0000: Added typing and linting tooling framework, setup shared vscode workspace configuration

.gitignore

@@ -138,7 +138,13 @@ report.html
 howso/examples/output.csv
 
 # IDE files
-.vscode
+# VSCode
+.vscode/*
+!.vscode/settings.json
+!.vscode/tasks.json
+!.vscode/launch.json
+!.vscode/extensions.json
+!.vscode/*.code-snippets
 
 # Cache files
 .howso_recent_cache*

.vscode/settings.json

@@ -0,0 +1,22 @@
+{
+  "cSpell.words": [
+    "autouse",
+    "caml",
+    "camls",
+    "dateutil",
+    "finfo",
+    "howsoai",
+    "iinfo",
+    "isinstance",
+    "isoparse",
+    "issubdtype",
+    "itemsize",
+    "jsonifiable",
+    "pyright",
+    "pytest",
+    "setosa",
+    "SMAPE",
+    "subdtype",
+    "targetless"
+  ]
+}

howso/client/tests/test_client.py

@@ -460,7 +460,7 @@ def test_copy(self, trainee, trainee_builder):
         copy_features = self.client.get_feature_attributes(new_trainee.id)
         assert orig_features == copy_features
 
-    def test_trainee_conviction(self, trainee, trainee_builder):
+    def test_trainee_conviction(self, trainee):
         """
         Test the /copy/{trainee_id} endpoint.
 

howso/direct/client.py

@@ -138,7 +138,7 @@ def __init__(
         train_initial_batch_size: int = 100,
         verbose: bool = False,
         version_check: bool = True,
-        **kwargs
+        **kwargs  # noqa ARG002
     ):
         global _VERSION_CHECKED
 
@@ -378,10 +378,10 @@ def _deserialize(self, label: str, payload: str | bytes | None) -> t.Any:
             return data
         except HowsoError:
             raise
-        except Exception:  # noqa: Deliberately broad
+        except Exception: # Deliberately broad
             raise HowsoError('Failed to deserialize the Howso Engine response.')
 
-    def _resolve_trainee(self, trainee_id: str, **kwargs) -> DirectTrainee:
+    def _resolve_trainee(self, trainee_id: str, **kwargs) -> DirectTrainee:  # noqa ARG002
         """
         Resolve a Trainee and acquire its resources.
 
@@ -538,7 +538,7 @@ def _get_trainee_from_engine(self, trainee_id: str) -> DirectTrainee:
             file_size=file_size
         )
 
-    def _get_trainee_thread_count(self, trainee_id: str) -> int:
+    def _get_trainee_thread_count(self, trainee_id: str) -> int: # noqa ARG002
         """
         Get the number of available cpu threads a Trainee has access to.
 
@@ -612,7 +612,7 @@ def _trainee_size(self, filename: str) -> int | None:
             return None
         return path.stat().st_size
 
-    def execute(self, trainee_id: str, label: str, payload: t.Any, **kwargs) -> t.Any:
+    def execute(self, trainee_id: str, label: str, payload: t.Any, **kwargs) -> t.Any:  # noqa ARG002
         """
         Execute a label in Howso engine.
 
@@ -638,7 +638,7 @@ def execute(self, trainee_id: str, label: str, payload: t.Any, **kwargs) -> t.An
             raise HowsoError('Invalid payload - please check for infinity or NaN values') from err
         return self._deserialize(label, result)
 
-    def execute_sized(self, trainee_id: str, label: str, payload: t.Any, **kwargs) -> tuple[t.Any, int, int]:
+    def execute_sized(self, trainee_id: str, label: str, payload: t.Any, **kwargs) -> tuple[t.Any, int, int]:  # noqa ARG002
         """
         Execute a label in Howso engine and return the request and response sizes.
 
@@ -668,7 +668,7 @@ def execute_sized(self, trainee_id: str, label: str, payload: t.Any, **kwargs) -
             raise HowsoError('Invalid payload - please check for infinity or NaN values') from err
         return self._deserialize(label, result), len(json_payload), len(result)
 
-    def is_tracing_enabled(self, trainee_id: str) -> bool:
+    def is_tracing_enabled(self, trainee_id: str) -> bool: # noqa ARG002
         """
         Get if tracing is enabled for Trainee.
 
