dycw-utilities 0.155.1__tar.gz → 0.155.3__tar.gz

{dycw_utilities-0.155.1 → dycw_utilities-0.155.3}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: dycw-utilities
-Version: 0.155.1
+Version: 0.155.3
 Author-email: Derek Wan <d.wan@icloud.com>
 License-File: LICENSE
 Requires-Python: >=3.12

{dycw_utilities-0.155.1 → dycw_utilities-0.155.3}/pyproject.toml

@@ -227,7 +227,7 @@ dependencies = [
 name = "dycw-utilities"
 readme = "README.md"
 requires-python = ">= 3.12"
-version = "0.155.1"
+version = "0.155.3"
 
 [project.entry-points.pytest11]
 pytest-randomly = "utilities.pytest_plugins.pytest_randomly"
@@ -259,7 +259,7 @@ test = [
 # bump-my-version
 [tool.bumpversion]
 allow_dirty = true
-current_version = "0.155.1"
+current_version = "0.155.3"
 
 [[tool.bumpversion.files]]
 filename = "src/utilities/__init__.py"

{dycw_utilities-0.155.1 → dycw_utilities-0.155.3}/src/tests/test_altair.py

@@ -28,7 +28,7 @@ from utilities.altair import (
 )
 from utilities.functions import ensure_class
 from utilities.hypothesis import dates, text_ascii, zoned_date_times
-from utilities.polars import DatetimeUTC, zoned_datetime_dtype
+from utilities.polars import DatetimeUTC, zoned_date_time_dtype
 from utilities.tzdata import HongKong, Tokyo
 from utilities.whenever import get_now
 from utilities.zoneinfo import UTC
@@ -98,7 +98,7 @@ class TestPlotDataFrames:
         df = DataFrame(
             data=[(dt.datetime(2000, 1, 1, 12, tzinfo=time_zone), 0.0)],
             schema={
-                "datetime": zoned_datetime_dtype(time_zone=time_zone),
+                "datetime": zoned_date_time_dtype(time_zone=time_zone),
                 "value": Float64,
             },
             orient="row",

{dycw_utilities-0.155.1 → dycw_utilities-0.155.3}/src/tests/test_orjson.py

@@ -81,7 +81,7 @@ from utilities.orjson import (
     serialize,
     write_object,
 )
-from utilities.polars import check_polars_dataframe, zoned_datetime_dtype
+from utilities.polars import check_polars_dataframe, zoned_date_time_dtype
 from utilities.sentinel import Sentinel, sentinel
 from utilities.types import LogLevel, MaybeIterable, PathLike
 from utilities.typing import get_args
@@ -176,7 +176,7 @@ class TestGetLogRecords:
                 "level": UInt64,
                 "path_name": String,
                 "line_num": UInt64,
-                "datetime": zoned_datetime_dtype(time_zone=LOCAL_TIME_ZONE),
+                "datetime": zoned_date_time_dtype(time_zone=LOCAL_TIME_ZONE),
                 "func_name": String,
                 "stack_info": String,
                 "extra": Object,

