Quantopian's community platform is shutting down. Please read this post for more information and download your code.
Back to Community
Help Needed In Calculating Lower Partial Moments
Ron Murray
posted
Seeking Help Portfolio Optimization Pipeline

I've previously written an algorithm that calculates equal-risk weights for a multi-asset portfolio, using standard deviation as a proxy for risk.  Now, I'm writing an algorithm that calculates these weights based solely on the downside deviations (lower partial moments).  Here's what I've got so far:

def make_pipeline():  
    base_universe = StaticAssets(symbols('IHI','XLY','TLT'))      
    Close = USEquityPricing.close.latest.fillna(0)      
    returns = DailyReturns(inputs=[USEquityPricing.close], window_length=2)      
    diff = 0 - returns    #simplied form for threshold=0      
    diff = np.clip(diff,a_min=0,a_max=None)    Vola = np.sum(diff**2) / len(returns)

    pipe = Pipeline(
        columns={
            'VolFactors' : Close / Vola,
            'Closes' : Close,
        },
        screen=base_universe
    )
    return pipe

The code works fine all the way through diff.clip operation, but as soon as I add the Vola-defining equation, the pipeline chokes, providing the following error message:

            TypeError: f() got an unexpected keyword argument 'out'  

I would appreciate any assistance in sorting out the problem in this last, crucial step.

1 response
Ron Murray

I've worked through the problem by re-formulating the Lower Partial Moment calculation wholly as a Custom Factor with a fixed window, which was my originally intended approach until I was mis-directed by error messages.  After some more careful attention to parsing, I was able to get the algorithm working.  Here's the final result:

class Volatility(CustomFactor): 

    inputs = [USEquityPricing.close]  
    def compute(self, today, assets, out, close):  
        # [0:-1] is needed to remove last close since diff is one element shorter  
        daily_returns = np.diff(close, axis = 0) / close[0:-1]  
        diff = 0 - daily_returns  
        #a slight offset from 0 is required to avoid problems with long strings of positive daily_returns  
        diff = np.clip(diff,a_min=1.00E-07,a_max=None)  
        out[:] = (np.nansum(diff**2,axis=0) / len(daily_returns))

def make_pipeline():  
    base_universe = StaticAssets(symbols('IHI','XLY','TLT'))  
    Close = USEquityPricing.close.latest.fillna(0)  
    Vola = Volatility(window_length=period)

    pipe = Pipeline(  
        columns={  
            'VolFactors' : Close / Vola,  
            'Closes' : Close,  
        },  
        screen=base_universe  
    )  
    return pipe

The algorithm is performing well in initial testing.

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.