Update to Pydantic v2

batdata/schemas/__init__.py

@@ -17,27 +17,27 @@ class BatteryMetadata(BaseModel, extra=Extra.allow):
     """
 
     # Miscellaneous fields
-    name: str = Field(None, description="Name of the cell. Any format for the name is acceptable,"
-                                        " as it is intended to be used by the battery data provider.")
-    comments: str = Field(None, description="Long form comments describing the test")
+    name: Optional[str] = Field(None, description="Name of the cell. Any format for the name is acceptable,"
+                                                  " as it is intended to be used by the battery data provider.")
+    comments: Optional[str] = Field(None, description="Long form comments describing the test")
     version: str = Field(__version__, description="Version of this metadata")
 
     # Fields that describe the test protocol
-    cycler: str = Field(None, description='Name of the cycling machine')
-    start_date: date = Field(None, description="Date the initial test on the cell began")
-    set_temperature: float = Field(None, description="Set temperature for the battery testing equipment. Units: C")
-    schedule: str = Field(None, description="Schedule file used for the cycling machine")
+    cycler: Optional[str] = Field(None, description='Name of the cycling machine')
+    start_date: Optional[date] = Field(None, description="Date the initial test on the cell began")
+    set_temperature: Optional[float] = Field(None, description="Set temperature for the battery testing equipment. Units: C")
+    schedule: Optional[str] = Field(None, description="Schedule file used for the cycling machine")
 
     # Field that describe the battery assembly
     battery: Optional[BatteryDescription] = Field(None, description="Description of the battery being tested")
 
     # Fields that describe the source of data
-    source: str = Field(None, description="Organization who created this data")
-    dataset_name: str = Field(None, description="Name of a larger dataset this data is associated with")
-    authors: List[Tuple[str, str]] = Field(None, description="Name and affiliation of each of the authors of the data. First and last names")
-    associated_ids: List[AnyUrl] = Field(None, description="Any identifiers associated with this data file."
-                                                           " Identifiers can be any URI, such as DOIs of associated"
-                                                           " paper or HTTP addresses of associated websites")
+    source: Optional[str] = Field(None, description="Organization who created this data")
+    dataset_name: Optional[str] = Field(None, description="Name of a larger dataset this data is associated with")
+    authors: Optional[List[Tuple[str, str]]] = Field(None, description="Name and affiliation of each of the authors of the data. First and last names")
+    associated_ids: Optional[List[AnyUrl]] = Field(None, description="Any identifiers associated with this data file."
+                                                                     " Identifiers can be any URI, such as DOIs of associated"
+                                                                     " paper or HTTP addresses of associated websites")
 
     # Description of additional columns
     raw_data_columns: Dict[str, str] = Field(default_factory=dict, description='Descriptions of non-standard columns in the raw data')

batdata/schemas/cycling.py

@@ -87,7 +87,7 @@ def validate_dataframe(cls, data: DataFrame, allow_extra_columns: bool = True):
             # Get the data type for the column
             if '$ref' in col_schema['items']:
                 ref_name = col_schema['items']['$ref'].split("/")[-1]
-                col_type = schema['definitions'][ref_name]['type']
+                col_type = schema['$defs'][ref_name]['type']
             else:
                 col_type = col_schema['items']['type']
 
@@ -134,7 +134,7 @@ class RawData(ColumnSchema):
                                                     " or resting.")
     file_number: List[int] = Field(None, description="Used if test data is stored in multiple files. Number represents "
                                                      "the index of the file. All indices should be nonnegative and "
-                                                     "monotonically increasing", ge=0, monotonic=True)
+                                                     "monotonically increasing", monotonic=True)
     test_time: List[float] = Field(..., description="Time from the beginning of the cycling test. Times must be "
                                                     "nonnegative and monotonically increasing. Units: s",
                                    monotonic=True)

dev/README.md

@@ -0,0 +1,3 @@
+# Development Files
+
+Files useful to setting up a development environment

dev/environment.yml

@@ -0,0 +1,11 @@
+# Conda environment file
+name: batdata
+channels:
+  - defaults
+dependencies:
+  - python==3.9.*
+
+  # For now, use Pip for everything
+  - pip
+  - pip:
+    - -e ..[test]

pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "battery-data-toolkit"
-version = "0.1.1"
+version = "0.2.0"
 description = "Utilities for reading and manipulating battery testing data"
 readme = "README.md"
 requires-python = ">=3.9"
@@ -14,7 +14,7 @@ authors = [
 dependencies = [
     "pandas > 1.0",
     "scipy > 1.3",
-    "pydantic < 2",
+    "pydantic == 2.*",
     "tables > 3.6",
     "h5py == 3.*",
     "scythe-extractors >= 0.1",