tradestream 0.5.10

Machine Learning Models

Tradestream uses a variety of machine learning models to predict the future price of a stock. The models are trained on historical data and use a variety of features to make predictions. The models are trained on a daily basis and the predictions are made on a minute-by-minute basis.

Machine Learning Libraries

Tradestream researched the following machine learning libraries:

• TensorFlow
• LSTM
• GRU
• Transformer
• PyTorch
• LSTM
• GRU
• Transformer
• Scikit-learn
• Ridge
• Lasso
• ElasticNet
• RandomForest
• GradientBoosting
• AdaBoost
• Stacking
• Voting
• Bagging
• ExtraTrees
• IsolationForest
• LocalOutlierFactor
• XGBoost
• XGBRegressor
• XGBClassifier
• LightGBM
• LGBMRegressor
• LGBMClassifier
• CatBoost
• CatBoostRegressor
• CatBoostClassifier
• Prophet
• ProphetRegressor
• ProphetClassifier

Contributing to Tradestream

We welcome contributions to Tradestream! Please open an issue or submit a pull request with your changes. You can find the pull request template in the .github/pull_request_template.md file. If you have any questions, please open an issue and we will be happy to help. You can also find us on the Tradestream Discord if you have any questions. It is very important that you follow the Contributing Guidelines when contributing to Tradestream. We look forward to seeing your contributions!

Project Structure

Tradestream is a Python application that uses the Dash framework for the frontend and the Flask framework for the backend. The application is deployed to Heroku. The project is organized as follows:

tradestream/                 # Main directory for the application
│
├── dash_app/                # Directory for the Dash app (frontend)
│   ├── __init__.py          # Initialize the Dash app, include authentication
│   ├── layout.py            # Define the layout of the Dash app
│   ├── callbacks.py         # Define callbacks for interactivity
│   └── authentication.py    # Handle user authentication
│
├── services/                # Directory for services that fetch real-time market data
│   ├── __init__.py          # Initialization for services
│   ├── market_fetcher.py    # Code to fetch real-time data from the markets
│   └── scheduler.py         # Schedule tasks to fetch data at intervals
│
├── api/                     # Directory for the API server
│   ├── __init__.py          # Initialization for API server
│   ├── routes.py            # Define API routes
│   ├── models.py            # Define MongoDB models using ODM (like PyMongo or Motor)
│   └── views.py             # API views (logic to handle requests)
├── .env                     # DOTENV file
├── Procfile                 # Define process types for Heroku (e.g., web, worker)
├── requirements.txt         # Python dependencies
└── build.sh                 # Shell script to build the app
└── start.sh                 # Shell script to start the app
└── pyproject.toml           # Python package configuration