Science Score: 44.0%
This score indicates how likely this project is to be science-related based on various indicators:
-
✓CITATION.cff file
Found CITATION.cff file -
✓codemeta.json file
Found codemeta.json file -
✓.zenodo.json file
Found .zenodo.json file -
○DOI references
-
○Academic publication links
-
○Academic email domains
-
○Institutional organization owner
-
○JOSS paper metadata
-
○Scientific vocabulary similarity
Low similarity (15.1%) to scientific vocabulary
Repository
Basic Info
- Host: GitHub
- Owner: bf-malefiz
- Language: Python
- Default Branch: main
- Size: 9.23 MB
Statistics
- Stars: 0
- Watchers: 1
- Forks: 0
- Open Issues: 0
- Releases: 0
Metadata Files
README.md
⚽ Bundesliga Match Prediction Framework
A modular framework for probabilistic football match predictions, built with Kedro for pipeline orchestration and MLflow for experiment tracking. Developed as part of a B.Sc. thesis at HTW Berlin.
📖 Overview
This repository contains a reproducible machine learning system for: - Probabilistic modeling of football matches using PyMC and Pyro - Walk-Forward Validation for time-series predictions - Modular architecture to compare different engines/models - Experiment tracking with metrics visualization - End-to-end pipeline from data processing to model evaluation
🚀 Quick Start
Installation
```bash
Create conda environment with PyMC dependencies
conda create -c conda-forge -n bl-prediction "pymc>=5" pyro-ppl conda activate bl-prediction
Install project requirements
pip install -r requirements.txt ```
Run Pipelines
```bash
Train models (all engines)
kedro run
Run specific engine (e.g., Pyro)
kedro run --pipeline "pyro" ```
Visualize Results
```bash
Pipeline structure (http://localhost:4141/)
kedro viz
Experiment metrics (http://localhost:5000)
mlflow ui ```
🔧 Configuration
Configure models and parameters in:
- conf/base/parameters.yml - Model hyperparameters
- conf/base/datasets_list.yml - Data sources
- settings.py - Engine/model registry
📚 Documentation
For detailed usage, architecture, and extension guide:
📘 See Documentation - htmlpreview
For a better experience download the documentation and open it localy
📜 License
This project is licensed under the MIT License - see the LICENSE file for details.
Citation (CITATION.cff)
cff-version: 1.2.0
message: "If you use this software, please cite it as below."
authors:
- family-names: Dahlke
given-names: Philipp
orcid:
title: "BA - Bayesian Model Evaluation"
version: 1.0.0
identifiers:
- type: doi
value: 10.5281/zenodo.1234
date-released: 2025-02-17
url: "https://github.com/bf-malefiz/ba_env"
GitHub Events
Total
- Push event: 31
- Public event: 1
- Pull request event: 2
Last Year
- Push event: 31
- Public event: 1
- Pull request event: 2
Issues and Pull Requests
Last synced: 10 months ago
All Time
- Total issues: 0
- Total pull requests: 1
- Average time to close issues: N/A
- Average time to close pull requests: 2 minutes
- Total issue authors: 0
- Total pull request authors: 1
- Average comments per issue: 0
- Average comments per pull request: 0.0
- Merged pull requests: 1
- Bot issues: 0
- Bot pull requests: 0
Past Year
- Issues: 0
- Pull requests: 1
- Average time to close issues: N/A
- Average time to close pull requests: 2 minutes
- Issue authors: 0
- Pull request authors: 1
- Average comments per issue: 0
- Average comments per pull request: 0.0
- Merged pull requests: 1
- Bot issues: 0
- Bot pull requests: 0
Top Authors
Issue Authors
Pull Request Authors
- bf-malefiz (1)
Top Labels
Issue Labels
Pull Request Labels
Dependencies
- aesara *
- hypothesis *
- ipython >=8.10
- jupyterlab >=3.0
- kedro *
- kedro-datasets >=3.0
- kedro-mlflow *
- kedro-viz >=6.7.0
- mlflow *
- notebook *
- numpy ==1.26.4
- pre-commit *
- pymc-experimental *
- pyro-ppl *
- pytest *
- pytest-cov *
- ruff *
- scikit-learn *
- statsd *
- 237 dependencies