Skip to main content

​
Prerequisites

Before installing the F1 ML Prediction System, ensure you have:
  • Python 3.8+ installed on your system
  • pip package manager
  • Git for version control
  • At least 2GB of free disk space for data and models
  • Stable internet connection for data collection
This project uses FastF1 API which requires an active internet connection for initial data collection.

​
Quick Start Installation

1

Create Project Directory

Create a dedicated directory for your F1 ML project:
mkdir f1-ml-project
cd f1-ml-project
2

Set Up Virtual Environment

Create and activate a Python virtual environment:
python -m venv venv
source venv/bin/activate
You should see (venv) prefix in your terminal once activated.
3

Install Dependencies

Create a requirements.txt file with the following dependencies:
requirements.txt
# Core Data Science
pandas==2.1.4
numpy==1.26.2
scipy==1.11.4

# F1 Data
fastf1==3.2.0

# Machine Learning
scikit-learn==1.3.2
tensorflow==2.15.0
keras==2.15.0
xgboost==2.0.3
lightgbm==4.1.0

# Data Visualization
matplotlib==3.8.2
seaborn==0.13.0
plotly==5.18.0

# Web Framework
flask==3.0.0
dash==2.14.2
dash-bootstrap-components==1.5.0

# Utilities
jupyter==1.0.0
notebook==7.0.6
python-dotenv==1.0.0
tqdm==4.66.1

# Data Processing
openpyxl==3.1.2
requests==2.31.0
Install all dependencies:
pip install -r requirements.txt
Installation may take 5-10 minutes depending on your internet speed. TensorFlow is the largest dependency (~500MB).
4

Create Project Structure

Run the automated setup script to create the complete directory structure:
setup_project.py
import os

# Create directory structure
directories = [
    'data/raw',
    'data/processed',
    'data/cache',
    'notebooks',
    'src/data',
    'src/models',
    'src/utils',
    'frontend/static/css',
    'frontend/static/js',
    'frontend/templates',
    'models/saved_models',
    'logs'
]

for directory in directories:
    os.makedirs(directory, exist_ok=True)
    print(f"✓ Created: {directory}")

# Create __init__.py files
init_files = [
    'src/__init__.py',
    'src/data/__init__.py',
    'src/models/__init__.py',
    'src/utils/__init__.py'
]

for init_file in init_files:
    with open(init_file, 'w') as f:
        f.write('# F1 ML Project\n')
    print(f"✓ Created: {init_file}")

print("\n✅ Project structure created successfully!")
Execute the setup:
python setup_project.py
Expected Output:
✓ Created: data/raw
✓ Created: data/processed
✓ Created: data/cache
...
✅ Project structure created successfully!
5

Verify Installation

Verify all dependencies are correctly installed:
# verify_installation.py
import sys

packages = [
    'pandas', 'numpy', 'sklearn', 'tensorflow',
    'xgboost', 'fastf1', 'flask', 'plotly'
]

print("Verifying installation...\n")

for package in packages:
    try:
        __import__(package)
        print(f"✓ {package:15} installed")
    except ImportError:
        print(f"✗ {package:15} MISSING")
        sys.exit(1)

print("\n✅ All packages installed successfully!")
print(f"Python version: {sys.version}")
Run verification:
python verify_installation.py

​
Final Project Structure

After installation, your directory should look like this: 
f1-ml-project/
├── data/
│   ├── raw/                    # Raw F1 data (CSV files)
│   ├── processed/              # Engineered features
│   └── cache/                  # FastF1 cache
├── notebooks/                  # Jupyter notebooks
├── src/
│   ├── data/                   # Data collection scripts
│   ├── models/                 # ML model definitions
│   └── utils/                  # Helper functions
├── frontend/
│   ├── static/                 # CSS, JS assets
│   └── templates/              # HTML templates
├── models/
│   └── saved_models/           # Trained model files
├── logs/                       # Application logs
├── requirements.txt            # Python dependencies
└── setup_project.py            # Setup automation script

​
Troubleshooting

​
”Module not found” Errors

If you encounter import errors: 
# Ensure virtual environment is activated
source venv/bin/activate  # macOS/Linux
venv\Scripts\activate     # Windows

# Reinstall dependencies
pip install --upgrade pip
pip install -r requirements.txt

​
TensorFlow Installation Issues

On macOS with Apple Silicon (M1/M2): 
# Use TensorFlow Metal plugin
pip install tensorflow-metal
On Windows with GPU: 
# Install CUDA-compatible version
pip install tensorflow-gpu==2.15.0

​
FastF1 Cache Errors

Configure FastF1 cache directory: 
import fastf1

# Set custom cache location
fastf1.Cache.enable_cache('./data/cache')

​
Port Already in Use (Flask)

If port 5000 is occupied: 
# Find process using port 5000
lsof -i :5000
kill -9 <PID>
Or use a different port: 
app.run(host='0.0.0.0', port=8080)

​
Environment Variables

Create a .env file for configuration (optional):
.env
# Flask Configuration
FLASK_ENV=development
FLASK_DEBUG=True

# Data Collection
DATA_START_YEAR=2018
DATA_END_YEAR=2024
CACHE_DIR=./data/cache

# Model Training
RANDOM_STATE=42
TEST_SIZE=0.2
N_ESTIMATORS=100
Load environment variables in your code: 
from dotenv import load_dotenv
import os

load_dotenv()

cache_dir = os.getenv('CACHE_DIR', './data/cache')

​
System Requirements

​
Minimum Requirements

  • CPU: Dual-core processor
  • RAM: 4GB
  • Storage: 2GB free space
  • OS: Windows 10+, macOS 10.15+, Linux
  • CPU: Quad-core processor or better
  • RAM: 8GB or more
  • Storage: 5GB free space (for expanded datasets)
  • GPU: NVIDIA GPU with CUDA support (optional, for faster training)

​
Next Steps

Now that your environment is set up, proceed to the Quickstart Guide to:
  • Collect historical F1 data
  • Engineer features
  • Train prediction models
  • Run your first predictions
Bookmark this page for future reference when setting up the project on new machines.

Build docs developers (and LLMs) love

Get started for freeTalk to us