dycw-utilities 0.159.2__tar.gz → 0.159.4__tar.gz

{dycw_utilities-0.159.2 → dycw_utilities-0.159.4}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: dycw-utilities
-Version: 0.159.2
+Version: 0.159.4
 Author-email: Derek Wan <d.wan@icloud.com>
 License-File: LICENSE
 Requires-Python: >=3.12

{dycw_utilities-0.159.2 → dycw_utilities-0.159.4}/pyproject.toml

@@ -227,7 +227,7 @@ dependencies = [
 name = "dycw-utilities"
 readme = "README.md"
 requires-python = ">= 3.12"
-version = "0.159.2"
+version = "0.159.4"
 
 [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 = "0.159.2"
+current_version = "0.159.4"
 
 [[tool.bumpversion.files]]
 filename = "src/utilities/__init__.py"

{dycw_utilities-0.159.2 → dycw_utilities-0.159.4}/src/tests/test_math.py

@@ -843,22 +843,20 @@ class TestMaxLongAndDouble:
 
 class TestNumberOfDecimals:
     max_int: ClassVar[int] = int(1e6)
+    cases: ClassVar[list[tuple[float, int]]] = [
+        (0.0, 0),
+        (0.1, 1),
+        (0.12, 2),
+        (0.123, 3),
+        (0.1234, 4),
+        (0.12345, 5),
+        (0.123456, 6),
+        (0.1234567, 7),
+        (0.12345678, 8),
+        (0.123456789, 9),
+    ]
 
-    @given(
-        integer=integers(-max_int, max_int),
-        case=sampled_from([
-            (0.0, 0),
-            (0.1, 1),
-            (0.12, 2),
-            (0.123, 3),
-            (0.1234, 4),
-            (0.12345, 5),
-            (0.123456, 6),
-            (0.1234567, 7),
-            (0.12345678, 8),
-            (0.123456789, 9),
-        ]),
-    )
+    @given(integer=integers(-max_int, max_int), case=sampled_from(cases))
     def test_main(self, *, integer: int, case: tuple[float, int]) -> None:
         frac, expected = case
         x = integer + frac
@@ -870,7 +868,7 @@ class TestNumberOfDecimals:
         with raises(
             NumberOfDecimalsError,
             match=escape(
-                "Could not determine number of decimals of 1.401298464324817e-45 (up to 20)"
+                "Could not determine number of decimals of 1.401298464324817e-45 (up to 10)"
             ),
         ):
             _ = number_of_decimals(x)

{dycw_utilities-0.159.2 → dycw_utilities-0.159.4}/src/tests/test_polars.py

@@ -3,6 +3,7 @@ from __future__ import annotations
 import datetime as dt
 import enum
 import itertools
+import math
 from dataclasses import dataclass, field
 from enum import auto
 from itertools import chain, repeat
@@ -59,6 +60,7 @@ from pytest import mark, param, raises
 from whenever import DateDelta, DateTimeDelta, PlainDateTime, TimeDelta, ZonedDateTime
 
 import tests.test_math
+import utilities.math
 import utilities.polars
 from utilities.hypothesis import (
     date_deltas,
@@ -77,7 +79,6 @@ from utilities.hypothesis import (
     zoned_date_time_periods,
     zoned_date_times,
 )
-from utilities.math import number_of_decimals
 from utilities.numpy import DEFAULT_RNG
 from utilities.pathlib import PWD
 from utilities.polars import (
@@ -122,8 +123,6 @@ from utilities.polars import (
     _GetDataTypeOrSeriesTimeZoneNotDateTimeError,
     _GetDataTypeOrSeriesTimeZoneNotZonedError,
     _GetDataTypeOrSeriesTimeZoneStructNonUniqueError,
-    _GetSeriesNumberOfDecimalsAllNullError,
-    _GetSeriesNumberOfDecimalsNotFloatError,
     _InsertBetweenMissingColumnsError,
     _InsertBetweenNonConsecutiveError,
     _IsNearEventAfterError,
@@ -168,7 +167,6 @@ from utilities.polars import (
     get_data_type_or_series_time_zone,
     get_expr_name,
     get_frequency_spectrum,
-    get_series_number_of_decimals,
     increasing_horizontal,
     insert_after,
     insert_before,
@@ -182,6 +180,7 @@ from utilities.polars import (
     nan_sum_agg,
     nan_sum_cols,
     normal,
+    number_of_decimals,
     offset_datetime,
     one_column,
     order_of_magnitude,
@@ -1659,34 +1658,6 @@ class TestGetFrequencySpectrum:
         assert allclose(result.filter(col("frequency").abs() > 0.02)["amplitude"], 0.0)
 