{dycw_utilities-0.155.1 → dycw_utilities-0.155.3}/src/tests/test_polars.py

@@ -48,7 +48,6 @@ from polars import (
     col,
     concat,
     date_range,
-    datetime_range,
     int_range,
     lit,
     struct,
@@ -63,6 +62,7 @@ import tests.test_math
 import utilities.polars
 from utilities.hypothesis import (
     date_deltas,
+    date_periods,
     date_time_deltas,
     dates,
     float64s,
@@ -72,7 +72,9 @@ from utilities.hypothesis import (
     temp_paths,
     text_ascii,
     time_deltas,
+    time_periods,
     times,
+    zoned_date_time_periods,
     zoned_date_times,
 )
 from utilities.math import number_of_decimals
@@ -82,6 +84,7 @@ from utilities.polars import (
     AppendDataClassError,
     BooleanValueCountsError,
     ColumnsToDictError,
+    DatePeriodDType,
     DatetimeHongKong,
     DatetimeTokyo,
     DatetimeUSCentral,
@@ -95,7 +98,7 @@ from utilities.polars import (
     IsNotNullStructSeriesError,
     IsNullStructSeriesError,
     SetFirstRowAsColumnsError,
-    StructFromDataClassError,
+    TimePeriodDType,
     _check_polars_dataframe_predicates,
     _check_polars_dataframe_schema_list,
     _check_polars_dataframe_schema_set,
@@ -134,6 +137,8 @@ from utilities.polars import (
     _reconstruct_schema,
     _ReifyExprsEmptyError,
     _ReifyExprsSeriesNonUniqueError,
+    _StructFromDataClassNotADataclassError,
+    _StructFromDataClassTypeError,
     ac_halflife,
     acf,
     adjust_frequencies,
@@ -145,7 +150,6 @@ from utilities.polars import (
     are_frames_equal,
     bernoulli,
     boolean_value_counts,
-    ceil_datetime,
     check_polars_dataframe,
     choice,
     collect_series,
@@ -164,7 +168,6 @@ from utilities.polars import (
     ensure_expr_or_series,
     ensure_expr_or_series_many,
     finite_ewm_mean,
-    floor_datetime,
     get_data_type_or_series_time_zone,
     get_expr_name,
     get_frequency_spectrum,
@@ -202,8 +205,8 @@ from utilities.polars import (
     week_num,
     write_dataframe,
     write_series,
-    zoned_datetime_dtype,
-    zoned_datetime_period_dtype,
+    zoned_date_time_dtype,
+    zoned_date_time_period_dtype,
 )
 from utilities.sentinel import Sentinel, sentinel
 from utilities.tzdata import HongKong, Tokyo, USCentral, USEastern
@@ -532,44 +535,6 @@ class TestBooleanValueCounts:
             _ = boolean_value_counts(self.df, col("x").cast(Int64).alias("z"))
 
 
-class TestCeilDateTime:
-    start: ClassVar[dt.datetime] = dt.datetime(2000, 1, 1, 0, 0, tzinfo=UTC)
-    end: ClassVar[dt.datetime] = dt.datetime(2000, 1, 1, 0, 3, tzinfo=UTC)
-    expected: ClassVar[Series] = Series(
-        values=[
-            dt.datetime(2000, 1, 1, 0, 0, tzinfo=UTC),
-            dt.datetime(2000, 1, 1, 0, 1, tzinfo=UTC),
-            dt.datetime(2000, 1, 1, 0, 1, tzinfo=UTC),
-            dt.datetime(2000, 1, 1, 0, 1, tzinfo=UTC),
-            dt.datetime(2000, 1, 1, 0, 1, tzinfo=UTC),
-            dt.datetime(2000, 1, 1, 0, 1, tzinfo=UTC),
-            dt.datetime(2000, 1, 1, 0, 1, tzinfo=UTC),
-            dt.datetime(2000, 1, 1, 0, 2, tzinfo=UTC),
-            dt.datetime(2000, 1, 1, 0, 2, tzinfo=UTC),
-            dt.datetime(2000, 1, 1, 0, 2, tzinfo=UTC),
-            dt.datetime(2000, 1, 1, 0, 2, tzinfo=UTC),
-            dt.datetime(2000, 1, 1, 0, 2, tzinfo=UTC),
-            dt.datetime(2000, 1, 1, 0, 2, tzinfo=UTC),
-            dt.datetime(2000, 1, 1, 0, 3, tzinfo=UTC),
-            dt.datetime(2000, 1, 1, 0, 3, tzinfo=UTC),
-            dt.datetime(2000, 1, 1, 0, 3, tzinfo=UTC),
-            dt.datetime(2000, 1, 1, 0, 3, tzinfo=UTC),
-            dt.datetime(2000, 1, 1, 0, 3, tzinfo=UTC),
-            dt.datetime(2000, 1, 1, 0, 3, tzinfo=UTC),
-        ]
-    )
-
-    def test_expr(self) -> None:
-        data = datetime_range(self.start, self.end, interval="10s")
-        result = collect_series(ceil_datetime(data, "1m"))
-        assert_series_equal(result, self.expected, check_names=False)
-
-    def test_series(self) -> None:
-        data = datetime_range(self.start, self.end, interval="10s", eager=True)
-        result = ceil_datetime(data, "1m")
-        assert_series_equal(result, self.expected, check_names=False)
-
-
 class TestCheckPolarsDataFrame:
     def test_main(self) -> None:
         df = DataFrame()
@@ -1054,6 +1019,16 @@ class TestDataClassToDataFrame:
         df = dataclass_to_dataframe(objs)
         check_polars_dataframe(df, height=len(objs), schema_list={"x": Duration})
 
