pybear 0.2.0__tar.gz

pybear-0.2.0/CHANGELOG.md

@@ -0,0 +1,123 @@
+# Changelog
+
+All notable changes to this project will be documented in this file.
+
+The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.1.0/),
+and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
+
+
+
+## [0.2.0] - 2025-07-31
+
+### Added
+- base:
+    cast_to_ndarray,
+    check_1D_num_sequence,
+    check_1D_str_sequence,
+    check_2D_num_array,
+    check_2D_str_array,
+    check_dtype,
+    check_feature_names,
+    check_is_finite,
+    check_is_fitted,
+    check_n_features,
+    check_scipy_sparse,
+    check_shape,
+    copy_X,
+    DictMenuPrint,
+    ensure_2D,
+    get_feature_names,
+    get_feature_names_out,
+    is_fitted,
+    num_features,
+    num_samples,
+    set_order,
+    user_entry,
+    validate_data,
+    validate_user_float,
+    validate_user_int,
+    validate_user_mstr,
+    validate_user_str,
+    validate_user_str_cs,
+    ValidateUserDate,
+    FeatureMixin,
+    FileDumpMixin,
+    FitTransformMixin,
+    GetParamsMixin,
+    ReprMixin,
+    SetOutputMixin,
+    SetParamsMixin,
+    NotFittedError
+
+- feature_extraction
+    - text:
+        AutoTextCleaner,
+        Lexicon,
+        NGramMerger,
+        StopRemover
+        TextJoiner,
+        TextJustifier,
+        TextLookup,
+        TextLookupRealTime,
+        TextNormalizer,
+        TextPadder,
+        TextRemover,
+        TextReplacer,
+        TextSplitter,
+        TextStatistics,
+        TextStripper
+
+- model_selection:
+    autogridsearch_wrapper,
+    AutoGridSearchCV,
+    AutoGSTCV,
+    GSTCV
+
+- new_numpy:
+    - random:
+        choice,
+        Sparse
+        sparse
+
+- preprocessing:
+    ColumnDeduplicator,
+    InterceptManager,
+    MinCountTransformer,
+    NanStandardizer,
+    SlimPolyFeatures
+
+- utilities:
+    array_sparsity, 
+    check_pipeline,
+    feature_name_mapper,
+    get_module_name,
+    inf_mask,
+    nan_mask,
+    nan_mask_numerical,
+    nan_mask_string,
+    permuter,
+    serial_index_mapper,
+    time_memory_benchmark,
+    timer,
+    union_find
+
+
+### Changed
+- None
+
+### Deprecated
+- None
+
+### Removed
+- None
+
+### Fixed
+- None
+
+### Security
+- None
+
+## [0.1] - [Unreleased]
+
+
+

pybear-0.2.0/LICENSE

@@ -0,0 +1,28 @@
+BSD 3-Clause License
+
+Copyright (c) 2024, PylarBear
+
+Redistribution and use in source and binary forms, with or without
+modification, are permitted provided that the following conditions are met:
+
+1. Redistributions of source code must retain the above copyright notice, this
+   list of conditions and the following disclaimer.
+
+2. Redistributions in binary form must reproduce the above copyright notice,
+   this list of conditions and the following disclaimer in the documentation
+   and/or other materials provided with the distribution.
+
+3. Neither the name of the copyright holder nor the names of its
+   contributors may be used to endorse or promote products derived from
+   this software without specific prior written permission.
+
+THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
+AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
+DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT HOLDER OR CONTRIBUTORS BE LIABLE
+FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
+DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR
+SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER
+CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY,
+OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
+OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.

