dycw-utilities 0.155.1__py3-none-any.whl → 0.155.2__py3-none-any.whl

{dycw_utilities-0.155.1.dist-info → dycw_utilities-0.155.2.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: dycw-utilities
-Version: 0.155.1
+Version: 0.155.2
 Author-email: Derek Wan <d.wan@icloud.com>
 License-File: LICENSE
 Requires-Python: >=3.12

{dycw_utilities-0.155.1.dist-info → dycw_utilities-0.155.2.dist-info}/RECORD

@@ -1,4 +1,4 @@
-utilities/__init__.py,sha256=VUm6D-MbPENpEcdDNizwkQ7ZdWupTs1IZmUsMeC93k0,60
+utilities/__init__.py,sha256=UpA18BgKE4JKTnomInevMSHAcDOtpqnipumof6hoK_c,60
 utilities/altair.py,sha256=92E2lCdyHY4Zb-vCw6rEJIsWdKipuu-Tu2ab1ufUfAk,9079
 utilities/asyncio.py,sha256=QXkTtugXkqtYt7Do23zgYErqzdp6jwzPpV_SP9fJ1gI,16780
 utilities/atomicwrites.py,sha256=tPo6r-Rypd9u99u66B9z86YBPpnLrlHtwox_8Z7T34Y,5790
@@ -45,7 +45,7 @@ utilities/parse.py,sha256=JcJn5yXKhIWXBCwgBdPsyu7Hvcuw6kyEdqvaebCaI9k,17951
 utilities/pathlib.py,sha256=qGuU8XPmdgGpy8tOMUgelfXx3kxI8h9IaV3TI_06QGE,8428
 utilities/pickle.py,sha256=MBT2xZCsv0pH868IXLGKnlcqNx2IRVKYNpRcqiQQqxw,653
 utilities/platform.py,sha256=pTn7gw6N4T6LdKrf0virwarof_mze9WtoQlrGMzhGVI,2798
-utilities/polars.py,sha256=yedkwwcyX35lreA2CeOGVRyOrXrs8DKk98T9dWpnxCo,79844
+utilities/polars.py,sha256=kEYLh5kcpvjOqNS-Pv-DAjvzPZYm6qZ7ywMt-wZvRGE,78434
 utilities/polars_ols.py,sha256=Uc9V5kvlWZ5cU93lKZ-cfAKdVFFw81tqwLW9PxtUvMs,5618
 utilities/postgres.py,sha256=ynCTTaF-bVEOSW-KEAR-dlLh_hYjeVVjm__-4pEU8Zk,12269
 utilities/pottery.py,sha256=HJ96oLRarTP37Vhg0WTyB3yAu2hETeg6HgRmpDIqyUs,6581
@@ -65,7 +65,7 @@ utilities/shelve.py,sha256=4OzjQI6kGuUbJciqf535rwnao-_IBv66gsT6tRGiUt0,759
 utilities/slack_sdk.py,sha256=ppFBvKgfg5IRWiIoKPtpTyzBtBF4XmwEvU3I5wLJikM,2140
 utilities/socket.py,sha256=K77vfREvzoVTrpYKo6MZakol0EYu2q1sWJnnZqL0So0,118
 utilities/sqlalchemy.py,sha256=IJKzrKUd_eBOkyK6CucDlxtHwo2vYH3t-rV2_5rAxq8,40554
-utilities/sqlalchemy_polars.py,sha256=Mm-sShZfqqgnzTrupMQdCfSM2akrybXHXAErTs-ofM8,14244
+utilities/sqlalchemy_polars.py,sha256=5Q9HReETYg0qB6E6WQhFh4QAZlKE-IWlogj2BVif_-w,14246
 utilities/statsmodels.py,sha256=koyiBHvpMcSiBfh99wFUfSggLNx7cuAw3rwyfAhoKpQ,3410
 utilities/string.py,sha256=shmBK87zZwzGyixuNuXCiUbqzfeZ9xlrFwz6JTaRvDk,582
 utilities/tempfile.py,sha256=HxB2BF28CcecDJLQ3Bx2Ej-Pb6RJc6W9ngSpB9CnP4k,2018
@@ -87,8 +87,8 @@ utilities/zoneinfo.py,sha256=FBMcUQ4662Aq8SsuCL1OAhDQiyANmVjtb-C30DRrWoE,1966
 utilities/pytest_plugins/__init__.py,sha256=U4S_2y3zgLZVfMenHRaJFBW8yqh2mUBuI291LGQVOJ8,35
 utilities/pytest_plugins/pytest_randomly.py,sha256=B1qYVlExGOxTywq2r1SMi5o7btHLk2PNdY_b1p98dkE,409
 utilities/pytest_plugins/pytest_regressions.py,sha256=9v8kAXDM2ycIXJBimoiF4EgrwbUvxTycFWJiGR_GHhM,1466
-dycw_utilities-0.155.1.dist-info/METADATA,sha256=t4j9mkVdOy56nqyYGTiiODz6Zq0dOJUFTTz_4CTcQTg,1643
-dycw_utilities-0.155.1.dist-info/WHEEL,sha256=qtCwoSJWgHk21S1Kb4ihdzI2rlJ1ZKaIurTj_ngOhyQ,87
-dycw_utilities-0.155.1.dist-info/entry_points.txt,sha256=BOD_SoDxwsfJYOLxhrSXhHP_T7iw-HXI9f2WVkzYxvQ,135
-dycw_utilities-0.155.1.dist-info/licenses/LICENSE,sha256=gppZp16M6nSVpBbUBrNL6JuYfvKwZiKgV7XoKKsHzqo,1066
-dycw_utilities-0.155.1.dist-info/RECORD,,
+dycw_utilities-0.155.2.dist-info/METADATA,sha256=bti46Z55f6RXvAyFTu6sAzeis6LgdIEkMPTR0rQWj1w,1643
+dycw_utilities-0.155.2.dist-info/WHEEL,sha256=qtCwoSJWgHk21S1Kb4ihdzI2rlJ1ZKaIurTj_ngOhyQ,87
+dycw_utilities-0.155.2.dist-info/entry_points.txt,sha256=BOD_SoDxwsfJYOLxhrSXhHP_T7iw-HXI9f2WVkzYxvQ,135
+dycw_utilities-0.155.2.dist-info/licenses/LICENSE,sha256=gppZp16M6nSVpBbUBrNL6JuYfvKwZiKgV7XoKKsHzqo,1066
+dycw_utilities-0.155.2.dist-info/RECORD,,

