onekit 3.0.1__tar.gz → 4.0.0__tar.gz

{onekit-3.0.1 → onekit-4.0.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.3
 Name: onekit
-Version: 3.0.1
+Version: 4.0.0
 Summary: All-in-One Python Kit.
 License: BSD 3-Clause
 Keywords: onekit
@@ -15,6 +15,7 @@ Provides-Extra: base
 Provides-Extra: pyspark
 Requires-Dist: pandas[compression,computation,excel,output-formatting,parquet,performance,plot] (>=2.2.3,<3.0.0) ; extra == "analytics"
 Requires-Dist: pyspark (==3.5.3) ; extra == "pyspark"
+Requires-Dist: python-dateutil (>=2.9.0.post0,<3.0.0) ; extra == "base"
 Requires-Dist: pytz (>=2025.2,<2026.0) ; extra == "base"
 Requires-Dist: scikit-learn (>=1.6.1,<2.0.0) ; extra == "analytics"
 Requires-Dist: toolz (>=1.0.0,<2.0.0) ; extra == "base"
@@ -40,7 +41,7 @@ All-in-One Python Kit:
 
 - [Examples](https://onekit.readthedocs.io/en/stable/examples.html)
 - [Documentation](https://onekit.readthedocs.io/en/stable/index.html)
-- [Developer Guide](https://onekit.readthedocs.io/en/stable/developers.html)
+- [Dev Guide](https://onekit.readthedocs.io/en/stable/devguide.html)
 - [API Reference](https://onekit.readthedocs.io/en/stable/autoapi/index.html)
 
 ## Installation

{onekit-3.0.1 → onekit-4.0.0}/README.md

@@ -17,7 +17,7 @@ All-in-One Python Kit:
 
 - [Examples](https://onekit.readthedocs.io/en/stable/examples.html)
 - [Documentation](https://onekit.readthedocs.io/en/stable/index.html)
-- [Developer Guide](https://onekit.readthedocs.io/en/stable/developers.html)
+- [Dev Guide](https://onekit.readthedocs.io/en/stable/devguide.html)
 - [API Reference](https://onekit.readthedocs.io/en/stable/autoapi/index.html)
 
 ## Installation

{onekit-3.0.1 → onekit-4.0.0}/pyproject.toml

@@ -22,12 +22,13 @@ requires-python = ">=3.11"
 dependencies = []
 
 [tool.poetry]
-version = "3.0.1"
+version = "4.0.0"
 
 [project.optional-dependencies]
 base = [
-    "toolz (>=1.0.0,<2.0.0)",
+    "python-dateutil (>=2.9.0.post0,<3.0.0)",
     "pytz (>=2025.2,<2026.0)",
+    "toolz (>=1.0.0,<2.0.0)",
 ]
 analytics = [
     "pandas[compression,computation,excel,output-formatting,parquet,performance,plot] (>=2.2.3,<3.0.0)",
@@ -58,7 +59,7 @@ sphinx-copybutton = "^0.5.2"
 time-machine = "^2.16.0"
 
 [tool.poetry.group.packaging.dependencies]
-python-semantic-release = "^8.3.0"
+python-semantic-release = "8.3.0"
 
 [tool.black]
 line-length = 88

{onekit-3.0.1 → onekit-4.0.0}/src/onekit/exception.py

@@ -4,14 +4,14 @@ from typing import (
     Iterable,
 )
 
-from pyspark.sql import DataFrame as SparkDF
-
 from onekit import pythonkit as pk
 
 __all__ = (
     "ColumnNotFoundError",
     "InvalidChoiceError",
+    "InvalidDateRangeWarning",
     "OnekitError",
+    "OnekitWarning",
     "RowCountMismatchError",
     "RowValueMismatchError",
     "SchemaMismatchError",
@@ -96,6 +96,7 @@ class RowCountMismatchError(OnekitError):
         super().__init__(self.message)
 
 
+# noinspection PyUnresolvedReferences
 class RowValueMismatchError(OnekitError):
     """Exception for mismatch of row values.
 
@@ -107,8 +108,8 @@ class RowValueMismatchError(OnekitError):
 
     def __init__(
         self,
-        lft_rows: SparkDF,
-        rgt_rows: SparkDF,
+        lft_rows: "SparkDF",  # noqa: F821
+        rgt_rows: "SparkDF",  # noqa: F821
         num_lft: int,
         num_rgt: int,
     ):
@@ -140,3 +141,11 @@ class SchemaMismatchError(OnekitError):
         num_diff = sum(c == "|" for c in msg.splitlines()[1])
         self.message = pk.concat_strings(os.linesep, f"{num_diff=}", msg)
         super().__init__(self.message)
+
+
+class OnekitWarning(UserWarning):
+    """A base class for onekit warnings."""
+
+
+class InvalidDateRangeWarning(OnekitWarning):
+    """Warning for when a date range is provided in reverse order but is corrected."""

{onekit-3.0.1 → onekit-4.0.0}/src/onekit/numpykit.py

@@ -8,6 +8,7 @@ from onekit import mathkit as mk
 __all__ = (
     "check_random_state",
     "check_vector",
+    "create_boolean_array",
     "digitscale",
     "stderr",
 )
@@ -91,6 +92,25 @@ def check_vector(x: ArrayLike, /, *, n_min: int = 1, n_max: int = np.inf) -> Vec
     return x
 
 
+# noinspection PyTypeChecker
+def create_boolean_array(data: ArrayLike, pos_label: int | str) -> np.ndarray:
+    """Returns a boolean array indicating positions of pos_label in input data.
+
+    Examples
+    --------
+    >>> from onekit import numpykit as npk
+    >>> data = [0, 1, 2, 1, 0, 1]
+    >>> npk.create_boolean_array(data, pos_label=1)
+    array([False,  True, False,  True, False,  True])
+
+    >>> data = ["cat", "dog", "cat", "bird", "cat", "dog"]
+    >>> npk.create_boolean_array(data, pos_label="dog")
+    array([False,  True, False, False, False,  True])
+    """
+    data_array = np.asarray(data)
+    return data_array == pos_label
+
+
 def digitscale(x: ArrayLike, /, *, kind: str = "log") -> np.ndarray:
     """NumPy version of digitscale.