@@ -747,7 +747,7 @@ def check_name_valid_for_save(
                 ):
                     return False, 'Cannot write to this path'
 
-        except Exception as e:  # noqa: Deliberately broad
+        except Exception as e: # Deliberately broad
             return False, f'Exception {e} while checking file'
         else:
             return True, 'OK'
@@ -759,13 +759,13 @@ def create_trainee(  # noqa: C901
         *,
         id: t.Optional[str | uuid.UUID] = None,
         library_type: t.Optional[LibraryType] = None,
-        max_wait_time: t.Optional[int | float] = None,
+        max_wait_time: t.Optional[int | float] = None,  # noqa ARG002
         metadata: t.Optional[MutableMapping[str, t.Any]] = None,
         overwrite_trainee: bool = False,
         persistence: Persistence = "allow",
-        project: t.Optional[str | Project] = None,
+        project: t.Optional[str | Project] = None,  # noqa ARG002
         resources: t.Optional[Mapping[str, t.Any]] = None,
-        runtime: t.Optional[TraineeRuntimeOptions] = None,
+        runtime: t.Optional[TraineeRuntimeOptions] = None, # noqa ARG002
     ) -> Trainee:
         """
         Create a Trainee on the Howso service.
@@ -856,7 +856,7 @@ def create_trainee(  # noqa: C901
                     self.configuration.verbose,
                     f'Deleting existing Trainee "{trainee_id}" before creating.')
                 self.amlg.destroy_entity(trainee_id)
-            except Exception:  # noqa: Deliberately broad
+            except Exception: # Deliberately broad
                 util.dprint(
                     self.configuration.verbose,
                     f'Unable to delete Trainee "{trainee_id}". Continuing.')
@@ -1246,7 +1246,7 @@ def copy_trainee(
         *,
         library_type: t.Optional[LibraryType] = None,
         resources: t.Optional[Mapping[str, t.Any]] = None,
-        runtime: t.Optional[TraineeRuntimeOptions] = None
+        runtime: t.Optional[TraineeRuntimeOptions] = None # noqa ARG002
     ) -> Trainee:
         """
         Copies a trainee to a new trainee id in the Howso service.
@@ -1349,7 +1349,7 @@ def acquire_trainee_resources(
         self,
         trainee_id: str,
         *,
-        max_wait_time: t.Optional[int | float] = None
+        max_wait_time: t.Optional[int | float] = None  # noqa ARG002
     ):
         """
         Acquire resources for a trainee in the Howso service.
@@ -1511,7 +1511,7 @@ def query_sessions(
         search_terms: t.Optional[str] = None,
         *,
         trainee: t.Optional[str | Trainee] = None,
-        **kwargs
+        **kwargs # noqa ARG002
     ) -> list[Session]:
         """
         Return a list of all accessible sessions.

howso/engine/tests/test_engine.py

@@ -54,7 +54,7 @@ def test_pairwise_distances(self, trainee, from_values, to_values, expected):
             ([11, 41, 102], [[0, 0, 0], [0, 0, 0], [0, 0, 0]]),
         ],
     )
-    def test_distances_same(self, trainee, features, case_indices, expected):
+    def test_distances_same(self, trainee, case_indices, expected):
         """
         Test that get_distances returns values as expected.
 
@@ -80,7 +80,7 @@ def test_distances_same(self, trainee, features, case_indices, expected):
             ([2, 3, 4], [[0, 0, 0], [0, 0, 0], [0, 0, 0]]),
         ],
     )
-    def test_distances_different(self, trainee, features, case_indices, unexpected):
+    def test_distances_different(self, trainee, case_indices, unexpected):
         """
         Test that get_distances returns values as expected.
 