 
-class TestGetSeriesNumberOfDecimals:
-    @given(data=data(), n=hypothesis.strategies.integers(1, 10), nullable=booleans())
-    def test_main(self, *, data: DataObject, n: int, nullable: bool) -> None:
-        strategy = int64s() | none() if nullable else int64s()
-        ints_or_none = data.draw(lists(strategy, min_size=1, max_size=10))
-        values = [None if i is None else i / 10**n for i in ints_or_none]
-        series = Series(values=values, dtype=Float64)
-        result = get_series_number_of_decimals(series, nullable=nullable)
-        if not nullable:
-            assert result is not None
-            expected = max(number_of_decimals(v) for v in values if v is not None)
-            assert result == expected
-
-    def test_error_not_float(self) -> None:
-        with raises(
-            _GetSeriesNumberOfDecimalsNotFloatError,
-            match="Data type must be Float64; got Boolean",
-        ):
-            _ = get_series_number_of_decimals(Series(dtype=Boolean))
-
-    def test_error_not_zoned(self) -> None:
-        with raises(
-            _GetSeriesNumberOfDecimalsAllNullError,
-            match="Series must not be all-null; got .*",
-        ):
-            _ = get_series_number_of_decimals(Series(dtype=Float64))
-
-
 class TestIncreasingAndDecreasingHorizontal:
     def test_main(self) -> None:
         df = DataFrame(
@@ -1828,6 +1799,18 @@ class TestIntegers:
         assert series.is_between(0, high, closed="left").all()
 
 
+class TestIsClose:
+    @given(values=pairs(float64s()), rel_tol=floats(0.0, 1.0), abs_tol=floats(0.0, 1.0))
+    def test_main(
+        self, *, values: tuple[float, float], rel_tol: float, abs_tol: float
+    ) -> None:
+        x, y = values
+        x_sr, y_sr = [Series(values=[i], dtype=Float64) for i in values]
+        result = utilities.polars.is_close(x_sr, y_sr, rel_tol=rel_tol, abs_tol=abs_tol)
+        expected = math.isclose(x, y, rel_tol=rel_tol, abs_tol=abs_tol)
+        assert result.item() is expected
+
+
 class TestIsNearEvent:
     df: ClassVar[DataFrame] = DataFrame(
         data=[
@@ -2248,6 +2231,22 @@ class TestNormal:
         assert series.is_finite().all()
 
 
+class TestNumberOfDecimals:
+    @given(
+        integer=hypothesis.strategies.integers(
+            -tests.test_math.TestNumberOfDecimals.max_int,
+            tests.test_math.TestNumberOfDecimals.max_int,
+        ),
+        case=sampled_from(tests.test_math.TestNumberOfDecimals.cases),
+    )
+    def test_main(self, *, integer: int, case: tuple[float, int]) -> None:
+        frac, expected = case
+        x = integer + frac
+        series = Series(name="x", values=[x], dtype=Float64)
+        result = number_of_decimals(series)
+        assert result.item() == expected
+
+
 class TestOffsetDateTime:
     @mark.parametrize(
         ("n", "time"), [param(1, whenever.Time(13, 30)), param(2, whenever.Time(15))]

{dycw_utilities-0.159.2 → dycw_utilities-0.159.4}/src/utilities/__init__.py

@@ -1,3 +1,3 @@
 from __future__ import annotations
 
-__version__ = "0.159.2"
+__version__ = "0.159.4"

{dycw_utilities-0.159.2 → dycw_utilities-0.159.4}/src/utilities/math.py

@@ -641,7 +641,10 @@ def _is_close(
 ##
 
 
-def number_of_decimals(x: float, /, *, max_decimals: int = 20) -> int:
+MAX_DECIMALS = 10
+
+
+def number_of_decimals(x: float, /, *, max_decimals: int = MAX_DECIMALS) -> int:
     """Get the number of decimals."""
     _, frac = divmod(x, 1)
     results = (
@@ -889,6 +892,7 @@ def significant_figures(x: float, /, *, n: int = 2) -> str:
 
 
 __all__ = [
+    "MAX_DECIMALS",
     "MAX_FLOAT32",
     "MAX_FLOAT64",
     "MAX_INT8",

{dycw_utilities-0.159.2 → dycw_utilities-0.159.4}/src/utilities/polars.py

@@ -36,6 +36,7 @@ from polars import (
     datetime_range,
     int_range,
     lit,
+    max_horizontal,
     struct,
     sum_horizontal,
     when,
@@ -52,11 +53,10 @@ from polars.schema import Schema
 from polars.testing import assert_frame_equal, assert_series_equal
 from whenever import DateDelta, DateTimeDelta, PlainDateTime, TimeDelta, ZonedDateTime
 
+import utilities.math
 from utilities.dataclasses import yield_fields
 from utilities.errors import ImpossibleCaseError
 from utilities.functions import (
-    EnsureIntError,
-    ensure_int,
     is_dataclass_class,
     is_dataclass_instance,
     make_isinstance,
@@ -79,12 +79,12 @@ from utilities.iterables import (
 )
 from utilities.json import write_formatted_json
 from utilities.math import (
+    MAX_DECIMALS,
     CheckIntegerError,
     check_integer,
     ewm_parameters,
     is_less_than,
     is_non_negative,
-    number_of_decimals,
 )
 from utilities.reprlib import get_repr
 from utilities.types import MaybeStr, Number, PathLike, WeekDay
@@ -1426,56 +1426,6 @@ def get_frequency_spectrum(series: Series, /, *, d: int = 1) -> DataFrame:
 ##
 
 
-@overload
-def get_series_number_of_decimals(
-    series: Series, /, *, nullable: Literal[True]
-) -> int | None: ...
-@overload
-def get_series_number_of_decimals(
-    series: Series, /, *, nullable: Literal[False] = False
-) -> int: ...
-@overload
-def get_series_number_of_decimals(
-    series: Series, /, *, nullable: bool = False
-) -> int | None: ...
-def get_series_number_of_decimals(
-    series: Series, /, *, nullable: bool = False
-) -> int | None:
-    """Get the number of decimals of a series."""
-    if not isinstance(dtype := series.dtype, Float64):
-        raise _GetSeriesNumberOfDecimalsNotFloatError(dtype=dtype)
-    decimals = series.map_elements(number_of_decimals, return_dtype=Int64).max()
-    try:
-        return ensure_int(decimals, nullable=nullable)
-    except EnsureIntError:
-        raise _GetSeriesNumberOfDecimalsAllNullError(series=series) from None
-
-
-@dataclass(kw_only=True, slots=True)
-class GetSeriesNumberOfDecimalsError(Exception): ...
-
-
-@dataclass(kw_only=True, slots=True)
-class _GetSeriesNumberOfDecimalsNotFloatError(GetSeriesNumberOfDecimalsError):
-    dtype: DataType
-
-    @override
-    def __str__(self) -> str:
-        return f"Data type must be Float64; got {self.dtype}"
-
-
-@dataclass(kw_only=True, slots=True)
-class _GetSeriesNumberOfDecimalsAllNullError(GetSeriesNumberOfDecimalsError):
-    series: Series
-
-    @override
-    def __str__(self) -> str:
-        return f"Series must not be all-null; got {self.series}"
-
-
-##
-
-
 @overload
 def increasing_horizontal(*columns: ExprLike) -> Expr: ...
 @overload
@@ -1641,6 +1591,42 @@ def integers(
 ##
 