+    @given(data=data())
+    def test_date_period(self, *, data: DataObject) -> None:
+        @dataclass(kw_only=True, slots=True)
+        class Example:
+            x: DatePeriod
+
+        objs = data.draw(lists(builds(Example, x=date_periods()), min_size=1))
+        df = dataclass_to_dataframe(objs, globalns=globals())
+        check_polars_dataframe(df, height=len(objs), schema_list={"x": DatePeriodDType})
+
     @given(data=data())
     def test_date_time_delta(self, *, data: DataObject) -> None:
         @dataclass(kw_only=True, slots=True)
@@ -1066,6 +1041,23 @@ class TestDataClassToDataFrame:
         df = dataclass_to_dataframe(objs)
         check_polars_dataframe(df, height=len(objs), schema_list={"x": Duration})
 
+    @given(data=data())
+    def test_multiple_periods(self, *, data: DataObject) -> None:
+        @dataclass(kw_only=True, slots=True)
+        class Example:
+            x: DatePeriod
+            y: DatePeriod
+
+        objs = data.draw(
+            lists(builds(Example, x=date_periods(), y=date_periods()), min_size=1)
+        )
+        df = dataclass_to_dataframe(objs, globalns=globals())
+        check_polars_dataframe(
+            df,
+            height=len(objs),
+            schema_list={"x": DatePeriodDType, "y": DatePeriodDType},
+        )
+
     @given(data=data())
     def test_nested(self, *, data: DataObject) -> None:
         @dataclass(kw_only=True, slots=True)
@@ -1112,6 +1104,16 @@ class TestDataClassToDataFrame:
         df = dataclass_to_dataframe(objs)
         check_polars_dataframe(df, height=len(objs), schema_list={"x": Duration})
 
+    @given(data=data())
+    def test_time_period(self, *, data: DataObject) -> None:
+        @dataclass(kw_only=True, slots=True)
+        class Example:
+            x: TimePeriod
+
+        objs = data.draw(lists(builds(Example, x=time_periods()), min_size=1))
+        df = dataclass_to_dataframe(objs, globalns=globals())
+        check_polars_dataframe(df, height=len(objs), schema_list={"x": TimePeriodDType})
+
     @given(data=data())
     def test_uuid(self, *, data: DataObject) -> None:
         @dataclass(kw_only=True, slots=True)
@@ -1131,7 +1133,21 @@ class TestDataClassToDataFrame:
         objs = data.draw(lists(builds(Example, x=zoned_date_times()), min_size=1))
         df = dataclass_to_dataframe(objs, localns=locals())
         check_polars_dataframe(
-            df, height=len(objs), schema_list={"x": zoned_datetime_dtype()}
+            df, height=len(objs), schema_list={"x": zoned_date_time_dtype()}
+        )
+
+    @given(data=data())
+    def test_zoned_datetime_period(self, *, data: DataObject) -> None:
+        @dataclass(kw_only=True, slots=True)
+        class Example:
+            x: ZonedDateTimePeriod
+
+        objs = data.draw(
+            lists(builds(Example, x=zoned_date_time_periods()), min_size=1)
+        )
+        df = dataclass_to_dataframe(objs, globalns=globals())
+        check_polars_dataframe(
+            df, height=len(objs), schema_list={"x": zoned_date_time_period_dtype()}
         )
 
