openstef 4.0.0a21

Open Short Term Energy forecasting library

OpenSTEF

OpenSTEF is a modular library for creating short-term forecasts in the energy sector. Version 4.0 introduces a complete architectural refactor with enhanced modularity, type safety, and modern Python development practices.

What's New in 4.0

• Modular Architecture: Install only the components you need
• Modern Tooling: Built with uv, ruff, pyright, and poe for optimal developer experience
• Full Type Safety: Comprehensive type hints throughout the codebase
• Monorepo Structure: Unified development with specialized packages
• Enhanced Workflows: Streamlined development and contribution processes

Table of Contents

• OpenSTEF
  • What's New in 4.0
  • Table of Contents
  • Quick Start
  • Package Architecture
  • Installation
    • Requirements
    • Basic Installation
    • Modern Package Managers
  • Documentation
  • Contributing
    • Quick Development Setup
  • License
  • Contact & Support

Quick Start

# Install OpenSTEF
pip install openstef

# Start forecasting
python -c "import openstef_models; print('OpenSTEF 4.0 ready!')"

Get started with our Quick Start Guide - step-by-step tutorial with real examples.

Package Architecture

OpenSTEF 4.0 uses a modular design with specialized packages:

Package	Purpose	Install Command
openstef	Meta-package with core components	pip install openstef
openstef-models	ML models, feature engineering, data processing	pip install openstef-models
openstef-beam	Backtesting, Evaluation, Analysis, Metrics	pip install openstef-beam
openstef-core	Core utilities, dataset types, shared types and base models used by other packages	pip install openstef-core
openstef-compatibility	OpenSTEF 3.x compatibility layer	Coming soon
openstef-foundational-models	Deep learning and foundational models	Coming soon

Learn more about the architecture in our documentation.

Installation

Requirements

• Python 3.12+ (Python 3.13 supported)
• 64-bit operating system (Windows, macOS, Linux)

Basic Installation

# For most users
pip install openstef

# Core forecasting only
pip install openstef-models

# With all optional tools
pip install "openstef[all]"

Modern Package Managers

# Using uv (recommended for development)
uv add openstef

# Using conda
conda install -c conda-forge openstef

Complete Installation Guide - detailed instructions including troubleshooting for Apple Silicon, GPU support, and development setup.

Documentation

• Main Documentation - guides and API reference
• Quick Start Guide - get up and running fast
• Tutorials - step-by-step examples
• API Reference - detailed function documentation
• Contributing Guide - how to contribute to OpenSTEF

Contributing

We welcome contributions to OpenSTEF 4.0!

Read our Contributing Guide - documentation for contributors including:

• How to report bugs and suggest features
• Documentation improvements and examples
• Code contributions and development setup
• Sharing datasets and real-world use cases

Quick Development Setup

# Clone and set up for development
git clone https://github.com/OpenSTEF/openstef.git
cd openstef
uv sync --dev

# Run tests and quality checks
uv run poe all

Code of Conduct: We follow the Contributor Code of Conduct to ensure a welcoming environment for all contributors.

License

Mozilla Public License Version 2.0 - see LICENSE.md for details.

This project includes third-party libraries licensed under their respective Open-Source licenses. SPDX-License-Identifier headers show applicable licenses. License files are in the LICENSES/ directory.

Contact & Support

• Support Guide - how to get help
• GitHub Discussions - community Q&A and discussions
• Issue Tracker - bug reports and feature requests
• LF Energy OpenSTEF - project homepage