df-eval 0.1.1__tar.gz

df_eval-0.1.1/.github/workflows/ci.yml

@@ -0,0 +1,80 @@
+name: CI
+
+on:
+  push:
+    branches: [ main ]
+  pull_request:
+    branches: [ main ]
+
+permissions:
+  contents: read
+
+jobs:
+  test:
+    runs-on: ubuntu-latest
+    strategy:
+      matrix:
+        python-version: ["3.11", "3.12", "3.13"]
+    
+    steps:
+    - uses: actions/checkout@v4
+    
+    - name: Install uv
+      uses: astral-sh/setup-uv@v5
+      with:
+        enable-cache: true
+    
+    - name: Set up Python ${{ matrix.python-version }}
+      uses: actions/setup-python@v5
+      with:
+        python-version: ${{ matrix.python-version }}
+    
+    - name: Install dependencies
+      run: |
+        uv sync --all-extras
+    
+    - name: Run tests
+      run: |
+        uv run pytest --cov=df_eval --cov-report=xml --cov-report=term
+    
+    - name: Upload coverage to Codecov
+      uses: codecov/codecov-action@v4
+      if: matrix.python-version == '3.11'
+      with:
+        file: ./coverage.xml
+        flags: unittests
+        name: codecov-umbrella
+        fail_ci_if_error: false
+
+  docs:
+    runs-on: ubuntu-latest
+    permissions:
+      contents: read
+    
+    steps:
+    - uses: actions/checkout@v4
+    
+    - name: Install uv
+      uses: astral-sh/setup-uv@v5
+      with:
+        enable-cache: true
+    
+    - name: Set up Python
+      uses: actions/setup-python@v5
+      with:
+        python-version: "3.11"
+    
+    - name: Install dependencies
+      run: |
+        uv sync --all-extras
+    
+    - name: Build documentation
+      run: |
+        cd docs
+        uv run sphinx-build -b html . _build/html -W
+    
+    - name: Upload documentation artifacts
+      uses: actions/upload-artifact@v4
+      with:
+        name: documentation
+        path: docs/_build/html

df_eval-0.1.1/.github/workflows/docs.yml

@@ -0,0 +1,48 @@
+name: docs
+
+on:
+  push:
+    branches: [ main ]
+
+permissions:
+  contents: read
+  pages: write
+  id-token: write
+
+jobs:
+  build:
+    runs-on: ubuntu-latest
+    steps:
+      - name: Checkout
+        uses: actions/checkout@v4
+
+      - name: Set up Python
+        uses: actions/setup-python@v5
+        with:
+          python-version: "3.11"
+
+      - name: Install uv
+        uses: astral-sh/setup-uv@v5
+
+      - name: Install dependencies
+        run: uv sync --extra dev
+
+      - name: Build Sphinx HTML
+        run: |
+          uv run sphinx-build -b html docs docs/_build/html
+
+      - name: Upload Pages artifact
+        uses: actions/upload-pages-artifact@v3
+        with:
+          path: docs/_build/html
+
+  deploy:
+    needs: build
+    runs-on: ubuntu-latest
+    environment:
+      name: github-pages
+      url: ${{ steps.deployment.outputs.page_url }}
+    steps:
+      - name: Deploy to GitHub Pages
+        id: deployment
+        uses: actions/deploy-pages@v4

df_eval-0.1.1/.github/workflows/publish_to_pypi.yml

@@ -0,0 +1,44 @@
+
+name: Publish to PyPI
+
+on:
+  release:
+    types: [published]
+  workflow_dispatch:
+
+jobs:
+  publish:
+    runs-on: ubuntu-latest
+    permissions:
+      id-token: write
+      contents: read
+
+    steps:
+      - name: Checkout code
+        uses: actions/checkout@v4
+
+      - name: Set up Python
+        uses: actions/setup-python@v5
+        with:
+          python-version: "3.12"
+
+      - name: Install uv
+        run: pip install uv
+
+      # ✅ Sync dependencies from uv.lock
+      - name: Sync dependencies
+        run: uv sync --frozen
+
+      # ✅ Install packaging tools
+      - name: Install build tools
+        run: uv pip install build twine
+
+      # ✅ Build the package
+      - name: Build package
+        run: uv run python -m build
+
+      # ✅ Publish to PyPI using Trusted Publisher
+      - name: Publish to PyPI
+        uses: pypa/gh-action-pypi-publish@release/v1
+        with:
+          skip-existing: true