     def test_error_empty(self) -> None:
@@ -1565,44 +1581,6 @@ class TestFiniteEWMWeights:
             _ = _finite_ewm_weights(min_weight=1.0)
 
 
-class TestFloorDateTime:
-    start: ClassVar[dt.datetime] = dt.datetime(2000, 1, 1, 0, 0, tzinfo=UTC)
-    end: ClassVar[dt.datetime] = dt.datetime(2000, 1, 1, 0, 3, tzinfo=UTC)
-    expected: ClassVar[Series] = Series(
-        values=[
-            dt.datetime(2000, 1, 1, 0, 0, tzinfo=UTC),
-            dt.datetime(2000, 1, 1, 0, 0, tzinfo=UTC),
-            dt.datetime(2000, 1, 1, 0, 0, tzinfo=UTC),
-            dt.datetime(2000, 1, 1, 0, 0, tzinfo=UTC),
-            dt.datetime(2000, 1, 1, 0, 0, tzinfo=UTC),
-            dt.datetime(2000, 1, 1, 0, 0, tzinfo=UTC),
-            dt.datetime(2000, 1, 1, 0, 1, tzinfo=UTC),
-            dt.datetime(2000, 1, 1, 0, 1, tzinfo=UTC),
-            dt.datetime(2000, 1, 1, 0, 1, tzinfo=UTC),
-            dt.datetime(2000, 1, 1, 0, 1, tzinfo=UTC),
-            dt.datetime(2000, 1, 1, 0, 1, tzinfo=UTC),
-            dt.datetime(2000, 1, 1, 0, 1, tzinfo=UTC),
-            dt.datetime(2000, 1, 1, 0, 2, tzinfo=UTC),
-            dt.datetime(2000, 1, 1, 0, 2, tzinfo=UTC),
-            dt.datetime(2000, 1, 1, 0, 2, tzinfo=UTC),
-            dt.datetime(2000, 1, 1, 0, 2, tzinfo=UTC),
-            dt.datetime(2000, 1, 1, 0, 2, tzinfo=UTC),
-            dt.datetime(2000, 1, 1, 0, 2, tzinfo=UTC),
-            dt.datetime(2000, 1, 1, 0, 3, tzinfo=UTC),
-        ]
-    )
-
-    def test_expr(self) -> None:
-        data = datetime_range(self.start, self.end, interval="10s")
-        result = collect_series(floor_datetime(data, "1m"))
-        assert_series_equal(result, self.expected, check_names=False)
-
-    def test_series(self) -> None:
-        data = datetime_range(self.start, self.end, interval="10s", eager=True)
-        result = floor_datetime(data, "1m")
-        assert_series_equal(result, self.expected, check_names=False)
-
-
 class TestGetDataTypeOrSeriesTimeZone:
     @given(
         time_zone=sampled_from([HongKong, UTC]),
@@ -1618,9 +1596,9 @@ class TestGetDataTypeOrSeriesTimeZone:
     ) -> None:
         match flat_or_struct:
             case "flat":
-                dtype = zoned_datetime_dtype(time_zone=time_zone)
+                dtype = zoned_date_time_dtype(time_zone=time_zone)
             case "struct":
-                dtype = zoned_datetime_period_dtype(time_zone=time_zone)
+                dtype = zoned_date_time_period_dtype(time_zone=time_zone)
             case never:
                 assert_never(never)
         match dtype_or_series:
@@ -2369,7 +2347,7 @@ class TestPeriodRange:
     def test_main(self, *, end_or_length: ZonedDateTime | int) -> None:
         rng = period_range(self.start, end_or_length, interval="1h", eager=True)
         assert len(rng) == 3
-        assert rng.dtype == zoned_datetime_period_dtype()
+        assert rng.dtype == zoned_date_time_period_dtype()
         assert rng[0]["start"] == self.start.py_datetime()
         assert rng[-1]["end"] == self.end.py_datetime()
 
