http/client.py

@@ -0,0 +1,39 @@
+from __future__ import annotations
+
+from typing import Any, Mapping
+
+import requests
+from requests import Response
+
+from openml.__version__ import __version__
+
+
+class HTTPClient:
+    def __init__(self, base_url: str) -> None:
+        self.base_url = base_url
+        self.headers: dict[str, str] = {"user-agent": f"openml-python/{__version__}"}
+
+    def get(
+        self,
+        path: str,
+        params: Mapping[str, Any] | None = None,
+    ) -> Response:
+        url = f"{self.base_url}/{path}"
+        return requests.get(url, params=params, headers=self.headers, timeout=10)
+
+    def post(
+        self,
+        path: str,
+        data: Mapping[str, Any] | None = None,
+        files: Any = None,
+    ) -> Response:
+        url = f"{self.base_url}/{path}"
+        return requests.post(url, data=data, files=files, headers=self.headers, timeout=10)
+
+    def delete(
+        self,
+        path: str,
+        params: Mapping[str, Any] | None = None,
+    ) -> Response:
+        url = f"{self.base_url}/{path}"
+        return requests.delete(url, params=params, headers=self.headers, timeout=10)

openml/_api/resources/__init__.py

@@ -0,0 +1,4 @@
+from openml._api.resources.datasets import DatasetsV1, DatasetsV2
+from openml._api.resources.tasks import TasksV1, TasksV2
+
+__all__ = ["DatasetsV1", "DatasetsV2", "TasksV1", "TasksV2"]

openml/_api/resources/base.py

@@ -0,0 +1,31 @@
+from __future__ import annotations
+
+from abc import ABC, abstractmethod
+from typing import TYPE_CHECKING
+
+if TYPE_CHECKING:
+    from requests import Response
+
+    from openml._api.http import HTTPClient
+    from openml.datasets.dataset import OpenMLDataset
+    from openml.tasks.task import OpenMLTask
+
+
+class ResourceAPI:
+    def __init__(self, http: HTTPClient):
+        self._http = http
+
+
+class DatasetsAPI(ResourceAPI, ABC):
+    @abstractmethod
+    def get(self, dataset_id: int) -> OpenMLDataset | tuple[OpenMLDataset, Response]: ...
+
+
+class TasksAPI(ResourceAPI, ABC):
+    @abstractmethod
+    def get(
+        self,
+        task_id: int,
+        *,
+        return_response: bool = False,
+    ) -> OpenMLTask | tuple[OpenMLTask, Response]: ...

openml/_api/resources/datasets.py

@@ -0,0 +1,20 @@
+from __future__ import annotations
+
+from typing import TYPE_CHECKING
+
+from openml._api.resources.base import DatasetsAPI
+
+if TYPE_CHECKING:
+    from responses import Response
+
+    from openml.datasets.dataset import OpenMLDataset
+
+
+class DatasetsV1(DatasetsAPI):
+    def get(self, dataset_id: int) -> OpenMLDataset | tuple[OpenMLDataset, Response]:
+        raise NotImplementedError
+
+
+class DatasetsV2(DatasetsAPI):
+    def get(self, dataset_id: int) -> OpenMLDataset | tuple[OpenMLDataset, Response]:
+        raise NotImplementedError

