_get_estimation_procedure_list work

Author: satvshr

openml/_api/resources/base/resources.py

@@ -12,8 +12,7 @@
 if TYPE_CHECKING:
     import pandas as pd
 
-    from openml.estimation_procedures import OpenMLEstimationProcedure
-    from openml.evaluations import OpenMLEvaluation
+    from openml import OpenMLEvaluation
     from openml.flows.flow import OpenMLFlow
     from openml.setups.setup import OpenMLSetup
     from openml.tasks.task import OpenMLTask, TaskType
@@ -88,9 +87,6 @@ class EstimationProcedureAPI(ResourceAPI):
 
     resource_type: ResourceType = ResourceType.ESTIMATION_PROCEDURE
 
-    @abstractmethod
-    def list(self) -> list[OpenMLEstimationProcedure]: ...
-
 
 class EvaluationAPI(ResourceAPI):
     """Abstract API interface for evaluation resources."""

openml/_api/resources/task.py

@@ -6,7 +6,7 @@
 import pandas as pd
 import xmltodict
 
-import openml
+from openml.tasks.functions import _get_estimation_procedure_list
 from openml.tasks.task import (
     OpenMLClassificationTask,
     OpenMLClusteringTask,
@@ -19,62 +19,6 @@
 from .base import ResourceV1API, ResourceV2API, TaskAPI
 
 
-def _get_estimation_procedure_list() -> list[dict[str, Any]]:
-    """Return a list of all estimation procedures which are on OpenML.
-
-    Returns
-    -------
-    procedures : list
-        A list of all estimation procedures. Every procedure is represented by
-        a dictionary containing the following information: id, task type id,
-        name, type, repeats, folds, stratified.
-    """
-    url_suffix = "estimationprocedure/list"
-    xml_string = openml._api_calls._perform_api_call(url_suffix, "get")
-
-    procs_dict = xmltodict.parse(xml_string)
-    # Minimalistic check if the XML is useful
-    if "oml:estimationprocedures" not in procs_dict:
-        raise ValueError("Error in return XML, does not contain tag oml:estimationprocedures.")
-
-    if "@xmlns:oml" not in procs_dict["oml:estimationprocedures"]:
-        raise ValueError(
-            "Error in return XML, does not contain tag "
-            "@xmlns:oml as a child of oml:estimationprocedures.",
-        )
-
-    if procs_dict["oml:estimationprocedures"]["@xmlns:oml"] != "http://openml.org/openml":
-        raise ValueError(
-            "Error in return XML, value of "
-            "oml:estimationprocedures/@xmlns:oml is not "
-            "http://openml.org/openml, but {}".format(
-                str(procs_dict["oml:estimationprocedures"]["@xmlns:oml"])
-            ),
-        )
-
-    procs: list[dict[str, Any]] = []
-    for proc_ in procs_dict["oml:estimationprocedures"]["oml:estimationprocedure"]:
-        task_type_int = int(proc_["oml:ttid"])
-        try:
-            task_type_id = TaskType(task_type_int)
-            procs.append(
-                {
-                    "id": int(proc_["oml:id"]),
-                    "task_type_id": task_type_id,
-                    "name": proc_["oml:name"],
-                    "type": proc_["oml:type"],
-                },
-            )
-        except ValueError as e:
-            warnings.warn(
-                f"Could not create task type id for {task_type_int} due to error {e}",
-                RuntimeWarning,
-                stacklevel=2,
-            )
-
-    return procs
-
-
 def _create_task_from_xml(xml: str) -> OpenMLTask:
     """Create a task given a xml string.
 

openml/tasks/functions.py

@@ -1,18 +1,14 @@
 # License: BSD 3-Clause
 from __future__ import annotations
 
-import os
-import re
 import warnings
 from functools import partial
 from typing import TYPE_CHECKING, Any
 
 import pandas as pd
 
 import openml.utils
-from openml._api.resources.task import _create_task_from_xml
 from openml.datasets import get_dataset
-from openml.exceptions import OpenMLCacheException
 
 from .task import (
     OpenMLClassificationTask,
@@ -30,48 +26,6 @@
 TASKS_CACHE_DIR_NAME = "tasks"
 
 
-def _get_cached_tasks() -> dict[int, OpenMLTask]:
-    """Return a dict of all the tasks which are cached locally.
-
-    Returns
-    -------
-    tasks : OrderedDict
-        A dict of all the cached tasks. Each task is an instance of
-        OpenMLTask.
-    """
-    task_cache_dir = openml.utils._create_cache_directory(TASKS_CACHE_DIR_NAME)
-    directory_content = os.listdir(task_cache_dir)  # noqa: PTH208
-    directory_content.sort()
-
-    # Find all dataset ids for which we have downloaded the dataset
-    # description
-    tids = (int(did) for did in directory_content if re.match(r"[0-9]*", did))
-    return {tid: _get_cached_task(tid) for tid in tids}
-
-
-def _get_cached_task(tid: int) -> OpenMLTask:
-    """Return a cached task based on the given id.
-
-    Parameters
-    ----------
-    tid : int
-        Id of the task.
-
-    Returns
-    -------
-    OpenMLTask
-    """
-    tid_cache_dir = openml.utils._create_cache_directory_for_id(TASKS_CACHE_DIR_NAME, tid)
-
-    task_xml_path = tid_cache_dir / "task.xml"
-    try:
-        with task_xml_path.open(encoding="utf8") as fh:
-            return _create_task_from_xml(fh.read())
-    except OSError as e:
-        openml.utils._remove_cache_dir_for_id(TASKS_CACHE_DIR_NAME, tid_cache_dir)
-        raise OpenMLCacheException(f"Task file for tid {tid} not cached") from e
-
-
 def _get_estimation_procedure_list() -> list[dict[str, Any]]:
     """Return a list of all estimation procedures which are on OpenML.
 

tests/test_tasks/test_task_functions.py

@@ -29,7 +29,7 @@ def tearDown(self):
 
     @pytest.mark.test_server()
     def test__get_estimation_procedure_list(self):
-        estimation_procedures = openml._api.resources.task._get_estimation_procedure_list()
+        estimation_procedures = openml.tasks.functions._get_estimation_procedure_list()
         assert isinstance(estimation_procedures, list)
         assert isinstance(estimation_procedures[0], dict)
         assert estimation_procedures[0]["task_type_id"] == TaskType.SUPERVISED_CLASSIFICATION