Quantopian's community platform is shutting down. Please read this post for more information and download your code.
Back to Community
ValueError: NaN or Inf values provided to FactorExposure for argument 'loadings'.
Josh Stansfield
posted

I'm encountering the following error when running a full backtest between the dates 2007-04-01 and 2010-05-01:

ValueError: NaN or Inf values provided to FactorExposure for argument 'loadings'.
Rows/Columns with NaNs:
row=Equity(32620 [PFF]) col='momentum'
row=Equity(32620 [PFF]) col='short_term_reversal'
row=Equity(32620 [PFF]) col='size'
row=Equity(32620 [PFF]) col='value'
row=Equity(32620 [PFF]) col='volatility'
Rows/Columns with Infs:
None
There was a runtime error on line 194.

I've copied the algorithm in the getting started tutorial and dropped in my custom alpha factor and a factor for filtering out securities with nans and infs as a mask for it. I've verified that my pipeline output is nan free over the test period via the research interface. In any case the error seems to suggest that it is the Factor values that are causing problems. The 2010-04-01 to 2013-05-01 window works fine without throwing any errors.

Line 194 is : version=opt.Newest
This is within:
factor_risk_constraints = opt.experimental.RiskModelExposure(
context.risk_factor_betas,
version=opt.Newest
)

As a side note I thought Q1500US and QTradableStocksUS excluded etfs (I've reproduced this with both universes as base)?

4 responses
Ryan Tremblay

I am hitting the same issue after introducing risk_loading_pipeline/RiskModelExposure into my algorithm, and have the same questions as Josh (why am I getting this error, and why are ETFs being considered when using Q1500US)...

Indigo Monkey

To get rid of the error try adding dropna() to risk_loading_pipeline by changing the code from:

constrain_sector_style_risk = opt.experimental.RiskModelExposure(
context.risk_loading_pipeline,
version=0,
)

By changing to this:

constrain_sector_style_risk = opt.experimental.RiskModelExposure(
context.risk_loading_pipeline.dropna(),
version=0,
)

Josh Stansfield

Thanks Indigo,

This is what the current tutorial code should look like to avoid throwing the error in the event anyone with even less programming experience then myself searches for this:

factor_risk_constraints = opt.experimental.RiskModelExposure(
context.risk_factor_betas.dropna(),
version=opt.Newest
)

Might be worth adding that to the tutorial until the risk model is a little more stable. I'm still curious why etfs are showing up in QTradableStocksUS and Q1500US?

Zenothestoic

Thanks Indigo Monkey very helpful. Again, it is curious ETFs are showing up in the QTradableStocksUS universe. In my case HYG. My argument has always been from the asset allocation side and the inclusion of Bonds makes perfect sense from that point of view. Nonetheless, what other asset class ETFs are hidden away in that universe? Gold? Crude?

About Quantopian
Careers
Community
Events
Documentation
Academia
Lectures
Status
Facebook
Twitter
LinkedIn
YouTube
Terms of Use
Privacy Policy

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.