@@ -2626,15 +2604,6 @@ class TestStructFromDataClass:
         })
         assert result == expected
 
-    def test_datetime(self) -> None:
-        @dataclass(kw_only=True, slots=True)
-        class Example:
-            field: dt.datetime
-
-        result = struct_from_dataclass(Example, time_zone=UTC, globalns=globals())
-        expected = Struct({"field": DatetimeUTC})
-        assert result == expected
-
     def test_enum(self) -> None:
         class Truth(enum.Enum):
             true = auto()
@@ -2715,25 +2684,18 @@ class TestStructFromDataClass:
 
     def test_not_a_dataclass_error(self) -> None:
         with raises(
-            StructFromDataClassError, match="Object must be a dataclass; got None"
+            _StructFromDataClassNotADataclassError,
+            match="Object must be a dataclass; got None",
         ):
             _ = struct_from_dataclass(cast("Any", None))
 
-    def test_missing_time_zone_error(self) -> None:
-        @dataclass(kw_only=True, slots=True)
-        class Example:
-            field: dt.datetime
-
-        with raises(StructFromDataClassError, match="Time-zone must be given"):
-            _ = struct_from_dataclass(Example, globalns=globals())
-
     def test_missing_type_error(self) -> None:
         @dataclass(kw_only=True, slots=True)
         class Example:
             field: None
 
         with raises(
-            StructFromDataClassError, match="Unsupported type: <class 'NoneType'>"
+            _StructFromDataClassTypeError, match="Unsupported type: <class 'NoneType'>"
         ):
             _ = struct_from_dataclass(Example)
 
@@ -3043,7 +3005,7 @@ class TestWeekNum:
 
 class TestZonedDateTimeDType:
     def test_main(self) -> None:
-        dtype = zoned_datetime_dtype(time_zone=UTC)
+        dtype = zoned_date_time_dtype(time_zone=UTC)
         assert isinstance(dtype, Datetime)
         assert dtype.time_zone is not None
 
@@ -3051,5 +3013,5 @@ class TestZonedDateTimeDType:
 class TestZonedDateTimePeriodDType:
     @given(time_zone=sampled_from([UTC, (UTC, UTC)]))
     def test_main(self, *, time_zone: ZoneInfo | tuple[ZoneInfo, ZoneInfo]) -> None:
-        dtype = zoned_datetime_period_dtype(time_zone=time_zone)
+        dtype = zoned_date_time_period_dtype(time_zone=time_zone)
         assert isinstance(dtype, Struct)

{dycw_utilities-0.155.1 → dycw_utilities-0.155.3}/src/utilities/__init__.py

@@ -1,3 +1,3 @@
 from __future__ import annotations
 
-__version__ = "0.155.1"
+__version__ = "0.155.3"

{dycw_utilities-0.155.1 → dycw_utilities-0.155.3}/src/utilities/polars.py

@@ -1,6 +1,5 @@
 from __future__ import annotations
 
-import datetime as dt
 import enum
 from collections.abc import Callable, Iterator, Sequence
 from collections.abc import Set as AbstractSet
@@ -136,6 +135,10 @@ DatetimeTokyo = Datetime(time_zone="Asia/Tokyo")
 DatetimeUSCentral = Datetime(time_zone="US/Central")
 DatetimeUSEastern = Datetime(time_zone="US/Eastern")
 DatetimeUTC = Datetime(time_zone="UTC")
+DatePeriodDType = Struct({"start": pl.Date, "end": pl.Date})
+TimePeriodDType = Struct({"start": pl.Time, "end": pl.Time})
+
+
 _FINITE_EWM_MIN_WEIGHT = 0.9999
 
