🏎️ iRacing Stats Calculator

A comprehensive desktop application to analyze and visualize your iRacing statistics with integrated Machine Learning for intelligent predictions.

✨ Main Features

📊 Complete Statistics Analysis

• General statistics: Total races, laps, incidents, championship points
• Positions: Wins, podiums, Top 5, Top 10, DNFs
• Averages: Starting position, finishing position, positions gained/lost
• Consistency Score: Measures your regularity using standard deviation
• Series analysis: Statistics broken down by each iRacing series
• Track analysis: Performance at each circuit

📈 Data Visualization

• Position trend chart: Evolution of your starting vs finishing positions
• Incidents chart: Incident history per race with danger zones
• Championship points chart: Point accumulation over time
• SOF (Strength of Field) analysis: Distribution of race difficulty
• Interactive charts with integrated dark theme

🤖 Integrated Machine Learning

• Position prediction: The model learns from your history to predict your next position
• Incident prediction: Estimates how many incidents you might have
• Factor analysis: Identifies which factors affect your performance the most
• Persistent model: The model saves and improves with each session
• Smart insights: Personalized recommendations based on your data

🎯 Projection System

• Linear regression: Projects your future performance
• Trend analysis: Detects if you're improving, declining, or stable
• Points projection: Estimates your future championship points
• Confidence intervals: Prediction ranges with certainty levels

🎨 Modern Interface

• Native Dark Mode: Professional dark theme GitHub-style
• Responsive design: Adapts to different window sizes
• Tab navigation: Clear organization of information
• Stats cards: Quick visualization of key metrics

🚀 Installation

Requirements

• Python 3.8 or higher
• Windows 10/11

Installation from source

# Clone the repository
git clone https://github.com/D0PZ/iRacing-Stats-Calc.git
cd iRacing-Stats-Calc

# Install dependencies
pip install -r requirements.txt

# Run the application
python main.py

Dependencies

matplotlib>=3.5.0
scikit-learn>=1.0.0
numpy>=1.20.0
joblib>=1.0.0

📖 Usage

1. Export data from iRacing

1. Go to iRacing Members Site
2. Navigate to Stats → Series Stats
3. Select the series you want to analyze
4. Click Export to download the JSON file

2. Load data into the application

1. Open iRacing Stats Calculator
2. Click 📂 Load JSON
3. Select the exported file from iRacing
4. Explore your statistics!

3. Train the ML model

1. Go to the 🤖 Machine Learning tab
2. Click 🎓 Train Model
3. The model will learn from your historical data
4. Get personalized predictions and recommendations

🛠️ Project Structure

iRacing-Stats-Calc/
├── main.py                 # Entry point
├── requirements.txt        # Dependencies
├── README.md              # Documentation
├── app/
│   ├── __init__.py
│   ├── gui.py             # Graphical interface (Tkinter)
│   ├── data_loader.py     # JSON data loading and parsing
│   ├── stats_calculator.py # Statistical calculations
│   ├── projections.py     # Projection engine
│   ├── charts.py          # Chart generator (Matplotlib)
│   └── ml_engine.py       # Machine Learning engine
└── build/                 # Build files

📊 Calculated Statistics

Metric	Description
Total Races	Total number of races
Wins	Victories (P1)
Podiums	Positions 1-3
Top 5 / Top 10	Positions within the top
DNFs	Did Not Finish races
Avg Finish	Average finishing position
Avg Start	Average starting position
Avg Gain	Average positions gained/lost
Avg Incidents	Average incidents per race
Consistency	Standard deviation of positions
Laps Led	Laps led
Championship Points	Total championship points

🤖 Machine Learning Models

The application uses several scikit-learn algorithms:

• Random Forest Regressor: Main position prediction
• Gradient Boosting Regressor: High-performance alternative model
• Linear Regression: Base for comparison and projections
• K-Means Clustering: Race type grouping

Model Features

• Automatic persistence of trained model
• Training history
• Accuracy and confidence metrics
• Feature importance

🔧 Build Executable

To create a standalone executable:

# Install PyInstaller
pip install pyinstaller

# Build
python build_exe.py

The executable will be generated in the dist/ folder.

🤝 Contributing

Contributions are welcome! Please:

1. Fork the repository
2. Create a branch for your feature (git checkout -b feature/NewFeature)
3. Commit your changes (git commit -m 'Add new feature')
4. Push to the branch (git push origin feature/NewFeature)
5. Open a Pull Request

📝 License

This project is under the MIT License. See the LICENSE file for more details.

🙏 Acknowledgments

• iRacing for the platform and data API
• Matplotlib for visualizations
• scikit-learn for Machine Learning

---

Made with ❤️ for the iRacing community