df_eval-0.1.1/.gitignore

@@ -0,0 +1,208 @@
+ Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[codz]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+share/python-wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# PyInstaller
+#  Usually these files are written by a python script from a template
+#  before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.nox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+*.py.cover
+.hypothesis/
+.pytest_cache/
+cover/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+db.sqlite3
+db.sqlite3-journal
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+.pybuilder/
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+#   For a library or package, you might want to ignore these files since the code is
+#   intended to run in multiple environments; otherwise, check them in:
+# .python-version
+
+# pipenv
+#   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
+#   However, in case of collaboration, if having platform-specific dependencies or dependencies
+#   having no cross-platform support, pipenv may install dependencies that don't work, or not
+#   install all needed dependencies.
+#Pipfile.lock
+
+# UV
+#   Similar to Pipfile.lock, it is generally recommended to include uv.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+#uv.lock
+
+# poetry
+#   Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+#   https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control
+#poetry.lock
+#poetry.toml
+
+# pdm
+#   Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
+#   pdm recommends including project-wide configuration in pdm.toml, but excluding .pdm-python.
+#   https://pdm-project.org/en/latest/usage/project/#working-with-version-control
+#pdm.lock
+#pdm.toml
+.pdm-python
+.pdm-build/
+
+# pixi
+#   Similar to Pipfile.lock, it is generally recommended to include pixi.lock in version control.
+#pixi.lock
+#   Pixi creates a virtual environment in the .pixi directory, just like venv module creates one
+#   in the .venv directory. It is recommended not to include this directory in version control.
+.pixi
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm
+__pypackages__/
+
+# Celery stuff
+celerybeat-schedule
+celerybeat.pid
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.envrc
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+.dmypy.json
+dmypy.json
+
+# Pyre type checker
+.pyre/
+
+# pytype static type analyzer
+.pytype/
+
+# Cython debug symbols
+cython_debug/
+
+# PyCharm
+#  JetBrains specific template is maintained in a separate JetBrains.gitignore that can
+#  be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore
+#  and can be added to the global gitignore or merged into this file.  For a more nuclear
+#  option (not recommended) you can uncomment the following to ignore the entire idea folder.
+#.idea/
+
+# Abstra
+# Abstra is an AI-powered process automation framework.
+# Ignore directories containing user credentials, local state, and settings.
+# Learn more at https://abstra.io/docs
+.abstra/
+
+# Visual Studio Code
+#  Visual Studio Code specific template is maintained in a separate VisualStudioCode.gitignore 
+#  that can be found at https://github.com/github/gitignore/blob/main/Global/VisualStudioCode.gitignore
+#  and can be added to the global gitignore or merged into this file. However, if you prefer, 
+#  you could uncomment the following to ignore the entire vscode folder
+# .vscode/
+
+# Ruff stuff:
+.ruff_cache/
+
+# PyPI configuration file
+.pypirc
+
+# Cursor
+#  Cursor is an AI-powered code editor. `.cursorignore` specifies files/directories to
+#  exclude from AI features like autocomplete and code analysis. Recommended for sensitive data
+#  refer to https://docs.cursor.com/context/ignore-files
+.cursorignore
+.cursorindexingignore
+
+# Marimo
+marimo/_static/
+marimo/_lsp/
+__marimo__/
+/docs/auto_examples/

