Rewrite RandomVariableSet to JointDistribution

FriesischScott / UncertaintyQuantification.jl

Uncertainty Quantification in Julia

MIT License

28 stars 7 forks source link

Rewrite RandomVariableSet to JointDistribution #10

Closed FriesischScott closed 4 years ago

FriesischScott commented 4 years ago

Instead of the RandomVariableSet this introduces two new types:

JointDistribution
Copula

A JointDistribution is built from an array of marginal distributions and a copula of the same dimension. Currently the only implementation of Copula is the GaussianCopula.

coveralls commented 4 years ago

Coverage increased (+0.1%) to 94.853% when pulling badaf809663a117bbd25b07607124e6f84f2227e on joint-distribution into 54ef38ac7af1b9df5c805006f3ff69ecdfd1d313 on master.

AnderGray commented 4 years ago

100% the right move to move from RandomVariableSet to Copulas and JointDistributions.

The to_standard_normal_space and to_copula_space are very clean. I didn't know you could do them like that.

What are you using FiniteDifferences.jl for?

FriesischScott commented 4 years ago

FiniteDifferences is used to compute the gradients needed for LineSampling. Or if you just want to do local sensitivity.