xtrade-ai 1.1.1

A comprehensive reinforcement learning framework for algorithmic trading

XTrade-AI Framework

A comprehensive AI-powered trading framework built with Python, featuring machine learning models, backtesting, and live trading capabilities.

🏗️ Architecture

XTrade-AI Framework follows the Model-View-Controller (MVC) architecture pattern, providing a clean separation of concerns:

• Models (xtrade_ai/model/): Database models and data access layer
• Controllers (xtrade_ai/controller/): Business logic and application logic
• Routers (xtrade_ai/router/): API endpoints and request handling
• Database (xtrade_ai/database/): Database connection and migration management

✨ Features

• MVC Architecture: Clean, maintainable code structure
• PostgreSQL + TimescaleDB: High-performance time-series database
• FastAPI: Modern, fast web framework for building APIs
• Machine Learning: Support for XGBoost, scikit-learn, and custom models
• Backtesting Engine: Comprehensive backtesting with performance metrics
• Live Trading: Real-time trading with multiple brokers
• Data Management: Efficient market data storage and retrieval
• User Management: Multi-user support with role-based access control
• Migration System: Database schema versioning and management

🚀 Quick Start

Prerequisites

• Python 3.8+
• PostgreSQL 12+
• TimescaleDB extension

Installation

1. Clone the repository

   git clone https://github.com/your-username/xtrade-ai-framework.git
   cd xtrade-ai-framework
   

2. Create virtual environment

   python -m venv .venv
   source .venv/bin/activate  # On Windows: .venv\Scripts\activate
   

3. Install dependencies

   pip install -r requirements/base.txt
   

4. Set up environment variables

   cp config/env.example .env
   # Edit .env with your configuration
   

5. Set up database

   # Create PostgreSQL database
   createdb xtrade_ai
   
   # Run migrations
   python -m xtrade_ai.cli db migrate
   

6. Start the API server

   python -m xtrade_ai.cli api serve
   

📁 Project Structure

xtrade_ai/
├── api.py                 # Main API application
├── cli.py                 # Command-line interface
├── database/              # Database layer
│   ├── connection.py      # Database connection manager
│   └── migration_manager.py # Migration system
├── model/                 # Data models (MVC Model)
│   ├── base_model.py      # Base model class
│   ├── user_model.py      # User management
│   ├── model_model.py     # ML model management
│   ├── training_model.py  # Training sessions
│   ├── backtest_model.py  # Backtest sessions
│   ├── prediction_model.py # Predictions
│   └── market_data_model.py # Market data
├── controller/            # Business logic (MVC Controller)
│   ├── base_controller.py # Base controller
│   ├── user_controller.py # User management logic
│   ├── model_controller.py # Model management logic
│   ├── training_controller.py # Training logic
│   ├── backtest_controller.py # Backtest logic
│   ├── prediction_controller.py # Prediction logic
│   └── market_data_controller.py # Market data logic
├── router/                # API endpoints (MVC View)
│   ├── base_router.py     # Base router
│   ├── user_router.py     # User endpoints
│   ├── model_router.py    # Model endpoints
│   ├── training_router.py # Training endpoints
│   ├── backtest_router.py # Backtest endpoints
│   ├── prediction_router.py # Prediction endpoints
│   └── market_data_router.py # Market data endpoints
├── migrations/            # Database migrations
│   └── migration_001_initial_schema.sql
└── utils/                 # Utility functions
    ├── logger.py          # Logging configuration
    └── ...                # Other utilities

🗄️ Database Schema

The framework uses PostgreSQL with TimescaleDB for efficient time-series data storage:

• Users: User authentication and management
• Models: Machine learning model registry
• Training Sessions: Model training tracking
• Backtest Sessions: Backtesting results and metrics
• Market Data: OHLCV data with TimescaleDB hypertables
• Predictions: Model prediction requests and results

🔧 CLI Commands

Database Management

# Check migration status
python -m xtrade_ai.cli db status

# Run migrations
python -m xtrade_ai.cli db migrate

# Rollback migrations
python -m xtrade_ai.cli db rollback --steps 1

# Create new migration
python -m xtrade_ai.cli db create-migration add_new_table

# Test database connection
python -m xtrade_ai.cli db connect

API Management

# Start API server
python -m xtrade_ai.cli api serve

# Open API documentation
python -m xtrade_ai.cli api docs

General

# Show framework information
python -m xtrade_ai.cli info

🌐 API Endpoints

The framework provides RESTful API endpoints:

• Authentication: /api/v1/users/auth/*
• User Management: /api/v1/users/*
• Models: /api/v1/models/*
• Training: /api/v1/training/*
• Backtesting: /api/v1/backtest/*
• Predictions: /api/v1/predictions/*
• Market Data: /api/v1/market-data/*

🔐 Authentication

The framework supports:

• JWT-based authentication
• Role-based access control (User/Admin)
• API key management
• Secure password hashing with bcrypt

📊 Data Management

• Market Data: Efficient storage with TimescaleDB hypertables
• Model Storage: Local and cloud storage support (S3, GCS)
• Data Validation: Pydantic models for data validation
• Bulk Operations: Optimized for high-volume data processing

🧪 Testing

# Run tests
python -m pytest tests/

# Run with coverage
python -m pytest --cov=xtrade_ai tests/

📈 Performance

• Database: Connection pooling and optimized queries
• API: Async FastAPI with high concurrency
• Data Processing: Efficient pandas operations
• Caching: Redis integration for performance

🚀 Deployment

Docker

# Build image
docker build -t xtrade-ai .

# Run container
docker run -p 8000:8000 xtrade-ai

Production

• Use production-grade PostgreSQL
• Enable SSL/TLS
• Set up proper logging and monitoring
• Configure backup strategies

🤝 Contributing

1. Fork the repository
2. Create a feature branch
3. Make your changes
4. Add tests
5. Submit a pull request

📄 License

This project is licensed under the MIT License - see the LICENSE file for details.

🆘 Support

• Documentation: docs/
• Issues: GitHub Issues
• Discussions: GitHub Discussions

🔮 Roadmap

• Advanced ML model support (PyTorch, TensorFlow)
• Real-time streaming data
• Advanced risk management
• Multi-asset portfolio optimization
• Cloud-native deployment
• Advanced analytics dashboard

---

Built with ❤️ for the trading community