df_eval-0.1.1/CONTRIBUTING.md

@@ -0,0 +1,34 @@
+
+# Documentation Policy
+
+## README.md
+- The root `README.md` is the **only Markdown file** in the project.
+- It serves as the landing page for **GitHub** and **PyPI** and may be included in Sphinx as the index page.
+
+## Sphinx Documentation
+- All documentation under `docs/` **must use reStructuredText (`.rst`)** format.
+- Markdown files are **not allowed** in `docs/` except for the root `README.md`.
+- Use Sphinx directives and roles for cross-referencing and advanced features.
+
+## Heading Style for `.rst`
+- One **double underline heading** at the top of the page (Level 1).
+- Subsequent headings use **single underline** (Level 2) or `^` for Level 3 as needed.
+- Example:
+    ```rst
+    Main Title
+    ==========
+    
+    Section
+    --------
+    
+    Subsection
+    ^^^^^^^^^^
+    ```
+
+## Tools & Standards
+- Use **Google-style docstrings** in Python code.
+- Use `pathlib.Path` for file paths.
+- Follow best practices for Python programming:
+    - Object-Oriented Programming (OOP) where appropriate.
+    - Sphinx for documentation with `.rst` files.
+``

df_eval-0.1.1/LICENSE

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2026 Greg Elphick
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.

