⬆️ Upgrade black to 2023 major version

.pre-commit-config.yaml

@@ -1,10 +1,10 @@
 exclude: ^kedro_mlflow/template/project/run.py$
 repos:
     - repo: https://github.com/psf/black
-      rev: 22.12.0
+      rev: 23.7.0
       hooks:
           - id: black
-            language_version: python3.9
+            language_version: python3.10
     - repo: https://github.com/timothycrosley/isort
       rev: 5.12.0
       hooks:
@@ -21,7 +21,7 @@ repos:
       rev: v1.12.1
       hooks:
         - id: blacken-docs
-          additional_dependencies: [black==22.12.0]
+          additional_dependencies: [black==23.7.0]
     - repo: https://github.com/pre-commit/pre-commit-hooks
       rev: v4.4.0
       hooks:

kedro_mlflow/config/kedro_mlflow_config.py

@@ -103,7 +103,6 @@ class Config:
 
 
 class UiOptions(BaseModel):
-
     port: str = "5000"
     host: str = "127.0.0.1"
 

kedro_mlflow/framework/cli/cli.py

@@ -156,7 +156,6 @@ def ui(env: str, port: str, host: str):
         project_path=project_path,
         env=env,
     ) as session:
-
         context = session.load_context()
         host = host or context.mlflow.ui.host
         port = port or context.mlflow.ui.port

kedro_mlflow/framework/hooks/utils.py

@@ -6,7 +6,6 @@
 def _assert_mlflow_enabled(
     pipeline_name: str, mlflow_config: KedroMlflowConfig
 ) -> bool:
-
     # TODO: we may want to enable to filter on tags
     # but we need to deal with the case when several tags are passed
     # what to do if 1 out of 2 is in the list?

kedro_mlflow/io/artifacts/mlflow_artifact_dataset.py

@@ -20,7 +20,6 @@ def __new__(
         artifact_path: str = None,
         credentials: Dict[str, Any] = None,
     ):
-
         data_set, data_set_args = parse_dataset_definition(config=data_set)
 
         # fake inheritance : this mlflow class should be a mother class which wraps
@@ -47,7 +46,6 @@ def _logging_activated(self, flag):
                 self.__logging_activated = flag
 
             def _save(self, data: Any):
-
                 # _get_save_path needs to be called before super, otherwise
                 # it will throw exception that file under path already exist.
                 if hasattr(self, "_version"):

kedro_mlflow/io/models/mlflow_model_logger_dataset.py

@@ -69,11 +69,9 @@ def model_uri(self):
             run_id = mlflow.active_run().info.run_id
         if run_id is None:
             raise DataSetError(
-                (
-                    "To access the model_uri, you must either: "
-                    "\n -  specifiy 'run_id' "
-                    "\n - have an active run to retrieve data from"
-                )
+                "To access the model_uri, you must either: "
+                "\n -  specifiy 'run_id' "
+                "\n - have an active run to retrieve data from"
             )
 
         model_uri = f"runs:/{run_id}/{self._artifact_path}"
@@ -104,13 +102,11 @@ def _save(self, model: Any) -> None:
             if mlflow.active_run():
                 # it is not possible to log in a run which is not the current opened one
                 raise DataSetError(
-                    (
-                        "'run_id' cannot be specified"
-                        " if there is an mlflow active run."
-                        "Run_id mismatch: "
-                        f"\n - 'run_id'={self._run_id}"
-                        f"\n - active_run id={mlflow.active_run().info.run_id}"
-                    )
+                    "'run_id' cannot be specified"
+                    " if there is an mlflow active run."
+                    "Run_id mismatch: "
+                    f"\n - 'run_id'={self._run_id}"
+                    f"\n - active_run id={mlflow.active_run().info.run_id}"
                 )
             else:
                 # if the run id is specified and there is no opened run,
@@ -123,7 +119,6 @@ def _save(self, model: Any) -> None:
             self._save_model_in_run(model)
 
     def _save_model_in_run(self, model):
-
         if self._flavor == "mlflow.pyfunc":
             # PyFunc models utilise either `python_model` or `loader_module`
             # workflow. We we assign the passed `model` object to one of those keys

kedro_mlflow/io/models/mlflow_model_saver_dataset.py

@@ -22,7 +22,6 @@ def __init__(
         log_args: Dict[str, Any] = None,
         version: Version = None,
     ) -> None:
-
         """Initialize the Kedro MlflowModelDataSet.
 
