Commits
Author  Commit  Message  Labels  Comments  Approvals  Date 

Avoid pattern match failure on NaN in cumulative




Add logDensity to exponenetial distribution




Add logarithm of probability for discrete distributions




Eta reduce




Add logarithm of probablity density
Both density and logDensity could be expressed terms of each other
so default implementations are added.
Currently none of the distributions have good implementations of
logDensity since they use default implementation.
Affects #41





Entropy instance for LinearTransform





Entropy instance for HypergeometricDistribution





Entropy instance for BinomialDistribution





Improvements to Poisson entropy computation





Entropy instance for PoissonDistribution





Entropy instance for UniformDistribution





Entropy intsance for StudentT





Entropy instance for NormalDistribution





Entropy instance for GeometricDistribution
Also changed "finite entropy" to "welldefined entropy" in the
description of the contract for the Entropy
typeclass. GeometricDistribution defines Mean and Variance even though
it treats a success probability of 0 as legal, so we should be
consistent by defining Entropy (and not just MaybeEntropy) as well.





MaybeEntropy instance for GammaDistribution





Entropy instance for FDistribution





Entropy instance for ExponentialDistribution





Entropy instance for ChiSquared





Entropy instance for CauchyDistribution





Entropy instance for BetaDistribution





Define 'Entropy' and 'MaybeEntropy' typeclasses.




c0aca4b
M

Merge




Fix warning




Use incomplete beta as approximation for CDF of binomial distribution
It offer lower precision for some inputs but much faster for large N
and works for very large N
Fixes #53




Better error reporting for test case




Added tag 0.10.4.1 for changeset d916be3f8240




Bump version to 0.10.4.1



GHC < 7.6 needs ghcprim for GHC.Generics




Added tag 0.10.4.0 for changeset c1c805738838




c1c8057
M

Merge