 
@@ -458,29 +461,6 @@ class BooleanValueCountsError(Exception):
 ##
 
 
-@overload
-def ceil_datetime(column: ExprLike, every: ExprLike, /) -> Expr: ...
-@overload
-def ceil_datetime(column: Series, every: ExprLike, /) -> Series: ...
-@overload
-def ceil_datetime(column: IntoExprColumn, every: ExprLike, /) -> ExprOrSeries: ...
-def ceil_datetime(column: IntoExprColumn, every: ExprLike, /) -> ExprOrSeries:
-    """Compute the `ceil` of a datetime column."""
-    column = ensure_expr_or_series(column)
-    rounded = column.dt.round(every)
-    ceil = (
-        when(column <= rounded)
-        .then(rounded)
-        .otherwise(column.dt.offset_by(every).dt.round(every))
-    )
-    if isinstance(column, Expr):
-        return ceil
-    return DataFrame().with_columns(ceil.alias(column.name))[column.name]
-
-
-##
-
-
 def check_polars_dataframe(
     df: DataFrame,
     /,
@@ -1056,37 +1036,41 @@ def dataclass_to_dataframe(
 
 
 def _dataclass_to_dataframe_cast(series: Series, /) -> Series:
-    if series.dtype == Object:
-        if series.map_elements(
-            make_isinstance(whenever.Date), return_dtype=Boolean
-        ).all():
-            return series.map_elements(lambda x: x.py_date(), return_dtype=pl.Date)
-        if series.map_elements(make_isinstance(DateDelta), return_dtype=Boolean).all():
-            return series.map_elements(to_py_time_delta, return_dtype=Duration)
-        if series.map_elements(
-            make_isinstance(DateTimeDelta), return_dtype=Boolean
-        ).all():
-            return series.map_elements(to_py_time_delta, return_dtype=Duration)
-        is_path = series.map_elements(make_isinstance(Path), return_dtype=Boolean).all()
-        is_uuid = series.map_elements(make_isinstance(UUID), return_dtype=Boolean).all()
-        if is_path or is_uuid:
-            with suppress_warnings(category=PolarsInefficientMapWarning):
-                return series.map_elements(str, return_dtype=String)
-        if series.map_elements(
-            make_isinstance(whenever.Time), return_dtype=Boolean
-        ).all():
-            return series.map_elements(lambda x: x.py_time(), return_dtype=pl.Time)
-        if series.map_elements(make_isinstance(TimeDelta), return_dtype=Boolean).all():
-            return series.map_elements(to_py_time_delta, return_dtype=Duration)
-        if series.map_elements(
-            make_isinstance(ZonedDateTime), return_dtype=Boolean
-        ).all():
-            return_dtype = zoned_datetime_dtype(time_zone=one({dt.tz for dt in series}))
-            return series.map_elements(
-                lambda x: x.py_datetime(), return_dtype=return_dtype
-            )
-        raise NotImplementedError(series)  # pragma: no cover
-    return series
+    if series.dtype != Object:
+        return series
+    if series.map_elements(make_isinstance(whenever.Date), return_dtype=Boolean).all():
+        return series.map_elements(lambda x: x.py_date(), return_dtype=pl.Date)
+    if series.map_elements(make_isinstance(DateDelta), return_dtype=Boolean).all():
+        return series.map_elements(to_py_time_delta, return_dtype=Duration)
+    if series.map_elements(make_isinstance(DateTimeDelta), return_dtype=Boolean).all():
+        return series.map_elements(to_py_time_delta, return_dtype=Duration)
+    is_path = series.map_elements(make_isinstance(Path), return_dtype=Boolean).all()
+    is_uuid = series.map_elements(make_isinstance(UUID), return_dtype=Boolean).all()
+    if is_path or is_uuid:
+        with suppress_warnings(category=PolarsInefficientMapWarning):
+            return series.map_elements(str, return_dtype=String)
+    if series.map_elements(make_isinstance(whenever.Time), return_dtype=Boolean).all():
+        return series.map_elements(lambda x: x.py_time(), return_dtype=pl.Time)
+    if series.map_elements(make_isinstance(TimeDelta), return_dtype=Boolean).all():
+        return series.map_elements(to_py_time_delta, return_dtype=Duration)
+    if series.map_elements(make_isinstance(ZonedDateTime), return_dtype=Boolean).all():
+        return_dtype = zoned_date_time_dtype(time_zone=one({dt.tz for dt in series}))
+        return series.map_elements(lambda x: x.py_datetime(), return_dtype=return_dtype)
+    if series.map_elements(
+        lambda x: isinstance(x, dict) and (set(x) == {"start", "end"}),
+        return_dtype=Boolean,
+    ).all():
+        start = _dataclass_to_dataframe_cast(
+            series.map_elements(lambda x: x["start"], return_dtype=Object)
+        ).alias("start")
+        end = _dataclass_to_dataframe_cast(
+            series.map_elements(lambda x: x["end"], return_dtype=Object)
+        ).alias("end")
+        name = series.name
+        return concat_series(start, end).select(
+            struct(start=start, end=end).alias(name)
+        )[name]
+    raise NotImplementedError(series)  # pragma: no cover
 