openml/_api/resources/tasks.py

@@ -0,0 +1,128 @@
+from __future__ import annotations
+
+from typing import TYPE_CHECKING
+
+import xmltodict
+
+from openml._api.resources.base import TasksAPI
+from openml.tasks.task import (
+    OpenMLClassificationTask,
+    OpenMLClusteringTask,
+    OpenMLLearningCurveTask,
+    OpenMLRegressionTask,
+    OpenMLTask,
+    TaskType,
+)
+
+if TYPE_CHECKING:
+    from requests import Response
+
+
+class TasksV1(TasksAPI):
+    def get(
+        self,
+        task_id: int,
+        *,
+        return_response: bool = False,
+    ) -> OpenMLTask | tuple[OpenMLTask, Response]:
+        path = f"task/{task_id}"
+        response = self._http.get(path)
+        xml_content = response.text
+        task = self._create_task_from_xml(xml_content)
+
+        if return_response:
+            return task, response
+
+        return task
+
+    def _create_task_from_xml(self, xml: str) -> OpenMLTask:
+        """Create a task given a xml string.
+
+        Parameters
+        ----------
+        xml : string
+            Task xml representation.
+
+        Returns
+        -------
+        OpenMLTask
+        """
+        dic = xmltodict.parse(xml)["oml:task"]
+        estimation_parameters = {}
+        inputs = {}
+        # Due to the unordered structure we obtain, we first have to extract
+        # the possible keys of oml:input; dic["oml:input"] is a list of
+        # OrderedDicts
+
+        # Check if there is a list of inputs
+        if isinstance(dic["oml:input"], list):
+            for input_ in dic["oml:input"]:
+                name = input_["@name"]
+                inputs[name] = input_
+        # Single input case
+        elif isinstance(dic["oml:input"], dict):
+            name = dic["oml:input"]["@name"]
+            inputs[name] = dic["oml:input"]
+
+        evaluation_measures = None
+        if "evaluation_measures" in inputs:
+            evaluation_measures = inputs["evaluation_measures"]["oml:evaluation_measures"][
+                "oml:evaluation_measure"
+            ]
+
+        task_type = TaskType(int(dic["oml:task_type_id"]))
+        common_kwargs = {
+            "task_id": dic["oml:task_id"],
+            "task_type": dic["oml:task_type"],
+            "task_type_id": task_type,
+            "data_set_id": inputs["source_data"]["oml:data_set"]["oml:data_set_id"],
+            "evaluation_measure": evaluation_measures,
+        }
+        # TODO: add OpenMLClusteringTask?
+        if task_type in (
+            TaskType.SUPERVISED_CLASSIFICATION,
+            TaskType.SUPERVISED_REGRESSION,
+            TaskType.LEARNING_CURVE,
+        ):
+            # Convert some more parameters
+            for parameter in inputs["estimation_procedure"]["oml:estimation_procedure"][
+                "oml:parameter"
+            ]:
+                name = parameter["@name"]
+                text = parameter.get("#text", "")
+                estimation_parameters[name] = text
+
+            common_kwargs["estimation_procedure_type"] = inputs["estimation_procedure"][
+                "oml:estimation_procedure"
+            ]["oml:type"]
+            common_kwargs["estimation_procedure_id"] = int(
+                inputs["estimation_procedure"]["oml:estimation_procedure"]["oml:id"]
+            )
+
+            common_kwargs["estimation_parameters"] = estimation_parameters
+            common_kwargs["target_name"] = inputs["source_data"]["oml:data_set"][
+                "oml:target_feature"
+            ]
+            common_kwargs["data_splits_url"] = inputs["estimation_procedure"][
+                "oml:estimation_procedure"
+            ]["oml:data_splits_url"]
+
+        cls = {
+            TaskType.SUPERVISED_CLASSIFICATION: OpenMLClassificationTask,
+            TaskType.SUPERVISED_REGRESSION: OpenMLRegressionTask,
+            TaskType.CLUSTERING: OpenMLClusteringTask,
+            TaskType.LEARNING_CURVE: OpenMLLearningCurveTask,
+        }.get(task_type)
+        if cls is None:
+            raise NotImplementedError(f"Task type {common_kwargs['task_type']} not supported.")
+        return cls(**common_kwargs)  # type: ignore
+
+
+class TasksV2(TasksAPI):
+    def get(
+        self,
+        task_id: int,
+        *,
+        return_response: bool = False,
+    ) -> OpenMLTask | tuple[OpenMLTask, Response]:
+        raise NotImplementedError

openml/_api/runtime/core.py

@@ -0,0 +1,59 @@
+from __future__ import annotations
+
+from typing import TYPE_CHECKING
+
+from openml._api.config import (
+    API_V1_SERVER,
+    API_V2_SERVER,
+)
+from openml._api.http.client import HTTPClient
+from openml._api.resources import (
+    DatasetsV1,
+    DatasetsV2,
+    TasksV1,
+    TasksV2,
+)
+
+if TYPE_CHECKING:
+    from openml._api.resources.base import DatasetsAPI, TasksAPI
+
+
+class APIBackend:
+    def __init__(self, *, datasets: DatasetsAPI, tasks: TasksAPI):
+        self.datasets = datasets
+        self.tasks = tasks
+
+
+def build_backend(version: str, *, strict: bool) -> APIBackend:
+    v1_http = HTTPClient(API_V1_SERVER)
+    v2_http = HTTPClient(API_V2_SERVER)
+
+    v1 = APIBackend(
+        datasets=DatasetsV1(v1_http),
+        tasks=TasksV1(v1_http),
+    )
+
+    if version == "v1":
+        return v1
+
+    v2 = APIBackend(
+        datasets=DatasetsV2(v2_http),
+        tasks=TasksV2(v2_http),
+    )
+
+    if strict:
+        return v2
+
+    return v1
+
+
+class APIContext:
+    def __init__(self) -> None:
+        self._backend = build_backend("v1", strict=False)
+
+    def set_version(self, version: str, *, strict: bool = False) -> None:
+        self._backend = build_backend(version=version, strict=strict)
+
+    @property
+    def backend(self) -> APIBackend:
+        return self._backend

openml/_api/runtime/fallback.py

@@ -0,0 +1,12 @@
+from __future__ import annotations
+
+from typing import TYPE_CHECKING
+
+if TYPE_CHECKING:
+    from openml._api.resources.base import ResourceAPI
+
+
+class FallbackProxy:
+    def __init__(self, primary: ResourceAPI, fallback: ResourceAPI):
+        self._primary = primary
+        self._fallback = fallback

openml/tasks/functions.py

@@ -12,6 +12,7 @@
 
 import openml._api_calls
 import openml.utils
+from openml._api import api_context
 from openml.datasets import get_dataset
 from openml.exceptions import OpenMLCacheException
 
@@ -444,11 +445,16 @@ def _get_task_description(task_id: int) -> OpenMLTask:
     except OpenMLCacheException:
         _cache_dir = openml.utils._create_cache_directory_for_id(TASKS_CACHE_DIR_NAME, task_id)
         xml_file = _cache_dir / "task.xml"
-        task_xml = openml._api_calls._perform_api_call("task/%d" % task_id, "get")
+        result = api_context.backend.tasks.get(task_id, return_response=True)
 
-        with xml_file.open("w", encoding="utf8") as fh:
-            fh.write(task_xml)
-        return _create_task_from_xml(task_xml)
+        if isinstance(result, tuple):
+            task, response = result
+            with xml_file.open("w", encoding="utf8") as fh:
+                fh.write(response.text)
+        else:
+            task = result
+
+        return task
 
 
 def _create_task_from_xml(xml: str) -> OpenMLTask: