dycw-utilities 0.109.8__tar.gz → 0.109.9__tar.gz

{dycw_utilities-0.109.8 → dycw_utilities-0.109.9}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: dycw-utilities
-Version: 0.109.8
+Version: 0.109.9
 Author-email: Derek Wan <d.wan@icloud.com>
 License-File: LICENSE
 Requires-Python: >=3.12

{dycw_utilities-0.109.8 → dycw_utilities-0.109.9}/pyproject.toml

@@ -89,7 +89,7 @@ dependencies = [
 name = "dycw-utilities"
 readme = "README.md"
 requires-python = ">= 3.12"
-version = "0.109.8"
+version = "0.109.9"
 
 [project.optional-dependencies]
 test = [
@@ -332,7 +332,7 @@ zzz-test-zoneinfo = [
 # bump-my-version
 [tool.bumpversion]
 allow_dirty = true
-current_version = "0.109.8"
+current_version = "0.109.9"
 
 [[tool.bumpversion.files]]
 filename = "src/utilities/__init__.py"

{dycw_utilities-0.109.8 → dycw_utilities-0.109.9}/src/tests/test_polars.py

@@ -11,6 +11,7 @@ from pathlib import Path
 from typing import TYPE_CHECKING, Any, ClassVar, Literal, cast
 from uuid import UUID, uuid4
 
+import hypothesis.strategies
 import polars as pl
 from hypothesis import given
 from hypothesis.strategies import (
@@ -20,7 +21,6 @@ from hypothesis.strategies import (
     data,
     fixed_dictionaries,
     floats,
-    integers,
     lists,
     none,
     sampled_from,
@@ -50,10 +50,12 @@ from polars import (
 from polars.testing import assert_frame_equal, assert_series_equal
 from pytest import raises
 
+import utilities.polars
 from utilities.datetime import get_now, get_today
 from utilities.hypothesis import (
     assume_does_not_raise,
     int64s,
+    pairs,
     text_ascii,
     zoned_datetimes,
 )
@@ -129,11 +131,13 @@ from utilities.polars import (
     map_over_columns,
     nan_sum_agg,
     nan_sum_cols,
+    normal,
     replace_time_zone,
     set_first_row_as_columns,
     struct_dtype,
     struct_from_dataclass,
     touch,
+    uniform,
     unique_element,
     week_num,
     yield_struct_series_dataclasses,
@@ -1210,7 +1214,7 @@ class TestGetDataTypeOrSeriesTimeZone:
 
 
 class TestGetSeriesNumberOfDecimals:
-    @given(data=data(), n=integers(1, 10), nullable=booleans())
+    @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))
@@ -1312,6 +1316,37 @@ class TestInsertBetween:
             _ = insert_between(self.df, "a", "c", lit(None).alias("new"))
 
 
+class TestIntegers:
+    @given(
+        length=hypothesis.strategies.integers(0, 10),
+        high=hypothesis.strategies.integers(1, 10),
+    )
+    def test_int(self, *, length: int, high: int) -> None:
+        series = utilities.polars.integers(length, high)
+        assert series.len() == length
+        assert series.is_between(0, high, closed="left").all()
+
+    @given(
+        length=hypothesis.strategies.integers(0, 10),
+        high=hypothesis.strategies.integers(1, 10),
+    )
+    def test_series(self, *, length: int, high: int) -> None:
+        orig = int_range(end=length, eager=True)
+        series = utilities.polars.integers(orig, high)
+        assert series.len() == length
+        assert series.is_between(0, high, closed="left").all()
+
+    @given(
+        length=hypothesis.strategies.integers(0, 10),
+        high=hypothesis.strategies.integers(1, 10),
+    )
+    def test_dataframe(self, *, length: int, high: int) -> None:
+        df = int_range(end=length, eager=True).to_frame()
+        series = utilities.polars.integers(df, high)
+        assert series.len() == length
+        assert series.is_between(0, high, closed="left").all()
+
+
 class TestIsNullAndIsNotNullStructSeries:
     @given(
         case=sampled_from([
@@ -1526,6 +1561,28 @@ class TestNanSumCols:
         assert df["z"].item() == expected
 
 
+class TestNormal:
+    @given(length=hypothesis.strategies.integers(0, 10))
+    def test_int(self, *, length: int) -> None:
+        series = normal(length)
+        assert series.len() == length
+        assert series.is_finite().all()
+
+    @given(length=hypothesis.strategies.integers(0, 10))
+    def test_series(self, *, length: int) -> None:
+        orig = int_range(end=length, eager=True)
+        series = normal(orig)
+        assert series.len() == length
+        assert series.is_finite().all()
+
+    @given(length=hypothesis.strategies.integers(0, 10))
+    def test_dataframe(self, *, length: int) -> None:
+        df = int_range(end=length, eager=True).to_frame()
+        series = normal(df)
+        assert series.len() == length
+        assert series.is_finite().all()
+
+
 class TestReplaceTimeZone:
     def test_datetime(self) -> None:
         now_utc = get_now()
@@ -1711,6 +1768,40 @@ class TestStructFromDataClass:
             _ = struct_from_dataclass(Example)
 
 
+class TestUniform:
+    @given(
+        length=hypothesis.strategies.integers(0, 10),
+        bounds=pairs(floats(0.0, 1.0), sorted=True),
+    )
+    def test_int(self, *, length: int, bounds: tuple[float, float]) -> None:
+        low, high = bounds
+        series = uniform(length, low=low, high=high)
+        assert series.len() == length
+        assert series.is_between(low, high).all()
+
+    @given(
+        length=hypothesis.strategies.integers(0, 10),
+        bounds=pairs(floats(0.0, 1.0), sorted=True),
+    )
+    def test_series(self, *, length: int, bounds: tuple[float, float]) -> None:
+        low, high = bounds
+        orig = int_range(end=length, eager=True)
+        series = uniform(orig, low=low, high=high)
+        assert series.len() == length
+        assert series.is_between(low, high).all()
+
+    @given(
+        length=hypothesis.strategies.integers(0, 10),
+        bounds=pairs(floats(0.0, 1.0), sorted=True),
+    )
+    def test_dataframe(self, *, length: int, bounds: tuple[float, float]) -> None:
+        low, high = bounds
+        df = int_range(end=length, eager=True).to_frame()
+        series = uniform(df, low=low, high=high)
+        assert series.len() == length
+        assert series.is_between(low, high).all()
+
+
 class TestUniqueElement:
     def test_main(self) -> None:
         series = Series(

{dycw_utilities-0.109.8 → dycw_utilities-0.109.9}/src/utilities/__init__.py

@@ -1,3 +1,3 @@
 from __future__ import annotations
 
-__version__ = "0.109.8"
+__version__ = "0.109.9"

{dycw_utilities-0.109.8 → dycw_utilities-0.109.9}/src/utilities/polars.py

@@ -1165,6 +1165,52 @@ class _InsertBetweenNonConsecutiveError(InsertBetweenError):
 ##
 
 
+def integers(
+    obj: int | Series | DataFrame,
+    low: int,
+    /,
+    *,
+    high: int | None = None,
+    seed: int | None = None,
+    endpoint: bool = False,
+    name: str | None = None,
+    dtype: PolarsDataType = Int64,
+) -> Series:
+    """Construct a series of normally-distributed numbers."""
+    match obj:
+        case int() as height:
+            from numpy.random import default_rng
+
+            rng = default_rng(seed=seed)
+            values = rng.integers(low, high=high, size=height, endpoint=endpoint)
+            return Series(name=name, values=values, dtype=dtype)
+        case Series() as series:
+            return integers(
+                series.len(),
+                low,
+                high=high,
+                seed=seed,
+                endpoint=endpoint,
+                name=name,
+                dtype=dtype,
+            )
+        case DataFrame() as df:
+            return integers(
+                df.height,
+                low,
+                high=high,
+                seed=seed,
+                endpoint=endpoint,
+                name=name,
+                dtype=dtype,
+            )
+        case _ as never:
+            assert_never(never)
+
+
+##
+
+
 def is_not_null_struct_series(series: Series, /) -> Series:
     """Check if a struct-dtype Series is not null as per the <= 1.1 definition."""
     try:
@@ -1324,6 +1370,39 @@ def nan_sum_cols(
 ##
 
 
+def normal(
+    obj: int | Series | DataFrame,
+    /,
+    *,
+    loc: float = 0.0,
+    scale: float = 1.0,
+    seed: int | None = None,
+    name: str | None = None,
+    dtype: PolarsDataType = Float64,
+) -> Series:
+    """Construct a series of normally-distributed numbers."""
+    match obj:
+        case int() as height:
+            from numpy.random import default_rng
+
+            rng = default_rng(seed=seed)
+            values = rng.normal(loc=loc, scale=scale, size=height)
+            return Series(name=name, values=values, dtype=dtype)
+        case Series() as series:
+            return normal(
+                series.len(), loc=loc, scale=scale, seed=seed, name=name, dtype=dtype
+            )
+        case DataFrame() as df:
+            return normal(
+                df.height, loc=loc, scale=scale, seed=seed, name=name, dtype=dtype
+            )
+        case _ as never:
+            assert_never(never)
+
+
+##
+
+
 @overload
 def replace_time_zone(
     obj: Series, /, *, time_zone: TimeZoneLike | None = UTC
@@ -1461,6 +1540,39 @@ class _StructFromDataClassTypeError(StructFromDataClassError):
 ##
 
 
+def uniform(
+    obj: int | Series | DataFrame,
+    /,
+    *,
+    low: float = 0.0,
+    high: float = 1.0,
+    seed: int | None = None,
+    name: str | None = None,
+    dtype: PolarsDataType = Float64,
+) -> Series:
+    """Construct a series of uniformly-distributed numbers."""
+    match obj:
+        case int() as height:
+            from numpy.random import default_rng
+
+            rng = default_rng(seed=seed)
+            values = rng.uniform(low=low, high=high, size=height)
+            return Series(name=name, values=values, dtype=dtype)
+        case Series() as series:
+            return uniform(
+                series.len(), low=low, high=high, seed=seed, name=name, dtype=dtype
+            )
+        case DataFrame() as df:
+            return uniform(
+                df.height, low=low, high=high, seed=seed, name=name, dtype=dtype
+            )
+        case _ as never:
+            assert_never(never)
+
+
+##
+
+
 def unique_element(column: ExprLike, /) -> Expr:
     """Get the unique element in a list."""
     column = ensure_expr_or_series(column)
@@ -1645,17 +1757,20 @@ __all__ = [
     "insert_after",
     "insert_before",
     "insert_between",
+    "integers",
     "is_not_null_struct_series",
     "is_null_struct_series",
     "join",
     "map_over_columns",
     "nan_sum_agg",
     "nan_sum_cols",
+    "normal",
     "replace_time_zone",
     "set_first_row_as_columns",
     "struct_dtype",
     "struct_from_dataclass",
     "touch",
+    "uniform",
     "unique_element",
     "yield_struct_series_dataclasses",
     "yield_struct_series_elements",