cca_zoo

cca_zoo copied to clipboard

Hi James, I tried to simulate data using this example, but I get:

LinAlgError: Matrix is not positive definite

I assume you mean you get that error when you run exactly the code in the example? If so could you share scikit-learn version as that's the only place I can think it comes from.

If it's from adding sparsity the Positive Definite problem can happen and you can try changing the random seed a bit.

If you aren't bothered about having a random covariance structure then you can pass

LinearSimulatedData(structure='identity')

which I think works more generally but can make signal recovery more difficult.

LinearSimulatedData(structure='identity') solved it for me but changing the random seed did not have any effect. I am using scikit-learn 1.3.0