valediction 1.0.3__tar.gz → 1.1.0__tar.gz

{valediction-1.0.3 → valediction-1.1.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: valediction
-Version: 1.0.3
+Version: 1.1.0
 Summary: Valediction is a convenience data validation package that allows generation, import, and constraint enforcement of user-defined data dictionaries against datasets.
 Author-email: Cai Davis <Cai.Davis@uhs.nhs.uk>
 Requires-Python: <4.0,>=3.11

{valediction-1.0.3 → valediction-1.1.0}/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "valediction"
-version = "1.0.3"
+version = "1.1.0"
 description = "Valediction is a convenience data validation package that allows generation, import, and constraint enforcement of user-defined data dictionaries against datasets."
 authors = [{ name = "Cai Davis", email = "Cai.Davis@uhs.nhs.uk" }]
 requires-python = ">=3.11,<4.0"

{valediction-1.0.3 → valediction-1.1.0}/src/valediction/convenience.py

@@ -3,12 +3,11 @@ from pathlib import Path
 from pandas import DataFrame
 
 from valediction.datasets.datasets import Dataset
-from valediction.dictionary.importing import import_dictionary
 from valediction.dictionary.model import Dictionary
 
 
 def validate(
-    data: str | Path | dict[str, DataFrame] | Dictionary,
+    dataset: str | Path | dict[str, DataFrame],
     dictionary: Dictionary | str | Path,
     *,
     import_data: bool = False,
@@ -31,20 +30,16 @@ def validate(
     Returns:
         Dataset: dataset, with or without Issues
     """
-    dictionary = (
-        dictionary
-        if isinstance(dictionary, Dictionary)
-        else import_dictionary(dictionary)
-    )
-    data: Dataset = Dataset.create_from(data)
-    data.import_dictionary(dictionary)
+
+    _dataset: Dataset = Dataset.create_from(dataset)
+    _dataset.import_dictionary(dictionary)
 
     if import_data:
-        data.import_data()
+        _dataset.import_data()
 
-    data.validate(
+    _dataset.validate(
         chunk_size=chunk_size,
         feedback=feedback,
     )
 
-    return data
+    return _dataset

{valediction-1.0.3 → valediction-1.1.0}/src/valediction/datasets/datasets.py

@@ -135,16 +135,16 @@ class DatasetItem:
     # Validation
     def validate(
         self,
-        chunk_size: int = None,
+        chunk_size: int | None = 10_000_000,
         feedback: bool = True,
-    ):
+    ) -> None:
         """
         Summary:
             Validates the dataset item against the dictionary.
             Warns if there are issues with the integrity of the data.
 
         Arguments:
-            chunk_size (int): Size of chunks for validating data to optimise RAM usage,
+            chunk_size (int | None): Size of chunks for validating data to optimise RAM usage,
                 if reading from CSV (default: 10_000_000)
             feedback (bool): Provide user feedback on progress (default: True)
 
@@ -710,7 +710,7 @@ class Dataset(list[DatasetItem]):
     # Validation
     def validate(
         self,
-        chunk_size: int = None,
+        chunk_size: int | None = 10_000_000,
         feedback: bool = True,
     ) -> None:
         """
@@ -751,7 +751,7 @@ class Dataset(list[DatasetItem]):
         if feedback:
             print("\n", end="")
 
-    def __reattach_issues(self):
+    def __reattach_issues(self) -> None:
         self.issues = Issues()
         for item in self:
             self.issues.extend(item.issues)

{valediction-1.0.3 → valediction-1.1.0}/src/valediction/validation/validation.py

@@ -62,7 +62,7 @@ class Validator:
         dataset_item: DatasetItemLike,
         table_dictionary: Table,
         feedback: bool = True,
-        chunk_size: int = 10_000_000,
+        chunk_size: int | None = 10_000_000,
         _padding: int = 0,
     ):
         # User Variables