Early tutorial/demo project: walks through the full quantitative workflow with off-the-shelf Python libraries (data β strategy β backtest β trader). For production use, see the Delta ecosystem below.
- imooc - Intro to Quantitative Trading: Companion course for this repo; data, strategy, backtest, and simulated trading with existing libraries. Suitable for beginners.
- imooc - Programmer's AI Quantitative Finance System Course: Advanced course; deep dive into deltafq architecture from 0 to 1, live trading loop, and production-grade quant development. For those who have finished the intro course.
Open-source quant stack from research and backtest to live trading; lightweight, extensible, for individuals and teams.
- deltafq: Pure native quant framework, minimal dependencies, full pipeline from data, strategy, backtest to live.
- deltafstation: Quant trading platform built on deltafq; data services, strategy management, and trading connectivity, with sim and live support.
git clone https://github.com/Delta-F/DeltaTrader.git- π Market Data - JQData API and web scraping
- βοΈ Strategy Models - Rule-based strategy creation
- π€ Automated Trading - Simulated live trading
Get stock price data:
import data.stock as st
data = st.get_single_price(code='000001.XSHE',
time_freq='daily',
start_date='2021-01-01',
end_date='2021-02-01')Export to CSV:
import data.stock as st
data = st.get_single_price(code='000001.XSHE')
st.export_data(data=data, filename='000001.XSHE', type='price')- Feedback and improvements: Issue or leek_li@outlook.com.
- Contributors: deltaf (framework design & Python 3), ACE (market data crawler).
MIT License.