Repository of structured JSON datasets containing football match fixtures and results across major European leagues (English Premier League, Bundesliga, Serie A, La Liga, UEFA Champions League) spanning 2011-2027. Files are auto-generated from upstream Football.TXT text sources via a GitHub Actions workflow that refreshes data daily. Each league/season file follows a consistent schema: a top-level object with league metadata and a `matches` array containing per-match objects with round, date, teams, and score objects (half-time, full-time, optionally extra time and penalties). The repository is purely a data source - no application code, scripts, tests, or configuration beyond the JSON files. Raw GitHub links serve as a free public API for web applications, mobile apps, prediction models, or analytics pipelines. The data is clean and machine-readable but lacks schema validation, versioning, and formal documentation. Known issues include schema drift across seasons (missing half-time scores, awarded matches with `status: 'awarded'`, team name variations) that downstream consumers must handle defensively. The primary value is the breadth and consistency of match data across 15+ leagues and 15+ seasons, making it suitable for football statistics applications, prediction models, or league visualization tools. The auto-update pipeline keeps current seasons fresh, but upstream Football.TXT sources may not be maintained for older seasons, and the lack of schema enforcement risks silent data drift. This is a data_research repository - a data source rather than an application - with no executable code or processing pipeline present.
This repository implements an end-to-end predictive modeling pipeline for Premier League football match outcomes (home win, draw, away win). It ingests raw match statistics from the api-football.com REST API, processes JSON data into structured DataFrames, engineers features using rolling averages (5- and 10-game windows) and team-vs-opponent differentials, trains multiple classifiers (Random Forest, SVM, KNN, MLP) with hyperparameter tuning, and serves live predictions via a Flask web application. The dominant character is data research: the primary deliverable is a set of trained models and an analytical pipeline, with the web server being a secondary deployment artifact. The best-performing model is a Random Forest achieving ~50-51% test accuracy, demonstrating that football outcomes are modestly predictable from historical statistics. The codebase includes modular helper modules for feature engineering, data scaling, and evaluation plotting that are reusable for other sports or time-series classification tasks. However, the project suffers from hardcoded absolute paths, outdated dependencies (Python 3.7, sklearn 0.23.1), plain-text API keys in the repository, and a static dataset that will drift over time.