 
 @dataclass(kw_only=True, slots=True)
@@ -1362,29 +1346,6 @@ class _FiniteEWMWeightsError(Exception):
 ##
 
 
-@overload
-def floor_datetime(column: ExprLike, every: ExprLike, /) -> Expr: ...
-@overload
-def floor_datetime(column: Series, every: ExprLike, /) -> Series: ...
-@overload
-def floor_datetime(column: IntoExprColumn, every: ExprLike, /) -> ExprOrSeries: ...
-def floor_datetime(column: IntoExprColumn, every: ExprLike, /) -> ExprOrSeries:
-    """Compute the `floor` of a datetime column."""
-    column = ensure_expr_or_series(column)
-    rounded = column.dt.round(every)
-    floor = (
-        when(column >= rounded)
-        .then(rounded)
-        .otherwise(column.dt.offset_by("-" + every).dt.round(every))
-    )
-    if isinstance(column, Expr):
-        return floor
-    return DataFrame().with_columns(floor.alias(column.name))[column.name]
-
-
-##
-
-
 def get_data_type_or_series_time_zone(
     dtype_or_series: PolarsDataType | Series, /
 ) -> ZoneInfo:
@@ -2480,10 +2441,6 @@ def _struct_from_dataclass_one(
     }
     with suppress(KeyError):
         return mapping[ann]
-    if ann is dt.datetime:
-        if time_zone is None:
-            raise _StructFromDataClassTimeZoneMissingError
-        return zoned_datetime_dtype(time_zone=time_zone)
     if is_dataclass_class(ann):
         return struct_from_dataclass(ann, time_zone=time_zone)
     if (isinstance(ann, type) and issubclass(ann, enum.Enum)) or (
@@ -2512,13 +2469,6 @@ class _StructFromDataClassNotADataclassError(StructFromDataClassError):
         return f"Object must be a dataclass; got {self.cls}"
 
 
-@dataclass(kw_only=True, slots=True)
-class _StructFromDataClassTimeZoneMissingError(StructFromDataClassError):
-    @override
-    def __str__(self) -> str:
-        return "Time-zone must be given"
-
-
 @dataclass(kw_only=True, slots=True)
 class _StructFromDataClassTypeError(StructFromDataClassError):
     ann: Any
@@ -2612,27 +2562,27 @@ def week_num(column: IntoExprColumn, /, *, start: WeekDay = "mon") -> ExprOrSeri
 ##
 