pybear-0.2.0/PKG-INFO

@@ -0,0 +1,367 @@
+Metadata-Version: 2.3
+Name: pybear
+Version: 0.2.0
+Summary: Python modules for miscellaneous data analytics applications
+License: BSD-3-Clause
+Keywords: python data analytics scikit-API text
+Author: Bill Sousa
+Author-email: WKSJR99@msn.com
+Maintainer: Bill Sousa
+Requires-Python: >=3.10,<3.14
+Classifier: License :: OSI Approved :: BSD License
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3.10
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Programming Language :: Python :: 3.13
+Requires-Dist: joblib (>=1.3.0)
+Requires-Dist: numpy (>=2.1.0)
+Requires-Dist: pandas (>=2.2.3)
+Requires-Dist: polars (>=1.19.0)
+Requires-Dist: psutil (>=5.7.0)
+Requires-Dist: scikit-learn (>=1.5.2)
+Requires-Dist: scipy (>=1.15.0)
+Requires-Dist: typing_extensions (>=4.12.0)
+Project-URL: Documentation, https://pybear.readthedocs.io/en/stable/
+Project-URL: Homepage, https://github.com/PylarBear/pybear
+Project-URL: Repository, https://github.com/PylarBear/pybear
+Description-Content-Type: text/x-rst
+
+pybear
+======
+
+|Tests|
+|Coverage|
+|Test Status 313|
+|Test Status 312|
+|Test Status 311|
+|Test Status 310|
+
+.. |Tests| image:: https://raw.githubusercontent.com/PylarBear/pybear/main/.github/badges/tests-badge.svg
+   :target: https://github.com/PylarBear/pybear/actions
+
+.. |Coverage| image:: https://raw.githubusercontent.com/PylarBear/pybear/main/.github/badges/coverage-badge.svg
+   :target: https://github.com/PylarBear/pybear/actions
+
+.. |Test Status 313| image:: https://github.com/PylarBear/pybear/actions/workflows/matrix-tests-py313.yml/badge.svg
+   :target: https://github.com/PylarBear/pybear/actions/workflows/matrix-tests-py313.yml
+
+.. |Test Status 312| image:: https://github.com/PylarBear/pybear/actions/workflows/matrix-tests-py312.yml/badge.svg
+   :target: https://github.com/PylarBear/pybear/actions/workflows/matrix-tests-py312.yml
+
+.. |Test Status 311| image:: https://github.com/PylarBear/pybear/actions/workflows/matrix-tests-py311.yml/badge.svg
+   :target: https://github.com/PylarBear/pybear/actions/workflows/matrix-tests-py311.yml
+
+.. |Test Status 310| image:: https://github.com/PylarBear/pybear/actions/workflows/matrix-tests-py310.yml/badge.svg
+   :target: https://github.com/PylarBear/pybear/actions/workflows/matrix-tests-py310.yml
+
+|Doc Status|
+
+.. |Doc Status| image:: https://readthedocs.org/projects/pybear/badge/?version=latest
+   :target: https://pybear.readthedocs.io/en/latest/?badge=latest
+   :alt: Documentation Status
+
+|TestPyPI Build Status|
+
+.. |TestPyPI Build Status| image:: https://github.com/PylarBear/pybear/actions/workflows/testpypi-publish.yml/badge.svg
+   :target: https://github.com/PylarBear/pybear/actions/workflows/testpypi-publish.yml
+
+|PyPI Build Status|
+|Version|
+|PyPI Downloads|
+
+.. |PyPI Build Status| image:: https://github.com/PylarBear/pybear/actions/workflows/pypi-publish.yml/badge.svg
+   :target: https://github.com/PylarBear/pybear/actions/workflows/pypi-publish.yml
+
+.. |Version| image:: https://img.shields.io/pypi/v/pybear
+   :target: https://pypi.org/project/pybear
+   :alt: PyPI Version
+
+.. |PyPI Downloads| image:: https://static.pepy.tech/badge/pybear
+   :target: https://pepy.tech/project/pybear
+   :alt: PyPI Downloads
+
+.. _documentation: https://pybear.readthedocs.io/
+
+.. |PythonVersion| replace:: >=3.10, <3.14
+.. |JoblibVersion| replace:: >=1.3.0
+.. |NumpyVersion| replace:: >=2.1.0
+.. |PandasVersion| replace:: >=2.2.3
+.. |PolarsVersion| replace:: >=1.19.0
+.. |PsutilVersion| replace:: >=5.7.0
+.. |PytestVersion| replace:: >=7.0.0
+.. |ScipyVersion| replace:: >=1.15.0
+.. |ScikitLearnVersion| replace:: >=1.5.2
+.. |TypingExtensionsVersion| replace:: >=4.12.0
+
+
+
+Cool, but not frozen, packages to augment your Python data analytics experience.
+
+pybear is a scikit-learn-style Python computing library that augments data
+analytics functionality found in popular packages like scikit-learn and xgboost.
+
+See documentation_ for more information.
+
+Website: https://pybear.readthedocs.io/en/stable/index.html
+
+License
+-------
+
+BSD 3-Clause License. See `License File <https://github.com/PylarBear/pybear/blob/main/LICENSE>`__.
