trading-strategy-tester 0.1.3

Simulate and evaluate trading strategies

Trading Strategy Tester

A flexible Python package for simulating and evaluating algorithmic trading strategies with modular conditions, strategies, and trade simulations.

Installation

To install the Trading Strategy Tester package, you can use pip:

pip install trading-strategy-tester

If you want to install the latest development version, you can clone the repository and install it locally:

git clone https://github.com/DrDanicka/trading_strategy_tester.git

Documentation

The documentation is available in the docs directory. You can view it online at this link.

Examples

You can find examples of how to use the package in the examples tab of the user documentation. These examples cover various aspects of the package, including strategy creation, execution, and visualization or using technical indicators.

LLM Integration

The project integrates with Large Language Models (LLMs) to help generate trading strategies from natural language descriptions. It provides a user-friendly interface for generating via web UI.

This project uses Llama 3.2 models via Ollama framework. The models are fine-tuned on a custom dataset of trading strategies and their natural language descriptions. For running the project with LLM integration follow these steps:

1. Install Ollama on your machine from here.
2. Clone this meta-repository with backend and frontend.

git clone --recurse-submodules https://github.com/DrDanicka/trading_strategy_tester_docker.git

3. Navigate to the trading_strategy_tester_docker directory and build the Docker image:

cd trading_strategy_tester_docker
docker-compose up --build 

Note: Building the image may take some time, because it downloads the weights of the Llama models. 4. Open your web browser and navigate to http://localhost:5001 to access the web UI.