utilities/__init__.py

@@ -1,3 +1,3 @@
 from __future__ import annotations
 
-__version__ = "0.155.1"
+__version__ = "0.155.2"

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 +1036,38 @@ 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")
+        return concat_series(start, end).select(x=struct(start=start, end=end))["x"]
+    raise NotImplementedError(series)  # pragma: no cover
 
 
 @dataclass(kw_only=True, slots=True)
@@ -1362,29 +1343,6 @@ 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 +2438,6 @@ 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 +2466,6 @@ 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 +2559,27 @@ 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 +2588,7 @@ __all__ = [
     "CheckPolarsDataFrameError",
     "ColumnsToDictError",
     "DataClassToDataFrameError",
+    "DatePeriodDType",
     "DatetimeHongKong",
     "DatetimeTokyo",
     "DatetimeUSCentral",
@@ -2658,6 +2606,7 @@ __all__ = [
     "IsNullStructSeriesError",
     "SetFirstRowAsColumnsError",
     "StructFromDataClassError",
+    "TimePeriodDType",
     "acf",
     "adjust_frequencies",
     "all_dataframe_columns",
@@ -2668,7 +2617,6 @@ __all__ = [
     "are_frames_equal",
     "bernoulli",
     "boolean_value_counts",
-    "ceil_datetime",
     "check_polars_dataframe",
     "choice",
     "collect_series",
@@ -2685,7 +2633,6 @@ __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 +2668,6 @@ __all__ = [
     "unique_element",
     "write_dataframe",
     "write_series",
-    "zoned_datetime_dtype",
-    "zoned_datetime_period_dtype",
+    "zoned_date_time_dtype",
+    "zoned_date_time_period_dtype",
 ]

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):