 
-def zoned_datetime_dtype(
+def zoned_date_time_dtype(
     *, time_unit: TimeUnit = "us", time_zone: TimeZoneLike = UTC
 ) -> Datetime:
-    """Create a zoned datetime data type."""
+    """Create a zoned date-time data type."""
     return Datetime(time_unit=time_unit, time_zone=get_time_zone_name(time_zone))
 
 
-def zoned_datetime_period_dtype(
+def zoned_date_time_period_dtype(
     *,
     time_unit: TimeUnit = "us",
     time_zone: TimeZoneLike | tuple[TimeZoneLike, TimeZoneLike] = UTC,
 ) -> Struct:
-    """Create a zoned datetime period data type."""
+    """Create a zoned date-time period data type."""
     match time_zone:
         case start, end:
             return struct_dtype(
-                start=zoned_datetime_dtype(time_unit=time_unit, time_zone=start),
-                end=zoned_datetime_dtype(time_unit=time_unit, time_zone=end),
+                start=zoned_date_time_dtype(time_unit=time_unit, time_zone=start),
+                end=zoned_date_time_dtype(time_unit=time_unit, time_zone=end),
             )
         case _:
-            dtype = zoned_datetime_dtype(time_unit=time_unit, time_zone=time_zone)
+            dtype = zoned_date_time_dtype(time_unit=time_unit, time_zone=time_zone)
             return struct_dtype(start=dtype, end=dtype)
 
 
@@ -2641,6 +2591,7 @@ __all__ = [
     "CheckPolarsDataFrameError",
     "ColumnsToDictError",
     "DataClassToDataFrameError",
+    "DatePeriodDType",
     "DatetimeHongKong",
     "DatetimeTokyo",
     "DatetimeUSCentral",
@@ -2658,6 +2609,7 @@ __all__ = [
     "IsNullStructSeriesError",
     "SetFirstRowAsColumnsError",
     "StructFromDataClassError",
+    "TimePeriodDType",
     "acf",
     "adjust_frequencies",
     "all_dataframe_columns",
@@ -2668,7 +2620,6 @@ __all__ = [
     "are_frames_equal",
     "bernoulli",
     "boolean_value_counts",
-    "ceil_datetime",
     "check_polars_dataframe",
     "choice",
     "collect_series",
@@ -2685,7 +2636,6 @@ __all__ = [
     "ensure_expr_or_series",
     "ensure_expr_or_series_many",
     "finite_ewm_mean",
-    "floor_datetime",
     "get_data_type_or_series_time_zone",
     "get_expr_name",
     "get_frequency_spectrum",
@@ -2721,6 +2671,6 @@ __all__ = [
     "unique_element",
     "write_dataframe",
     "write_series",
-    "zoned_datetime_dtype",
-    "zoned_datetime_period_dtype",
+    "zoned_date_time_dtype",
+    "zoned_date_time_period_dtype",
 ]

{dycw_utilities-0.155.1 → dycw_utilities-0.155.3}/src/utilities/sqlalchemy_polars.py

@@ -35,7 +35,7 @@ from utilities.iterables import (
     chunked,
     one,
 )
-from utilities.polars import zoned_datetime_dtype
+from utilities.polars import zoned_date_time_dtype
 from utilities.reprlib import get_repr
 from utilities.sqlalchemy import (
     CHUNK_SIZE_FRAC,
@@ -390,7 +390,7 @@ def _select_to_dataframe_map_table_column_type_to_dtype(
         return pl.Date
     if is_subclass_gen(py_type, dt.datetime):
         has_tz: bool = type_use.timezone
-        return zoned_datetime_dtype(time_zone=time_zone) if has_tz else Datetime()
+        return zoned_date_time_dtype(time_zone=time_zone) if has_tz else Datetime()
     if issubclass(py_type, dt.time):
         return Time
     if issubclass(py_type, dt.timedelta):