Fix mypy errors: made implicit optional typing to be explicit

openml · mfeurer · Apr 25, 2023 · Apr 10, 2023 · Apr 10, 2023 · Apr 18, 2023
commit d766d9804b753b5f2c73c03bcc6e7178070d4763
diff --git a/doc/progress.rst b/doc/progress.rst
@@ -9,15 +9,16 @@ Changelog
 0.13.1
 ~~~~~~
 
- * DOC #1241 #1229 #1231: Minor documentation fixes and resolve documentation examples not working.
  * 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.
  * ADD #1180: Improve the error message when the checksum of a downloaded dataset does not match the checksum provided by the API.
  * ADD #1201: Make ``OpenMLTraceIteration`` a dataclass.
  * DOC #1069: Add argument documentation for the ``OpenMLRun`` class.
+ * DOC #1241 #1229 #1231: Minor documentation fixes and resolve documentation examples not working.
  * 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.
  * FIX #1216: Allow unknown task types on the server. This is only relevant when new task types are added to the test server.
+ * FIX #1223: Fix mypy errors for implicit optional typing.
  * MAINT #1155: Add dependabot github action to automatically update other github actions.
  * MAINT #1199: Obtain pre-commit's flake8 from github.com instead of gitlab.com.
  * MAINT #1215: Support latest numpy version.

diff --git a/openml/_api_calls.py b/openml/_api_calls.py
@@ -195,7 +195,7 @@ def _download_minio_bucket(
 def _download_text_file(
     source: str,
     output_path: Optional[str] = None,
-    md5_checksum: str = None,
+    md5_checksum: Optional[str] = None,
     exists_ok: bool = True,
     encoding: str = "utf8",
 ) -> Optional[str]:

diff --git a/openml/datasets/functions.py b/openml/datasets/functions.py
@@ -351,7 +351,7 @@ def get_datasets(
 def get_dataset(
     dataset_id: Union[int, str],
     download_data: bool = True,
-    version: int = None,
+    version: Optional[int] = None,
     error_if_multiple: bool = False,
     cache_format: str = "pickle",
     download_qualities: bool = True,
@@ -982,7 +982,7 @@ def _get_dataset_description(did_cache_dir, dataset_id):
 
 def _get_dataset_parquet(
     description: Union[Dict, OpenMLDataset],
-    cache_directory: str = None,
+    cache_directory: Optional[str] = None,
     download_all_files: bool = False,
 ) -> Optional[str]:
     """Return the path to the local parquet file of the dataset. If is not cached, it is downloaded.
@@ -1049,7 +1049,9 @@ def _get_dataset_parquet(
     return output_file_path
 
 
-def _get_dataset_arff(description: Union[Dict, OpenMLDataset], cache_directory: str = None) -> str:
+def _get_dataset_arff(
+    description: Union[Dict, OpenMLDataset], cache_directory: Optional[str] = None
+) -> str:
     """Return the path to the local arff file of the dataset. If is not cached, it is downloaded.
 
     Checks if the file is in the cache, if yes, return the path to the file.
@@ -1171,8 +1173,8 @@ def _create_dataset_from_description(
     description: Dict[str, str],
     features_file: str,
     qualities_file: str,
-    arff_file: str = None,
-    parquet_file: str = None,
+    arff_file: Optional[str] = None,
+    parquet_file: Optional[str] = None,
     cache_format: str = "pickle",
 ) -> OpenMLDataset:
     """Create a dataset object from a description dict.

diff --git a/openml/exceptions.py b/openml/exceptions.py
@@ -1,5 +1,7 @@
 # License: BSD 3-Clause
 
+from typing import Optional
+
 
 class PyOpenMLError(Exception):
     def __init__(self, message: str):
@@ -20,7 +22,7 @@ class OpenMLServerException(OpenMLServerError):
 
     # 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):
+    def __init__(self, message: str, code: Optional[int] = None, url: Optional[str] = None):
         self.message = message
         self.code = code
         self.url = url

diff --git a/openml/flows/functions.py b/openml/flows/functions.py
@@ -374,7 +374,7 @@ def _check_flow_for_server_id(flow: OpenMLFlow) -> None:
 def assert_flows_equal(
     flow1: OpenMLFlow,
     flow2: OpenMLFlow,
-    ignore_parameter_values_on_older_children: str = None,
+    ignore_parameter_values_on_older_children: Optional[str] = None,
     ignore_parameter_values: bool = False,
     ignore_custom_name_if_none: bool = False,
     check_description: bool = True,

diff --git a/openml/runs/functions.py b/openml/runs/functions.py
@@ -49,8 +49,8 @@ def run_model_on_task(
     model: Any,
     task: Union[int, str, OpenMLTask],
     avoid_duplicate_runs: bool = True,
-    flow_tags: List[str] = None,
-    seed: int = None,
+    flow_tags: Optional[List[str]] = None,
+    seed: Optional[int] = None,
     add_local_measures: bool = True,
     upload_flow: bool = False,
     return_flow: bool = False,
@@ -148,8 +148,8 @@ def run_flow_on_task(
     flow: OpenMLFlow,
     task: OpenMLTask,
     avoid_duplicate_runs: bool = True,
-    flow_tags: List[str] = None,
-    seed: int = None,
+    flow_tags: Optional[List[str]] = None,
+    seed: Optional[int] = None,
     add_local_measures: bool = True,
     upload_flow: bool = False,
     dataset_format: str = "dataframe",
@@ -438,7 +438,7 @@ def _run_task_get_arffcontent(
     extension: "Extension",
     add_local_measures: bool,
     dataset_format: str,
-    n_jobs: int = None,
+    n_jobs: Optional[int] = None,
 ) -> Tuple[
     List[List],
     Optional[OpenMLRunTrace],
@@ -621,7 +621,7 @@ def _run_task_get_arffcontent_parallel_helper(
     sample_no: int,
     task: OpenMLTask,
     dataset_format: str,
-    configuration: Dict = None,
+    configuration: Optional[Dict] = None,
 ) -> Tuple[
     np.ndarray,
     Optional[pd.DataFrame],