Quantopian's community platform is shutting down. Please read this post for more information and download your code.
Back to Community
Pulling a Sentdex Signal (Sentiment Score) on a Single Stock

Hi all -- I've explored using Sentdex as a long-short factor in a pipeline, but I'd like to see a template algorithm to see a Sentdex Score
on a single security

Does anyone have suggestions on how to do this? I've been searching for quite awhile and haven't been able to find a way to pull a sentiment score on a single security.

Bottom line: I want to run my regular long-short multi-factor portfolio but add a trigger so if SPY hits equal to or below a certain sentiment score, my portfolio converts to a risk-off position.

Any help/suggestions are much appreciated!

2 responses

Factor values for specific assets can be fetched either within pipeline or once the pipeline dataframe is fetched. One common way to access specific values from a dataframe is by using the pandas at method (https://pandas.pydata.org/pandas-docs/version/0.18/generated/pandas.DataFrame.at.html). Something like this, in an algo, would fetch the sentiment for just APPL and return a scaler value.

    # Fetch pipeline data  
    data = pipeline_output('my_pipe')

    # Select the sentiment for a single asset using the 'at' method  
    apple = symbol('AAPL')  
    apple_sentiment = data.at[apple, 'mean_sentiment_5day']  

Attached is a sample algo showing how this could potentially be used.

Now, one big issue. Sentdex only tracks sentiment for a limited number of stocks and doesn't track sentiment for ETFs including SPY. If you try to get sentiment data for SPY it will be all nans. As an alternative, one could create a factor which is the mean sentiment of the Q500US. That might be a similar indicator?

Disclaimer

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.

Thanks very much, Dan -- very helpful. Could you show me how to create the factor for the mean sentiment score of all the stocks in the Q500US universe as you indicated? I don't quite understand how to set the sentiment function to just produce a mean score for a specific universe.