use field default-factory for optional dict fields

CHANGELOG.md

@@ -20,6 +20,7 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 
 - correct chunk size estimate [\#59](https://github.com/mllam/mllam-data-prep/pull/59), @ealerskans
 - fix bug arising when variables provided to derived functions are renamed [\#56](https://github.com/mllam/mllam-data-prep/pull/56), @leifdenby
+- ensure config fields defaulting to `None` are typed as `Optional` and fields defaulting to `{}` are given a default-factory so that serialization with default values works correctly [\#63](https://github.com/mllam/mllam-data-prep/pull/63), @leifdenby
 
 ### Maintenance
 

mllam_data_prep/config.py

@@ -74,7 +74,7 @@ class Range:
 
     start: Union[str, int, float]
     end: Union[str, int, float]
-    step: Union[str, int, float] = None
+    step: Optional[Union[str, int, float]] = None
 
 
 @dataclass
@@ -93,7 +93,7 @@ class ValueSelection:
     """
 
     values: Union[List[Union[float, int]], Range]
-    units: str = None
+    units: Optional[str] = None
 
 
 @dataclass
@@ -177,7 +177,7 @@ class DimMapping:
     method: str
     dims: Optional[List[str]] = None
     dim: Optional[str] = None
-    name_format: str = field(default=None)
+    name_format: Optional[str] = field(default=None)
 
 
 @dataclass
@@ -273,7 +273,7 @@ class Split:
 
     start: str
     end: str
-    compute_statistics: Statistics = None
+    compute_statistics: Optional[Statistics] = None
 
 
 @dataclass
@@ -332,9 +332,9 @@ class Output:
     """
 
     variables: Dict[str, List[str]]
-    coord_ranges: Dict[str, Range] = None
+    coord_ranges: Dict[str, Range] = field(default_factory=dict)
     chunking: Dict[str, int] = field(default_factory=dict)
-    splitting: Splitting = None
+    splitting: Optional[Splitting] = None
 
 
 @dataclass
@@ -371,7 +371,7 @@ class Config(dataclass_wizard.JSONWizard, dataclass_wizard.YAMLWizard):
     inputs: Dict[str, InputDataset]
     schema_version: str
     dataset_version: str
-    extra: Dict[str, Any] = None
+    extra: Dict[str, Any] = field(default_factory=dict)
 
     def __post_init__(self):
         validate_config(self.inputs)

mllam_data_prep/create_dataset.py

@@ -126,7 +126,7 @@ def create_dataset(config: Config):
             f" {', '.join(SUPPORTED_CONFIG_VERSIONS)} are supported by mllam-data-prep "
             f"v{__version__}."
         )
-    if config.schema_version == "v0.2.0" and config.extra is not None:
+    if config.schema_version == "v0.2.0" and config.extra:
         raise ValueError(
             "Config schema version v0.2.0 does not support the `extra` field. Please "
             "update the schema version used in your config to v0.5.0."