         Parameters are passed from the Data Catalog.

kedro_mlflow/mlflow/kedro_pipeline_model.py

@@ -80,7 +80,6 @@ def copy_mode(self):
 
     @copy_mode.setter
     def copy_mode(self, copy_mode):
-
         if isinstance(copy_mode, str) or copy_mode is None:
             # if it is a string, we must create manually the dictionary
             # of all catalog entries with this copy_mode
@@ -105,7 +104,6 @@ def copy_mode(self, copy_mode):
             )
 
     def _extract_pipeline_catalog(self, catalog: DataCatalog) -> DataCatalog:
-
         sub_catalog = DataCatalog()
         for data_set_name in self.pipeline.inputs():
             if data_set_name == self.input_name:
@@ -137,18 +135,15 @@ def _extract_pipeline_catalog(self, catalog: DataCatalog) -> DataCatalog:
                     sub_catalog.add(data_set_name=data_set_name, data_set=data_set)
                 except KeyError:
                     raise KedroPipelineModelError(
-                        (
-                            f"The provided catalog must contains '{data_set_name}' data_set "
-                            "since it is the input of the pipeline."
-                        )
+                        f"The provided catalog must contains '{data_set_name}' data_set "
+                        "since it is the input of the pipeline."
                     )
 
         return sub_catalog
 
     def extract_pipeline_artifacts(
         self, parameters_saving_folder: Optional[Path] = None
     ):
-
         artifacts = {}
         for name, dataset in self.initial_catalog._data_sets.items():
             if name != self.input_name:
@@ -163,10 +158,8 @@ def extract_pipeline_artifacts(
                     persisted_dataset.save(dataset.load())
                     artifact_path = absolute_param_path.as_uri()
                     self._logger.info(
-                        (
-                            f"The parameter '{name[7:]}' is persisted (as pickle) "
-                            "at the following location: f'{artifact_path}'"
-                        )
+                        f"The parameter '{name[7:]}' is persisted (as pickle) "
+                        "at the following location: f'{artifact_path}'"
                     )
                 else:
                     # In this second case, we know it cannot be a MemoryDataSet
@@ -180,7 +173,6 @@ def extract_pipeline_artifacts(
         return artifacts
 
     def load_context(self, context):
-
         # a consistency check is made when loading the model
         # it would be better to check when saving the model
         # but we rely on a mlflow function for saving, and it is unaware of kedro
@@ -195,11 +187,9 @@ def load_context(self, context):
                 kedro_artifacts_keys - mlflow_artifacts_keys
             )
             raise ValueError(
-                (
-                    "Provided artifacts do not match catalog entries:"
-                    f"\n    - 'artifacts - inference.inputs()' = : {in_artifacts_but_not_inference}"
-                    f"\n    - 'inference.inputs() - artifacts' = : {in_inference_but_not_artifacts}"
-                )
+                "Provided artifacts do not match catalog entries:"
+                f"\n    - 'artifacts - inference.inputs()' = : {in_artifacts_but_not_inference}"
+                f"\n    - 'inference.inputs() - artifacts' = : {in_inference_but_not_artifacts}"
             )
 
         updated_catalog = self.initial_catalog.shallow_copy()
@@ -208,7 +198,6 @@ def load_context(self, context):
             self.loaded_catalog.save(name=name, data=updated_catalog.load(name))
 
     def predict(self, context, model_input):
-
         # we create an empty hook manager but do NOT register hooks
         # because we want this model be executable outside of a kedro project
         hook_manager = _create_hook_manager()

kedro_mlflow/pipeline/pipeline_ml.py

@@ -44,7 +44,6 @@ def __init__(
         kpm_kwargs: Optional[Dict[str, str]] = None,
         log_model_kwargs: Optional[Dict[str, str]] = None,
     ):
-
         """Store all necessary information for calling mlflow.log_model in the pipeline.
 
