Back

Controlling parallel backtests from Python

I would like to implement my own system for tuning hyperparemeters from Python. I would like to be able to launch multiple parallel backtests via Python and access the results.

From all the docs I've read, LEAN launches the backtest and controls the Python script. Is it possible to control the entire process from outside of LEAN?

In addition, is it possible to step through the trade tick by tick and request the next iteration rather than the automatic feed? This is important for my training model, but obviously i wouldn't do that in production.

Update Backtest







Welcome to QuantConnect Colin! You can do this locally on your own compute and data just by launching the LEAN engine via command line. You can configure the parameters with a few switches.

In the cloud, we don't have the features or business model in place for this to operate properly. To ensure smooth backtesting for everyone we cap the number of parallel backtests individuals can run.

Re: Stepping through prices:  sorry not at this time; however there is a 10minute per loop timeout; so you can easily just pause for up to 10 minutes per step.

0

The material on this website is provided for informational purposes only and does not constitute an offer to sell, a solicitation to buy, or a recommendation or endorsement for any security or strategy, nor does it constitute an offer to provide investment advisory services by QuantConnect. In addition, the material offers no opinion with respect to the suitability of any security or specific investment. QuantConnect makes no guarantees as to the accuracy or completeness of the views expressed in the website. The views are subject to change, and may have become unreliable for various reasons, including changes in market conditions or economic circumstances. All investments involve risk, including loss of principal. You should consult with an investment professional before making any investment decisions.


Update Backtest





0

The material on this website is provided for informational purposes only and does not constitute an offer to sell, a solicitation to buy, or a recommendation or endorsement for any security or strategy, nor does it constitute an offer to provide investment advisory services by QuantConnect. In addition, the material offers no opinion with respect to the suitability of any security or specific investment. QuantConnect makes no guarantees as to the accuracy or completeness of the views expressed in the website. The views are subject to change, and may have become unreliable for various reasons, including changes in market conditions or economic circumstances. All investments involve risk, including loss of principal. You should consult with an investment professional before making any investment decisions.


Loading...

This discussion is closed