Additional Calculations & Roll, Up, Down Helpers

[cgdeboer]

Summary

Added a few helper methods in the utils file that allow us to stack some transformation logic together before calling an actual metric. For example, if we want to calculate the rolling up capture of a strategy vs its benchmark, we want to be able to do something like [roll,up, capture] where roll, up, capture, are each methods that perform either a series deconstruction (roll), a filter (up), or a calculation (capture). Doing it this why is more DRY than embedding roll and filter logic in each method, but does add some complication.

I elected to add a variety of small methods to the stats file that wrap the complexity described above. This way we keep the API the user is used to calling the same. e.g there is actually a method called rolling_up_capture that takes the expected "returns, factor_returns" arguments. That function simply calls the more complex stacked function to get the results.

Details

• added new methods details below.
• added roll, up, and down as stackable methods to use in future calculations
• added a handful of tests for new methods
• corrected an issue with the max_drawdown. See note below
• updated nose_parameterized to just parameterized
• move date/period symbols into a separate file
• added some examples to the README

Not Done

• add information_ratio per Remove Information Ratio #41
• bump empyrical version
• add remainder of tests.

Max Drawdown

The max_drawdown code was not considering the first return in the array. The max_return array did not consider the starting value of 100 used in the function. In cases where ALL the returns in the array are negative, the max value in the array will be the 100 * (1+ the first negative return). For e.g if the first return in the array is -0.02, then the max value in the array will be 98. This will cause max drawdowns to appear less severe than if they started at 100.

The max drawdown code was masquerading as correct because the negative_returns Series in the test suite starts with a 0. (i.e they aren't all negative).

I've corrected that by ensuring that the cum_returns array starts with a value that matches the base value.

New Methods

    capture,
    up_capture,
    down_capture,
    up_down_capture,
    up_alpha_beta,
    down_alpha_beta,
    roll_max_drawdown,
    roll_up_capture,
    roll_down_capture,
    roll_up_down_capture,
    roll_alpha_beta,
    roll_sharpe_ratio,

Resolves #41 #46

[twiecki]

need to change doc string.

[twiecki]

needs a reference

[cgdeboer]

What kind of reference ?

• http://www.morningstar.com/InvGlossary/upside-downside-capture-ratio.aspx

• http://www.investopedia.com/terms/u/up-market-capture-ratio.asp

Something like that? or am I misunderstanding what you mean by reference ?

[twiecki]

@cgdeboer I won't do a full review yet as you label it as WIP but wanted to say that this looks fantastic.

[cgdeboer]

@twiecki I'll get this thing linted etc, and address your initial comments above. I'll remove the WIP title and notify you here once that's done.

[cgdeboer]

@twiecki alrighty, I still have some tests to write and verify, and I'm still conferring with some colleagues on the info ratio stuff (i.e how to best proceed with that). At my own peril, I'm removing the WIP, review away.

[cgdeboer]

@twiecki I think all of your comments have been addressed. Looks like ole Travis is just finishing up the CI testing (or maybe hung up on one build job).

[twiecki]

function

[cgdeboer]

Newman !! Fixed it in 6efeee1

[cgdeboer]

Alrighty @twiecki , addressed that last pluralized one. Let me know if you see anything else, could catch.

[twiecki]

Did the unittest catch it as well?

[cgdeboer]

Well. You know what, I don't think it did. Perhaps I need to write a functional test for each of the new methods. I sort of thought we'd rely on the individual stat tests for "financial" accuracy, and a sample of tests for the wrappers like up, down, and roll.

I could see it going either way. What is your preference?

[twiecki]

Best to have it run through all code paths.

[cgdeboer]

Will add tests for all the methods. Back in a few.

[twiecki]

@cgdeboer Any update?

[cgdeboer]

@twiecki should have em all done this week. (My few referenced above turned from a few hours to a few days). Other stuff hopped in the way. Shooting for Thursday morning.

[twiecki]

OK, no rush obviously, just wondered if we could help.

[cgdeboer]

Most of the new tests are now written, just taking some extra time to double check the inputs vs expected.

[cgdeboer]

@twiecki tests added. 🏀 is in your court.

[twiecki]

This should be reverted.

[cgdeboer]

Reverted in dfe495f.

[twiecki]

Great work, thanks @cgdeboer!

[cgdeboer]

Thanks !. @twiecki I'll keep an eye on https://pypi.python.org/pypi/empyrical/ for version update ?

[twiecki]

@cgdeboer New release should be up.