df_eval-0.1.1/PKG-INFO

@@ -0,0 +1,206 @@
+Metadata-Version: 2.4
+Name: df-eval
+Version: 0.1.1
+Summary: A lightweight expression evaluation engine for pandas DataFrames
+Author: Greg Elphick
+License: MIT
+License-File: LICENSE
+Classifier: Development Status :: 3 - Alpha
+Classifier: Intended Audience :: Developers
+Classifier: License :: OSI Approved :: MIT License
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Programming Language :: Python :: 3.13
+Requires-Python: >=3.11
+Requires-Dist: pandas>=2.0.0
+Provides-Extra: all
+Requires-Dist: black>=23.0.0; extra == 'all'
+Requires-Dist: frictionless>=4.0.0; extra == 'all'
+Requires-Dist: pandera[io]>=0.20.0; extra == 'all'
+Requires-Dist: pyarrow>=15.0.0; extra == 'all'
+Provides-Extra: dev
+Requires-Dist: matplotlib>=3.8.0; extra == 'dev'
+Requires-Dist: myst-parser>=2.0.0; extra == 'dev'
+Requires-Dist: pandera>=0.20.0; extra == 'dev'
+Requires-Dist: pyarrow>=15.0.0; extra == 'dev'
+Requires-Dist: pytest-cov>=4.0.0; extra == 'dev'
+Requires-Dist: pytest>=7.0.0; extra == 'dev'
+Requires-Dist: sphinx-autodoc-typehints>=1.24.0; extra == 'dev'
+Requires-Dist: sphinx-book-theme>=1.0.0; extra == 'dev'
+Requires-Dist: sphinx-gallery>=0.16.0; extra == 'dev'
+Requires-Dist: sphinx>=7.0.0; extra == 'dev'
+Provides-Extra: pandera
+Requires-Dist: black>=23.0.0; extra == 'pandera'
+Requires-Dist: frictionless>=4.0.0; extra == 'pandera'
+Requires-Dist: pandera[io]>=0.20.0; extra == 'pandera'
+Provides-Extra: parquet
+Requires-Dist: pyarrow>=15.0.0; extra == 'parquet'
+Description-Content-Type: text/markdown
+
+# df-eval
+
+<p align="center">
+  <img src="https://raw.githubusercontent.com/elphick/df-eval/main/docs/_static/branding/df-eval-icon.svg" alt="df-eval icon" width="120" />
+</p>
+
+[![CI](https://github.com/elphick/df-eval/actions/workflows/ci.yml/badge.svg)](https://github.com/elphick/df-eval/actions/workflows/ci.yml)
+[![Documentation](https://github.com/elphick/df-eval/actions/workflows/docs.yml/badge.svg)](https://github.com/elphick/df-eval/actions/workflows/docs.yml)
+[![Python 3.11+](https://img.shields.io/badge/python-3.11+-blue.svg)](https://www.python.org/downloads/)
+[![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](https://opensource.org/licenses/MIT)
+[![Code style: black](https://img.shields.io/badge/code%20style-black-000000.svg)](https://github.com/psf/black)
+
+A lightweight expression evaluation engine for pandas DataFrames, supporting schema-driven derived columns and external lookups.
+
+## Overview
+
+**df-eval** is a Python library that provides a flexible and efficient way to evaluate expressions on pandas DataFrames. It's designed for scenarios where you need to:
+
+- Apply complex transformations to DataFrames using string expressions
+- Define schemas of derived columns that depend on existing columns
+- Register custom functions (UDFs) and constants for use in expressions
+- Use safe, allow-listed functions (abs, log, exp, sqrt, clip, where, isna, fillna)
+- Handle dependencies between derived columns with automatic topological ordering
+- Perform lookups from external data sources (files, databases, HTTP APIs)
+- Track provenance of derived columns
+- Maintain clean, readable code for data transformations
+
+## Features
+
+- **Safe Expression Evaluation**: Allow-listed vectorized functions for secure evaluation
+- **UDF and Constant Registry**: Register custom functions and constants
+- **Schema-Driven Columns**: Define multiple derived columns with automatic dependency resolution
+- **Topological Ordering**: Automatically resolve dependencies between columns
+- **Cycle Detection**: Detect and report circular dependencies
+- **Dtype Casting**: Specify output types for derived columns
+- **Provenance Tracking**: Track the origin and dependencies of derived columns
+- **Lookup Functionality**: Resolve values from external sources with caching
+- **Type-Safe**: Built with Python 3.11+ type hints
+- **Well-Tested**: Comprehensive test suite with 95%+ coverage
+- **Well-Documented**: Full documentation with Sphinx
+- **Backend Seam**: Designed for future Arrow/Polars support
+
+## Installation
+
+```bash
+pip install df-eval
+```
+
+For development:
+
+```bash
+git clone https://github.com/elphick/df-eval.git
+cd df-eval
+uv sync
+```
+
+## Quick Start
+
+### Basic Expression Evaluation
+
+```python
+import pandas as pd
+from df_eval import Engine
+
+# Create a DataFrame
+df = pd.DataFrame({
+    "a": [1, 2, 3],
+    "b": [4, 5, 6]
+})
+
+# Create an engine
+engine = Engine()
+
+# Evaluate an expression
+result = engine.evaluate(df, "a + b")
+print(result)  # [5, 7, 9]
+```
+
+### Schema-Driven Derived Columns
+
+```python
+# Define a schema with dependent columns
+schema = {
+    "sum": "a + b",
+    "product": "a * b",
+    "ratio": "a / b"
+}
+
+df_with_derived = engine.apply_schema(df, schema)
+print(df_with_derived)
+```
+
+### Using Allow-Listed Safe Functions
+
+```python
+# Use safe, allow-listed functions
+schema = {
+    "abs_a": "abs(a)",
+    "log_b": "log(b)",
+    "sqrt_sum": "sqrt(a + b)",
+    "clipped": "clip(a, 0, 2)"
+}
+
+result = engine.apply_schema(df, schema)
+```
+
+### Register Custom Functions (UDFs)
+
+```python
+# Register a custom function
+def custom_transform(x):
+    return x ** 2 + 10
+
+engine.register_function("transform", custom_transform)
+
+# Use it in expressions
+result = engine.evaluate(df, "transform(a)")
+```
+
+## Built-in Functions
+
+The library provides several allow-listed safe functions:
+
+- `abs(x)`: Absolute value
+- `log(x)`: Natural logarithm (handles negative values safely)
+- `exp(x)`: Exponential function (handles overflow safely)
+- `sqrt(x)`: Square root (handles negative values safely)
+- `clip(x, min, max)`: Clip values to a range
+- `where(condition, x, y)`: Conditional selection
+- `isna(x)`: Check for NaN/None values
+- `fillna(x, value)`: Fill NaN/None with a value
+- `safe_divide(a, b)`: Division with NaN for divide-by-zero
+- `coalesce(*args)`: Return first non-null value
+
+## Documentation
+
+For comprehensive documentation including advanced usage, API reference, and more examples, visit the [full documentation](https://elphick.github.io/df-eval/).
+
+## Requirements
+
+- Python 3.11 or higher
+- pandas >= 2.0.0
+- numpy >= 1.26.0
+
+## Development
+
+### Running Tests
+
+```bash
+uv run pytest
+```
+
+### Building Documentation
+
+```bash
+cd docs
+uv run sphinx-build -b html . _build/html
+```
+
+## Contributing
+
+Contributions are welcome! Please feel free to submit a Pull Request.
+
+## License
+
+This project is licensed under the MIT License - see the LICENSE file for details.