@@ -224,7 +224,7 @@ def test_load_status_message(self, mocker, monkeypatch, status_msg, expected_msg
         """Test load_trainee raises status message from Amalgam."""
         file_path = Path(Path.cwd(), "test_load.caml")
 
-        monkeypatch.setattr(Path, "exists", lambda *args: True)
+        monkeypatch.setattr(Path, "exists", lambda *args: True)  # noqa ARG005
         mocker.patch(
             "amalgam.api.Amalgam.load_entity",
             return_value=SimpleNamespace(loaded=False, message=status_msg, version="")

howso/engine/trainee.py

@@ -772,7 +772,7 @@ def set_auto_ablation_params(
         relative_prediction_threshold_map: t.Optional[Mapping[str, float]] = None,
         residual_prediction_features: t.Optional[Collection[str]] = None,
         tolerance_prediction_threshold_map: t.Optional[Mapping[str, tuple[float, float]]] = None,
-        **kwargs
+        **kwargs # noqa ARG002
     ):
         """
         Set trainee parameters for auto-ablation.
@@ -1705,7 +1705,7 @@ def react(
             be used if the Trainee has them.
         use_regional_residuals : bool, default True
             When False, uses global residuals. When True, calculates and uses
-            regional residuals, which may increase runtime noticably.
+            regional residuals, which may increase runtime noticeably.
         weight_feature : str, optional
             Name of feature whose values to use as case weights.
             When left unspecified uses the internally managed case weight.

howso/utilities/feature_attributes/abstract_data.py

@@ -507,7 +507,7 @@ def _infer_datetime_attributes(self, feature_name: str) -> dict:
             'date_time_format': dt_format,
         }
 
-    def _infer_date_attributes(self, feature_name: str) -> dict:
+    def _infer_date_attributes(self, feature_name: str) -> dict: # noqa ARG002
         return {
             'type': 'continuous',
             'data_type': 'formatted_date_time',
@@ -543,13 +543,13 @@ def _infer_time_attributes(self, feature_name: str, user_time_format: str = None
             'date_time_format': time_format,
         }
 
-    def _infer_timedelta_attributes(self, feature_name: str) -> dict:
+    def _infer_timedelta_attributes(self, feature_name: str) -> dict: # noqa ARG002
         return {
             'type': 'continuous',
             'data_type': 'number',
         }
 
-    def _infer_boolean_attributes(self, feature_name: str) -> dict:
+    def _infer_boolean_attributes(self, feature_name: str) -> dict: # noqa ARG002
         return {
             'type': 'nominal',
             'data_type': 'boolean',
@@ -628,7 +628,7 @@ def _infer_string_attributes(self, feature_name: str) -> dict:
         else:
             return self._infer_unknown_attributes(feature_name)
 
-    def _infer_unknown_attributes(self, feature_name: str) -> dict:
+    def _infer_unknown_attributes(self, feature_name: str) -> dict: # noqa ARG002
         return {
             'type': 'nominal',
         }

howso/utilities/feature_attributes/base.py

@@ -301,7 +301,7 @@ def _validate_dtype(self, data: pd.DataFrame, feature: str,  # noqa: C901
                 if coerce:
                     coerced_df[feature] = series
                 is_valid = True
-            except Exception: # noqa: Intentionally broad
+            except Exception: # Intentionally broad
                 pass
         elif expected_dtype == 'datetime64':
             try:
@@ -317,7 +317,7 @@ def _validate_dtype(self, data: pd.DataFrame, feature: str,  # noqa: C901
                     else:
                         coerced_df[feature] = series
                 is_valid = True
-            except Exception: # noqa: Intentionally broad
+            except Exception: # Intentionally broad
                 pass
         else:
             # Else, compare the dtype directly
@@ -334,7 +334,7 @@ def _validate_dtype(self, data: pd.DataFrame, feature: str,  # noqa: C901
                     # If this happens, there is a null value, thus a float dtype is OK
                     if pd.api.types.is_float_dtype(series):
                         is_valid = True
-                except Exception: # noqa: Intentionally broad
+                except Exception: # Intentionally broad
                     pass
 
         # Raise warnings if the types do not match
@@ -617,7 +617,7 @@ def has_unsupported_data(self, feature_name: str) -> bool:
         """
         return feature_name in self.unsupported
 
-    def to_dataframe(self, *, include_all: bool = False) -> pd.DataFrame:
+    def to_dataframe(self, *, include_all: bool = False) -> pd.DataFrame:  # noqa ARG002
         """
         Return a DataFrame of the feature attributes.
 