+
+=======
+
+Installation
+------------
+
+Dependencies
+~~~~~~~~~~~~
+
+pybear requires:
+
+- Python (|PythonVersion|)
+- joblib (|JoblibVersion|)
+- numpy (|NumPyVersion|)
+- pandas (|PandasVersion|)
+- polars (|PolarsVersion|)
+- psutil (|PsutilVersion|)
+- scikit-learn (|ScikitLearnVersion|)
+- scipy (|ScipyVersion|)
+- typing_extensions (|TypingExtensionsVersion|)
+
+User installation
+~~~~~~~~~~~~~~~~~
+
+Install pybear from the online PyPI package repository using ``pip``::
+
+   (your-env) $ pip install pybear
+
+Conda distributions are expected to be made available sometime after release to
+PyPI.
+
+=======
+
+Usage
+-----
+The folder structure of pybear is nearly identical to scikit-learn. This is so
+those that are familiar with the scikit layout and have experience with writing
+the associated import statements have an easy transition to pybear. The pybear
+subfolders are *base*, *feature_extraction*, *model_selection*, *new_numpy*,
+*preprocessing*, and *utilities*. For the full layout, see the API section of
+the pybear website on Read The Docs.
+
+You can import pybear's packages in the same way you would with scikit. Here
+are a few examples of how you could import and use pybear modules:
+
+.. code-block:: console
+
+    from pybear.preprocessing import InterceptManager as IM
+
+    trfm = IM()
+    trfm.fit(X, y)
+
+    from pybear import preprocessing as pp
+
+    trfm = pp.ColumnDeduplicator()
+    trfm.fit(X, y)
+
+
+=======
+
+Major Modules
+-------------
+
+AutoGridSearchCV
+~~~~~~~~~~~~~~~~
+Perform multiple uninterrupted passes of grid search with sci-kit learn 
+GridSearchCV utilizing progressively narrower search grids.
+
+- Access via pybear.model_selection.AutoGridSearchCV.
+
+autogridsearch_wrapper
+~~~~~~~~~~~~~~~~~~~~~~
+Create your own auto-gridsearch class. A function that wraps any scikit-learn,
+pybear, or dask_ml GridSearchCV module to create an identical GridSearch class
+that performs multiple passes of grid search using progressively narrower
+search grids.
+
+- Access via pybear.model_selection.autogridsearch_wrapper.
+
+GSTCV (GridSearchThresholdCV)
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+Perform conventional grid search on a classifier with concurrent threshold 
+search. Finds the global optima for the passed parameters and thresholds. Fully
+compliant with the scikit-learn GridSearchCV API.
+
+- Access via pybear.model_selection.GSTCV.
+
+AutoGSTCV
+~~~~~~~~~
+Perform multiple uninterrupted passes of grid search with pybear GSTCV 
+utilizing progressively narrower search grids.
+
+- Access via pybear.model_selection.AutoGSTCV.
+
+MinCountTransformer
+~~~~~~~~~~~~~~~~~~~
+Perform minimum frequency thresholding on numerical or categorical data 
+simultaneously across an entire array of data. Violates the scikit-learn API 
+in that datasets are modified along the example axis (examples may be deleted.)
+Otherwise is fully compliant with the sci-kit learn transformer API, with fit, 
+transform, and partial_fit methods.
+
+- Access via pybear.preprocessing.MinCountTransformer.
+
+ColumnDeduplicator
+~~~~~~~~~~~~~~~~~~
+Identify and selectively remove duplicate columns in numerical or categorical 
+data. Fully compliant with the scikit-learn transformer API, with fit,
+transform, and partial_fit methods. Perfect for removing duplicate columns from
+one-hot encoded data in a scikit-learn pipeline. Also fits and transforms data 
+batch-wise, such as with dask_ml Incremental and ParallelPostFit wrappers.
+
+- Access via pybear.preprocessing.ColumnDeduplicator.
+
+InterceptManager
+~~~~~~~~~~~~~~~~
+A scikit-style transformer that identifies and manages constant columns in a 
+dataset. IM can remove all, selectively keep one, or append a column of 
+constants. Handles numerical & non-numerical data, and nan-like values. Does 
+batch-wise fitting via a partial_fit method, and can be wrapped with dask_ml 
+Incremental and ParallelPostFit wrappers.
+
+- Access via pybear.preprocessing.InterceptManager.
