specifying the args of CORN class about universal-portfolios HOT 8 CLOSED

Hey @shayandavoodii, to run CORN (or any other algorithm) you just call e.g.

S = ... dataframe with RAW prices
algo = CORN(window=10, rho=0.1)
result = algo.run(S)

print(result.summary())
result.plot(weights=False, assets=False, ucrp=True, logy=True);

the other methods like init_step or step_slow are internal (should have been prefixed with underscore) and you don't need need to know about them. What is interesting for analysis are methods and attributes of result from the code above.

from universal-portfolios.

Hey @shayandavoodii, to run CORN (or any other algorithm) you just call e.g.

S = ... dataframe with RAW prices
algo = CORN(window=10, rho=0.1)
result = algo.run(S)

print(result.summary())
result.plot(weights=False, assets=False, ucrp=True, logy=True);

the other methods like init_step or step_slow are internal (should have been prefixed with underscore) and you don't need need to know about them. What is interesting for analysis are methods and attributes of result from the code above.

Hi! Thanks for your response! I have two other questions:

1. Does this approach work for the other algorithms?
   example:

algo=[ANOTHER_ALGORITHM]()
result=algo.run()

2. Does the result variable in your code sample also contains optimal weights?

from universal-portfolios.

1. Yes, all algorithms have consistent interface and it's enough to call run() on them
2. I guess you mean algorithm weights by "optimal weights"? If yes, then it can be accessed as result.B. Check out result.__dict__ for a dictionary of available attributes

from universal-portfolios.

1. Yes, all algorithms have consistent interface and it's enough to call run() on them
2. I guess you mean algorithm weights by "optimal weights"? If yes, then it can be accessed as result.B. Check out result.__dict__ for a dictionary of available attributes

I meant the weight of each stock which should be the output of the algorithm. But, what are the result.weights then?

from universal-portfolios.

result.weights is a method that is run internally and returns B. What you're looking for is result.B.

algo.weights is a method that is run internally and returns B. It is then saved as result.B attribute which is identical to result.weights.

from universal-portfolios.

result.weights is a method that is run internally and returns B. What you're looking for is result.B.

Thanks!
Just in case of curiosity, Do you mean, result.weights returns the same thing as result.B?

from universal-portfolios.

Yes, it's exactly the same. Sorry, I thought you were talking about algo.weights(...) method. Updated my previous answer.

from universal-portfolios.

Yes, it's exactly the same. Sorry, I thought you were talking about algo.weights(...) method. Updated my previous answer.

Thanks a lot!

from universal-portfolios.