 
+@overload
+def is_close(
+    x: ExprLike, y: ExprLike, /, *, rel_tol: float = 1e-9, abs_tol: float = 0
+) -> Expr: ...
+@overload
+def is_close(
+    x: Series, y: Series, /, *, rel_tol: float = 1e-9, abs_tol: float = 0
+) -> Series: ...
+@overload
+def is_close(
+    x: IntoExprColumn,
+    y: IntoExprColumn,
+    /,
+    *,
+    rel_tol: float = 1e-9,
+    abs_tol: float = 0,
+) -> ExprOrSeries: ...
+def is_close(
+    x: IntoExprColumn,
+    y: IntoExprColumn,
+    /,
+    *,
+    rel_tol: float = 1e-9,
+    abs_tol: float = 0,
+) -> ExprOrSeries:
+    """Check if two columns are close."""
+    x, y = map(ensure_expr_or_series, [x, y])
+    result = (x - y).abs() <= max_horizontal(
+        rel_tol * max_horizontal(x.abs(), y.abs()), abs_tol
+    )
+    return try_reify_expr(result, x, y)
+
+
+##
+
+
 @overload
 def is_near_event(
     *exprs: ExprLike, before: int = 0, after: int = 0, **named_exprs: ExprLike
@@ -1986,6 +1972,26 @@ def normal(
 ##
 
 
+def number_of_decimals(
+    series: Series, /, *, max_decimals: int = MAX_DECIMALS
+) -> Series:
+    """Get the number of decimals."""
+    frac = series - series.floor()
+    results = [
+        _number_of_decimals_check_scale(frac, s) for s in range(max_decimals + 1)
+    ]
+    df_results = concat_series(*results)
+    return first_true_horizontal(df_results)
+
+
+def _number_of_decimals_check_scale(frac: Series, scale: int, /) -> Series:
+    scaled = 10**scale * frac
+    return is_close(scaled, scaled.round()).alias(str(scale))
+
+
+##
+
+
 def offset_datetime(
     datetime: ZonedDateTime, offset: str, /, *, n: int = 1
 ) -> ZonedDateTime:
@@ -2352,7 +2358,7 @@ def round_to_float(
     """Round a column to the nearest multiple of another float."""
     x = ensure_expr_or_series(x)
     z = (x / y).round(mode=mode) * y
-    return z.round(decimals=number_of_decimals(y) + 1)
+    return z.round(decimals=utilities.math.number_of_decimals(y) + 1)
 
 
 ##
@@ -2558,7 +2564,6 @@ __all__ = [
     "ExprOrSeries",
     "FiniteEWMMeanError",
     "GetDataTypeOrSeriesTimeZoneError",
-    "GetSeriesNumberOfDecimalsError",
     "InsertAfterError",
     "InsertBeforeError",
     "InsertBetweenError",
@@ -2597,12 +2602,12 @@ __all__ = [
     "get_data_type_or_series_time_zone",
     "get_expr_name",
     "get_frequency_spectrum",
-    "get_series_number_of_decimals",
     "increasing_horizontal",
     "insert_after",
     "insert_before",
     "insert_between",
     "integers",
+    "is_close",
     "is_false",
     "is_near_event",
     "is_true",
@@ -2612,6 +2617,7 @@ __all__ = [
     "nan_sum_agg",
     "nan_sum_cols",
     "normal",
+    "number_of_decimals",
     "offset_datetime",
     "one_column",
     "order_of_magnitude",

{dycw_utilities-0.159.2 → dycw_utilities-0.159.4}/src/utilities/types.py

@@ -79,6 +79,9 @@ type MaybeCoro[T] = T | Coro[T]
 
 
 # collections.abc
+type SupportsFloatOrIndex = SupportsFloat | SupportsIndex
+
+
 @runtime_checkable
 class SupportsKeysAndGetItem(Protocol[_T, _T_co]):
     def keys(self) -> Iterable[_T]: ...  # pragma: no cover
@@ -328,6 +331,7 @@ __all__ = [
     "SupportsBytes",
     "SupportsComplex",
     "SupportsFloat",
+    "SupportsFloatOrIndex",
     "SupportsGT",
     "SupportsInt",
     "SupportsInt",