dataframely 1.2.0__tar.gz → 1.2.1__tar.gz

{dataframely-1.2.0 → dataframely-1.2.1}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: dataframely
-Version: 1.2.0
+Version: 1.2.1
 Classifier: Programming Language :: Python :: 3
 Classifier: Programming Language :: Python :: 3.11
 Classifier: Programming Language :: Python :: 3.12

{dataframely-1.2.0 → dataframely-1.2.1}/dataframely/_rule.py

@@ -126,5 +126,7 @@ def _with_group_rules(lf: pl.LazyFrame, rules: dict[str, GroupRule]) -> pl.LazyF
     #    preserves the order of the left data frame.
     result = lf
     for group_columns, frame in group_evaluations.items():
-        result = result.join(frame, on=list(group_columns), how="left")
+        result = result.join(
+            frame, on=list(group_columns), how="left", nulls_equal=True
+        )
     return result

{dataframely-1.2.0 → dataframely-1.2.1}/dataframely/columns/enum.py

@@ -49,7 +49,7 @@ class Enum(Column):
             alias=alias,
             metadata=metadata,
         )
-        self.categories = categories
+        self.categories = list(categories)
 
     @property
     def dtype(self) -> pl.DataType:

{dataframely-1.2.0 → dataframely-1.2.1}/pyproject.toml

@@ -19,7 +19,7 @@ description = "A declarative, polars-native data frame validation library"
 name = "dataframely"
 readme = "README.md"
 requires-python = ">=3.11"
-version = "1.2.0"
+version = "1.2.1"
 
 [project.urls]
 Repository = "https://github.com/quantco/dataframely"

{dataframely-1.2.0 → dataframely-1.2.1}/tests/column_types/test_enum.py

@@ -52,3 +52,12 @@ def test_valid_cast(
     schema = create_schema("test", {"a": enum})
     df = df_type(data)
     assert schema.is_valid(df, cast=True) == valid
+
+
+@pytest.mark.parametrize("type1", [list, tuple])
+@pytest.mark.parametrize("type2", [list, tuple])
+def test_different_sequences(type1: type, type2: type) -> None:
+    allowed = ["a", "b"]
+    S = create_schema("test", {"x": dy.Enum(type1(allowed))})
+    df = pl.DataFrame({"x": pl.Series(["a", "b"], dtype=pl.Enum(type2(allowed)))})
+    S.validate(df)

{dataframely-1.2.0 → dataframely-1.2.1}/tests/schema/test_validate.py

@@ -116,3 +116,12 @@ def test_success_multi_row_strip_cast(
     )
     assert_frame_equal(actual, expected)
     assert MySchema.is_valid(df, cast=True)
+
+
+@pytest.mark.parametrize("df_type", [pl.DataFrame, pl.LazyFrame])
+def test_group_rule_on_nulls(df_type: type[pl.DataFrame] | type[pl.LazyFrame]) -> None:
+    # The schema is violated because we have multiple "b" values for the same "a" value
+    df = df_type({"a": [None, None], "b": [1, 2]})
+    with pytest.raises(RuleValidationError):
+        MyComplexSchema.validate(df, cast=True)
+    assert not MyComplexSchema.is_valid(df, cast=True)