I would like to train a Naive Bayes classifier on data I get through the data. history function. I start with an empty data frame and then I get the data when the market closes on a particular day and append it to my data frame and retrain my model on the whole data. So my model learns as it trades. Is there any way I can pre-train the data before I enter paper trading? This would be like training the model in backtesting and using the trained model for paper trading where it will be trained with the new data as well as the backtesting data.
Any way to use data.history without having to go through each day? How do you import data all at once with date range?
Hello, Posted this question a couple days ago. Wondering if anybody had an answer? I found that you can do this in research by importing data with a date range, but is there any way you can do this is to paper trade?
Take a look at this post for some ideas on using ML in both the research and the algo environments (https://www.quantopian.com/posts/machine-learning-on-quantopian). There are actually three posts so maybe look through them all.
Be careful simply appending data each day to a data frame. The data will not be split adjusted. If there is a 2:1 split then it will look like the stock price dropped by 50%. Stock splits actually happen more often than one would think. Especially if the resolution is daily, it's probably better to periodically fetch all new training data using either pipeline or data.history each time one wants to re-train the model. That way it will all be split adjusted and cleaned up for you.
Good luck.
Please sign in or
join Quantopian to
post a reply.
Need help?
Contact support.
Company
Learn & Support
Notices
Follow Us
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 Quantopian.
In addition, the material offers no opinion with respect to the suitability of any security or specific investment. No information contained herein should be regarded as a suggestion to engage in or refrain from any investment-related course of action as none of Quantopian nor any of its affiliates is undertaking to provide investment advice, act as an adviser to any plan or entity subject to the Employee Retirement Income Security Act of 1974, as amended, individual retirement account or individual retirement annuity, or give advice in a fiduciary capacity with respect to the materials presented herein. If you are an individual retirement or other investor, contact your financial advisor or other fiduciary unrelated to Quantopian about whether any given investment idea, strategy, product or service described herein may be appropriate for your circumstances. All investments involve risk, including loss of principal. Quantopian 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.