Issue 1028: public delete functions for run, task, flow and database (#1060)

Author: Mirkazemi

.gitignore

@@ -77,6 +77,7 @@ target/
 # IDE
 .idea
 *.swp
+.vscode
 
 # MYPY
 .mypy_cache

doc/api.rst

@@ -38,6 +38,7 @@ Dataset Functions
     attributes_arff_from_df
     check_datasets_active
     create_dataset
+    delete_dataset
     get_dataset
     get_datasets
     list_datasets
@@ -103,6 +104,7 @@ Flow Functions
    :template: function.rst
 
     assert_flows_equal
+    delete_flow
     flow_exists
     get_flow
     list_flows
@@ -133,6 +135,7 @@ Run Functions
    :toctree: generated/
    :template: function.rst
 
+    delete_run
     get_run
     get_runs
     get_run_trace
@@ -251,6 +254,7 @@ Task Functions
    :template: function.rst
 
     create_task
+    delete_task
     get_task
     get_tasks
     list_tasks

doc/progress.rst

@@ -10,10 +10,10 @@ Changelog
 ~~~~~~
 
  * Add new contributions here.
- * ADD#1144: Add locally computed results to the ``OpenMLRun`` object's representation.
+ * ADD#1028: Add functions to delete runs, flows, datasets, and tasks (e.g., ``openml.datasets.delete_dataset``).
+ * ADD#1144: Add locally computed results to the ``OpenMLRun`` object's representation if the run was created locally and not downloaded from the server.
  * FIX #1197 #559 #1131: Fix the order of ground truth and predictions in the ``OpenMLRun`` object and in ``format_prediction``.
  * FIX #1198: Support numpy 1.24 and higher.
- * ADD#1144: Add locally computed results to the ``OpenMLRun`` object's representation if the run was created locally and not downloaded from the server.
 
 0.13.0
 ~~~~~~

openml/_api_calls.py

@@ -351,10 +351,12 @@ def _send_request(request_method, url, data, files=None, md5_checksum=None):
                 xml.parsers.expat.ExpatError,
                 OpenMLHashException,
             ) as e:
-                if isinstance(e, OpenMLServerException):
-                    if e.code not in [107]:
-                        # 107: database connection error
-                        raise
+                if isinstance(e, OpenMLServerException) and e.code != 107:
+                    # Propagate all server errors to the calling functions, except
+                    # for 107 which represents a database connection error.
+                    # These are typically caused by high server load,
+                    # which means trying again might resolve the issue.
+                    raise
                 elif isinstance(e, xml.parsers.expat.ExpatError):
                     if request_method != "get" or retry_counter >= n_retries:
                         raise OpenMLServerError(

openml/datasets/__init__.py

@@ -11,6 +11,7 @@
     list_qualities,
     edit_dataset,
     fork_dataset,
+    delete_dataset,
 )
 from .dataset import OpenMLDataset
 from .data_feature import OpenMLDataFeature
@@ -28,4 +29,5 @@
     "list_qualities",
     "edit_dataset",
     "fork_dataset",
+    "delete_dataset",
 ]

openml/datasets/functions.py

@@ -1271,3 +1271,22 @@ def _get_online_dataset_format(dataset_id):
     dataset_xml = openml._api_calls._perform_api_call("data/%d" % dataset_id, "get")
     # build a dict from the xml and get the format from the dataset description
     return xmltodict.parse(dataset_xml)["oml:data_set_description"]["oml:format"].lower()
+
+
+def delete_dataset(dataset_id: int) -> bool:
+    """Delete dataset with id `dataset_id` from the OpenML server.
+
+    This can only be done if you are the owner of the dataset and
+    no tasks are attached to the dataset.
+
+    Parameters
+    ----------
+    dataset_id : int
+        OpenML id of the dataset
+
+    Returns
+    -------
+    bool
+        True if the deletion was successful. False otherwise.
+    """
+    return openml.utils._delete_entity("data", dataset_id)

openml/exceptions.py

@@ -11,15 +11,14 @@ class OpenMLServerError(PyOpenMLError):
     """class for when something is really wrong on the server
     (result did not parse to dict), contains unparsed error."""
 
