dataframely 1.12.0__tar.gz → 1.12.1__tar.gz

{dataframely-1.12.0 → dataframely-1.12.1}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: dataframely
-Version: 1.12.0
+Version: 1.12.1
 Classifier: Programming Language :: Python :: 3
 Classifier: Programming Language :: Python :: 3.10
 Classifier: Programming Language :: Python :: 3.11

{dataframely-1.12.0 → dataframely-1.12.1}/dataframely/columns/_base.py

@@ -381,15 +381,6 @@ class Column(ABC):
         if name == "check":
             return _compare_checks(lhs, rhs, column_expr)
 
-        lhs_is_series = isinstance(lhs, pl.Series)
-        rhs_is_series = isinstance(rhs, pl.Series)
-
-        if lhs_is_series != rhs_is_series:
-            return False
-
-        if lhs_is_series and rhs_is_series:
-            return _compare_series(lhs, rhs)
-
         return lhs == rhs
 
     # -------------------------------- DUNDER METHODS -------------------------------- #
@@ -413,10 +404,6 @@ class Column(ABC):
         return self.__class__.__name__.lower()
 
 
-def _compare_series(lhs: pl.Series, rhs: pl.Series) -> bool:
-    return (len(lhs) == len(rhs)) and lhs.equals(rhs)
-
-
 def _compare_checks(lhs: Check | None, rhs: Check | None, expr: pl.Expr) -> bool:
     match (lhs, rhs):
         case (None, None):

{dataframely-1.12.0 → dataframely-1.12.1}/dataframely/columns/enum.py

@@ -67,12 +67,8 @@ class Enum(Column):
             metadata=metadata,
         )
         if isclass(categories) and issubclass(categories, enum.Enum):
-            categories = pl.Series(
-                values=[getattr(v, "value", v) for v in categories.__members__.values()]
-            )
-        elif not isinstance(categories, pl.Series):
-            categories = pl.Series(values=categories)
-        self.categories = categories
+            categories = (item.value for item in categories)
+        self.categories = list(categories)
 
     @property
     def dtype(self) -> pl.DataType:
@@ -81,7 +77,7 @@ class Enum(Column):
     def validate_dtype(self, dtype: PolarsDataType) -> bool:
         if not isinstance(dtype, pl.Enum):
             return False
-        return self.categories.equals(dtype.categories)
+        return self.categories == dtype.categories.to_list()
 
     def sqlalchemy_dtype(self, dialect: sa.Dialect) -> sa_TypeEngine:
         category_lengths = [len(c) for c in self.categories]
@@ -102,6 +98,6 @@ class Enum(Column):
     def _sample_unchecked(self, generator: Generator, n: int) -> pl.Series:
         return generator.sample_choice(
             n,
-            choices=self.categories.to_list(),
+            choices=self.categories,
             null_probability=self._null_probability,
         ).cast(self.dtype)

{dataframely-1.12.0 → dataframely-1.12.1}/pyproject.toml

@@ -25,7 +25,7 @@ description = "A declarative, polars-native data frame validation library"
 name = "dataframely"
 readme = "README.md"
 requires-python = ">=3.10"
-version = "1.12.0"
+version = "1.12.1"
 
 [project.optional-dependencies]
 deltalake = ["deltalake"]

{dataframely-1.12.0 → dataframely-1.12.1}/tests/schema/test_repr.py

@@ -52,3 +52,14 @@ def test_repr_with_rules() -> None:
             - "my_rule": [(col("a")) < (dyn int: 100)]
             - "my_group_rule": [(col("a").sum()) > (dyn int: 50)] grouped by ['a']
         """)
+
+
+def test_repr_enum() -> None:
+    class SchemaNoRules(dy.Schema):
+        a = dy.Enum(["a"])
+
+    assert repr(SchemaNoRules) == textwrap.dedent("""\
+        [Schema "SchemaNoRules"]
+          Columns:
+            - "a": Enum(categories=['a'], nullable=True)
+        """)

{dataframely-1.12.0 → dataframely-1.12.1}/tests/schema/test_serialization.py

@@ -40,6 +40,7 @@ def test_simple_serialization() -> None:
         create_schema("test", {"a": dy.Int64(check=[lambda expr: expr > 5])}),
         create_schema("test", {"a": dy.Int64(check={"x": lambda expr: expr > 5})}),
         create_schema("test", {"a": dy.Int64(alias="foo")}),
+        create_schema("test", {"a": dy.Enum(["a"])}),
         create_schema("test", {"a": dy.Decimal(scale=2, min=Decimal("1.5"))}),
         create_schema("test", {"a": dy.Date(min=dt.date(2020, 1, 1))}),
         create_schema("test", {"a": dy.Datetime(min=dt.datetime(2020, 1, 1))}),