         Args:
@@ -110,10 +109,8 @@ def input_name(self, name: str) -> None:
         pp_allowed_names = "\n    - ".join(allowed_names)
         if name not in allowed_names:
             raise KedroMlflowPipelineMLError(
-                (
-                    f"input_name='{name}' but it must be an input of 'inference'"
-                    f", i.e. one of: \n    - {pp_allowed_names}"
-                )
+                f"input_name='{name}' but it must be an input of 'inference'"
+                f", i.e. one of: \n    - {pp_allowed_names}"
             )
         self._input_name = name
 
@@ -122,17 +119,14 @@ def _check_inference(self, inference: Pipeline) -> None:
         outputs_txt = "\n - ".join(inference.outputs())
         if len(inference.outputs()) != 1:
             raise KedroMlflowPipelineMLError(
-                (
-                    "The inference pipeline must have one"
-                    " and only one output. You are trying"
-                    " to set a inference pipeline with"
-                    f" '{nb_outputs}' output(s): \n - {outputs_txt}"
-                    " "
-                )
+                "The inference pipeline must have one"
+                " and only one output. You are trying"
+                " to set a inference pipeline with"
+                f" '{nb_outputs}' output(s): \n - {outputs_txt}"
+                " "
             )
 
     def _check_consistency(self) -> None:
-
         inference_parameters = {
             input for input in self.inference.inputs() if input.startswith("params:")
         }
@@ -148,14 +142,12 @@ def _check_consistency(self) -> None:
         if len(free_inputs_set) > 0:
             input_set_txt = "\n     - ".join(free_inputs_set)
             raise KedroMlflowPipelineMLError(
-                (
-                    "The following inputs are free for the inference pipeline:\n"
-                    f"    - {input_set_txt}."
-                    " \nNo free input is allowed."
-                    " Please make sure that 'inference.inputs()' are all"
-                    " in 'training.all_outputs() + training.inputs()'"
-                    "except 'input_name' and parameters which starts with 'params:'."
-                )
+                "The following inputs are free for the inference pipeline:\n"
+                f"    - {input_set_txt}."
+                " \nNo free input is allowed."
+                " Please make sure that 'inference.inputs()' are all"
+                " in 'training.all_outputs() + training.inputs()'"
+                "except 'input_name' and parameters which starts with 'params:'."
             )
 
         return None

setup.py

@@ -52,7 +52,7 @@ def _parse_requirements(path, encoding="utf-8"):
             "pytest-mock>=3.1.0, <4.0.0",
             "scikit-learn>=0.23.0, <1.3.0",
             "flake8==6.0.0",  # ensure consistency with pre-commit
-            "black==22.12.0",  # pin black version because it is not compatible with a pip range (because of non semver version number)
+            "black==23.7.0",  # pin black version because it is not compatible with a pip range (because of non semver version number)
             "isort==5.12.0",  # ensure consistency with pre-commit
         ],
         "dev": [

tests/config/test_kedro_mlflow_config.py

@@ -38,7 +38,6 @@ def test_kedro_mlflow_config_init():
 def test_kedro_mlflow_config_new_experiment_does_not_exists(
     kedro_project_with_mlflow_conf,
 ):
-
     config = KedroMlflowConfig(
         server=dict(mlflow_tracking_uri="mlruns"),
         tracking=dict(experiment=dict(name="exp1")),
@@ -57,7 +56,6 @@ def test_kedro_mlflow_config_new_experiment_does_not_exists(
 def test_kedro_mlflow_config_with_use_env_tracking_uri(
     kedro_project_with_mlflow_conf,
 ):
-
     os.environ["MLFLOW_TRACKING_URI"] = "my_mlruns"
 
     # default key server.mlflow_tracking_uri=None, so the environment variable will be used
@@ -72,7 +70,6 @@ def test_kedro_mlflow_config_with_use_env_tracking_uri(
 
 
 def test_kedro_mlflow_config_experiment_exists(kedro_project_with_mlflow_conf):
-
     # create an experiment with the same name
     mlflow_tracking_uri = (
         kedro_project_with_mlflow_conf / "conf" / "local" / "mlruns"
@@ -94,7 +91,6 @@ def test_kedro_mlflow_config_experiment_exists(kedro_project_with_mlflow_conf):
 
 
 def test_kedro_mlflow_config_experiment_was_deleted(kedro_project_with_mlflow_conf):
-
     # create an experiment with the same name and then delete it
     mlflow_tracking_uri = (kedro_project_with_mlflow_conf / "mlruns").as_uri()
     mlflow_client = MlflowClient(mlflow_tracking_uri)
@@ -122,7 +118,6 @@ def test_kedro_mlflow_config_experiment_was_deleted(kedro_project_with_mlflow_co
 def test_kedro_mlflow_config_setup_set_experiment_globally(
     kedro_project_with_mlflow_conf,
 ):
-
     mlflow_tracking_uri = (kedro_project_with_mlflow_conf / "mlruns").as_uri()
 