-    def __init__(self, message: str):
-        super().__init__(message)
+    pass
 
 
 class OpenMLServerException(OpenMLServerError):
     """exception for when the result of the server was
     not 200 (e.g., listing call w/o results)."""
 
-    # Code needs to be optional to allow the exceptino to be picklable:
+    # Code needs to be optional to allow the exception to be picklable:
     # https://stackoverflow.com/questions/16244923/how-to-make-a-custom-exception-class-with-multiple-init-args-pickleable  # noqa: E501
     def __init__(self, message: str, code: int = None, url: str = None):
         self.message = message
@@ -28,24 +27,19 @@ def __init__(self, message: str, code: int = None, url: str = None):
         super().__init__(message)
 
     def __str__(self):
-        return "%s returned code %s: %s" % (
-            self.url,
-            self.code,
-            self.message,
-        )
+        return f"{self.url} returned code {self.code}: {self.message}"
 
 
 class OpenMLServerNoResult(OpenMLServerException):
-    """exception for when the result of the server is empty."""
+    """Exception for when the result of the server is empty."""
 
     pass
 
 
 class OpenMLCacheException(PyOpenMLError):
     """Dataset / task etc not found in cache"""
 
-    def __init__(self, message: str):
-        super().__init__(message)
+    pass
 
 
 class OpenMLHashException(PyOpenMLError):
@@ -57,8 +51,7 @@ class OpenMLHashException(PyOpenMLError):
 class OpenMLPrivateDatasetError(PyOpenMLError):
     """Exception thrown when the user has no rights to access the dataset."""
 
-    def __init__(self, message: str):
-        super().__init__(message)
+    pass
 
 
 class OpenMLRunsExistError(PyOpenMLError):
@@ -69,3 +62,9 @@ def __init__(self, run_ids: set, message: str):
             raise ValueError("Set of run ids must be non-empty.")
         self.run_ids = run_ids
         super().__init__(message)
+
+
+class OpenMLNotAuthorizedError(OpenMLServerError):
+    """Indicates an authenticated user is not authorized to execute the requested action."""
+
+    pass

openml/flows/__init__.py

@@ -2,7 +2,14 @@
 
 from .flow import OpenMLFlow
 
-from .functions import get_flow, list_flows, flow_exists, get_flow_id, assert_flows_equal
+from .functions import (
+    get_flow,
+    list_flows,
+    flow_exists,
+    get_flow_id,
+    assert_flows_equal,
+    delete_flow,
+)
 
 __all__ = [
     "OpenMLFlow",
@@ -11,4 +18,5 @@
     "get_flow_id",
     "flow_exists",
     "assert_flows_equal",
+    "delete_flow",
 ]

openml/flows/functions.py

@@ -544,3 +544,22 @@ def _create_flow_from_xml(flow_xml: str) -> OpenMLFlow:
     """
 
     return OpenMLFlow._from_dict(xmltodict.parse(flow_xml))
+
+
+def delete_flow(flow_id: int) -> bool:
+    """Delete flow with id `flow_id` from the OpenML server.
+
+    You can only delete flows which you uploaded and which
+    which are not linked to runs.
+
+    Parameters
+    ----------
+    flow_id : int
+        OpenML id of the flow
+
+    Returns
+    -------
+    bool
+        True if the deletion was successful. False otherwise.
+    """
+    return openml.utils._delete_entity("flow", flow_id)

openml/runs/__init__.py

@@ -12,6 +12,7 @@
     run_exists,
     initialize_model_from_run,
     initialize_model_from_trace,
+    delete_run,
 )
 
 __all__ = [
@@ -27,4 +28,5 @@
     "run_exists",
     "initialize_model_from_run",
     "initialize_model_from_trace",
+    "delete_run",
 ]