@@ -704,7 +704,7 @@ def _process(self,  # noqa: C901
                  include_extended_nominal_probabilities: t.Optional[bool] = False,
                  include_sample: bool = False,
                  infer_bounds: bool = True,
-                 max_workers: t.Optional[int] = None,
+                 max_workers: t.Optional[int] = None,  # noqa ARG002
                  mode_bound_features: t.Optional[Iterable[str]] = None,
                  nominal_substitution_config: t.Optional[dict[str, dict]] = None,
                  ordinal_feature_values: t.Optional[dict[str, list[str]]] = None,
@@ -1228,7 +1228,7 @@ def _is_datetime(string: str):
         try:
             dt_parse(string)
             return True
-        except Exception:  # noqa: Intentionally broad
+        except Exception: # Intentionally broad
             return False
 
     def _is_iso8601_datetime_column(self, feature: str) -> bool:
@@ -1264,7 +1264,7 @@ def _is_iso8601_datetime_column(self, feature: str) -> bool:
                 if not self._is_datetime(rand_val):
                     return False
                 isoparse(rand_val)
-        except Exception:  # noqa: Intentionally broad
+        except Exception: # Intentionally broad
             return False
 
         # No issues; it's valid

howso/utilities/feature_attributes/pandas.py

@@ -130,7 +130,7 @@ def _get_feature_names(self) -> list[str]:
                     'your DataFrame to use string column names.')
         return feature_names
 
-    def _has_unique_constraint(self, feature_name: str) -> bool:
+    def _has_unique_constraint(self, feature_name: str) -> bool: # noqa ARG002
         # This always returns False for DataFrames, which don't support such
         # constraints.
         return False
@@ -648,7 +648,7 @@ def _infer_datetime_attributes(self, feature_name: str) -> dict:
             'date_time_format': dt_format,
         }
 
-    def _infer_date_attributes(self, feature_name: str) -> dict:
+    def _infer_date_attributes(self, feature_name: str) -> dict: # noqa ARG002
         return {
             'type': 'continuous',
             'data_type': 'formatted_date_time',
@@ -684,13 +684,13 @@ def _infer_time_attributes(self, feature_name: str, user_time_format: str = None
             'date_time_format': time_format,
         }
 
-    def _infer_timedelta_attributes(self, feature_name: str) -> dict:
+    def _infer_timedelta_attributes(self, feature_name: str) -> dict: # noqa ARG002
         return {
             'type': 'continuous',
             'data_type': 'number',
         }
 
-    def _infer_boolean_attributes(self, feature_name: str) -> dict:
+    def _infer_boolean_attributes(self, feature_name: str) -> dict: # noqa ARG002
         return {
             'type': 'nominal',
             'data_type': 'boolean',
@@ -770,7 +770,7 @@ def _infer_string_attributes(self, feature_name: str) -> dict:
         else:
             return self._infer_unknown_attributes(feature_name)
 
-    def _infer_unknown_attributes(self, feature_name: str) -> dict:
+    def _infer_unknown_attributes(self, feature_name: str) -> dict: # noqa ARG002
         return {
             'type': 'nominal',
         }

howso/utilities/feature_attributes/relational.py

@@ -698,7 +698,7 @@ def _infer_timedelta_attributes(self, feature_name: str) -> dict:
             'data_type': 'number',
         }
 
-    def _infer_boolean_attributes(self, feature_name: str) -> dict:
+    def _infer_boolean_attributes(self, feature_name: str) -> dict: # noqa ARG002
         return {
             'type': 'nominal',
             'data_type': 'boolean',
@@ -786,7 +786,7 @@ def _infer_string_attributes(self, feature_name: str) -> dict:
         else:
             return self._infer_unknown_attributes(feature_name)
 
-    def _infer_unknown_attributes(self, feature_name: str) -> dict:
+    def _infer_unknown_attributes(self, feature_name: str) -> dict: # noqa ARG002
         return {
             'type': 'nominal'
         }