+
+SlimPolyFeatures
+~~~~~~~~~~~~~~~~
+Perform a polynomial feature expansion on a dataset omitting constant and 
+duplicate columns. Follows the standard scikit-learn transformer API. Handles 
+scipy sparse matrices/arrays. Suitable for sklearn pipelines. Has a partial_fit 
+method for batch-wise training and can be wrapped with dask_ml Incremental and
+ParallelPostFit wrappers.
+
+- Access via pybear.preprocessing.SlimPolyFeatures.
+
+
+The pybear Text Wrangling Suite
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+pybear has a wide selection of text wrangling tools for those who don't have a
+PhD in NLP. Most modules have the dual capability of working with regular
+expressions or literal strings (for those who don't know regular expressions!)
+Most of the modules also accept data in 1D list-like format or (ragged!) 2D
+array-like format. All of these are built in scikit transformer API style and
+can be stacked in a scikit pipeline.
+
+These modules can be found in pybear.feature_extraction.text.
+The modules include:
+
+- Lexicon - A class exposing 68,000+ English words and a stop words attribute
+- NGramMerger - Join select adjacent tokens together to handle as a single token
+- StopRemover - Remove pybear stop words from a body of text
+- TextJoiner - Join tokenized text into a contiguous string with separators
+- TextJustifier - Justify to a fixed margin; wrap on literals or regex patterns
+- TextLookup - Compare words in a body of text against the pybear Lexicon
+- TextLookupRealTime - Same as TextLookup but with in-situ save capability
+- TextNormalizer - Normalize text to the same case
+- TextPadder - Pad ragged text into shaped containers using fill
+- TextRemover - Remove units of contiguous text
+- TextReplacer - Remove substrings from contiguous text
+- TextSplitter - Split contiguous text into tokens using literal strings or regex
+- TextStatistics - Compile statistics about a body of text
+- TextStripper - Remove leading and trailing spaces from text
+
+
+=======
+
+Related Resources
+-----------------
+pybear has a sister package called pybear_dask. A few of the pybear modules
+have a corresponding twin in pybear-dask. You can pip install pybear-dask
+from PyPI in the same way as pybear. There is no Read The Docs website for
+pybear-dask, but it does have a GitHub repo.
+
+https://github.com/PylarBear/pybear-dask/
+
+Use the pybear documentation for guidance on how to use the pybear-dask modules.
+
+
+=======
+
+Changelog
+---------
+
+See the `changelog <https://github.com/PylarBear/pybear/blob/main/CHANGELOG.md>`__
+for a history of notable changes to pybear.
+
+=======
+
+Development
+-----------
+
+Important links
+~~~~~~~~~~~~~~~
+
+- Official source code repo: https://github.com/PylarBear/pybear
+- Download releases: https://test.pypi.org/project/pybear/ (pypi coming soon!)
+- Issue tracker: https://github.com/PylarBear/pybear/issues
+
+Source code
+~~~~~~~~~~~
+
+You can clone the latest source code with the command::
+
+    git clone https://github.com/PylarBear/pybear.git
+
+Contributing
+~~~~~~~~~~~~
+
+pybear is not ready for contributions at this time!
+
+Testing
+~~~~~~~
+
+pybear 0.2 is tested via GitHub Actions to run on Linux, Windows, and MacOS,
+with Python versions 3.10, 3.11, 3.12, and 3.13. pybear is not tested on earlier
+versions, but some features may work.
+
+If you want to test pybear yourself, you will need:
+
+- pytest (|PytestVersion|)
+
+The tests are not available in the PyPI pip installation. You can get
+the tests by downloading the tarball from the pybear project page on
+`pypi.org <https://pypi.org/project/pybear/>`_ or cloning the pybear repo from
+`GitHub <https://github.com/PylarBear/pybear>`_. Once you have the source files
+in a local project folder, create a poetry environment for the project and
+install the test dependencies. After installation, open the poetry environment
+shell and you can launch the test suite from the root of your pybear project
+folder with::
+
+    (your-pybear-env) you@your_computer:/path/to/pybear/project$ pytest tests/
+
+Project History
+---------------
+
+The project originated in the early 2020's as a collection of miscellaneous 
+private modules to enhance the python data analytics ecosystem. In 2025, the 
+modules were formalized and bundled together for their first release as pybear.
+
+Help and Support
+----------------
+
+Documentation
+~~~~~~~~~~~~~
+
+- HTML documentation: https://pybear.readthedocs.io/en/stable/api.html
+
+Communication
+~~~~~~~~~~~~~
+
+- GitHub Discussions: https://github.com/PylarBear/pybear/discussions
+
+
+
+
+
+