     # the config must restore properly the experiment
@@ -157,7 +152,6 @@ def test_kedro_mlflow_config_setup_set_experiment_globally(
 
 
 def test_kedro_mlflow_config_setup_set_tracking_uri(kedro_project_with_mlflow_conf):
-
     mlflow_tracking_uri = (kedro_project_with_mlflow_conf / "awesome_tracking").as_uri()
 
     config = KedroMlflowConfig(
@@ -174,7 +168,6 @@ def test_kedro_mlflow_config_setup_set_tracking_uri(kedro_project_with_mlflow_co
 
 
 def test_kedro_mlflow_config_setup_set_registry_uri(kedro_project_with_mlflow_conf):
-
     mlflow_registry_uri = (
         kedro_project_with_mlflow_conf / "awesome_registry.db"
     ).as_uri()
@@ -194,7 +187,6 @@ def test_kedro_mlflow_config_setup_set_registry_uri(kedro_project_with_mlflow_co
 
 
 def test_kedro_mlflow_config_setup_export_credentials(kedro_project_with_mlflow_conf):
-
     (kedro_project_with_mlflow_conf / "conf/base/credentials.yml").write_text(
         yaml.dump(dict(my_mlflow_creds=dict(fake_mlflow_cred="my_fake_cred")))
     )
@@ -244,23 +236,20 @@ def test_kedro_mlflow_config_setup_tracking_priority(kedro_project_with_mlflow_c
 
 
 def test_validate_uri_local_relative_path(kedro_project_with_mlflow_conf):
-
     validated_uri = _validate_uri(
         uri=r"mlruns", project_path=kedro_project_with_mlflow_conf
     )
     assert validated_uri == (kedro_project_with_mlflow_conf / "mlruns").as_uri()
 
 
 def test_validate_uri_local_absolute_posix(kedro_project_with_mlflow_conf, tmp_path):
-
     validated_uri = _validate_uri(
         uri=tmp_path.as_posix(), project_path=kedro_project_with_mlflow_conf
     )
     assert validated_uri == tmp_path.as_uri()
 
 
 def test_validate_uri_local_absolute_uri(kedro_project_with_mlflow_conf, tmp_path):
-
     validated_uri = _validate_uri(
         uri=tmp_path.as_uri(), project_path=kedro_project_with_mlflow_conf
     )

tests/framework/cli/test_cli.py

@@ -139,7 +139,6 @@ def test_cli_init_existing_config_force_option(
 
     bootstrap_project(kedro_project)
     with KedroSession.create(project_path=kedro_project) as session:
-
         # emulate first call by writing a mlflow.yml file
         yaml_str = yaml.dump(dict(server=dict(mlflow_tracking_uri="toto")))
         (
@@ -197,7 +196,6 @@ def test_cli_init_with_wrong_env(monkeypatch, kedro_project, env):
 # other solution is to use pytest-xprocess
 # TODO: create an initlaized_kedro_project fixture with a global scope
 def test_ui_is_up(monkeypatch, mocker, kedro_project_with_mlflow_conf):
-
     monkeypatch.chdir(kedro_project_with_mlflow_conf)
     cli_runner = CliRunner()
 
@@ -233,7 +231,6 @@ def test_ui_is_up(monkeypatch, mocker, kedro_project_with_mlflow_conf):
 def test_ui_overwrite_conf_at_runtime(
     monkeypatch, mocker, kedro_project_with_mlflow_conf
 ):
-
     monkeypatch.chdir(kedro_project_with_mlflow_conf)
     cli_runner = CliRunner()
 
@@ -257,7 +254,6 @@ def test_ui_overwrite_conf_at_runtime(
 
 
 def test_ui_open_http_uri(monkeypatch, mocker, tmp_path):
-
     config = {
         "output_dir": tmp_path,
         "kedro_version": kedro_version,