fastbayes 0.1.0.0 → 0.2.0.0

raw patch · 2 files changed

+10/−7 lines, 2 filesdep ~basePVP ok

version bump matches the API change (PVP)

Dependency ranges changed: base

API changes (from Hackage documentation)

Files

• fastbayes.cabal +7/−4
• src/Statistics/FastBayes/Linear.hs +3/−3

@@ -3,13 +3,13 @@  -- The name of the package. name:                fastbayes-version:             0.1.0.0+version:             0.2.0.0  -- A short (one-line) description of the package. synopsis:            Bayesian modeling algorithms accelerated for particular model structures  -- A longer description of the package.-description:         General-purpose sampling approaches like Gibbs sampling are very useful for models that have not been studied extensively. But for some cases, specialized algorithms are available because of the model's generality (/e.g./, linear regression) or niche popularity (/e.g./, Latent Dirichlet Allocation). This package is an effort to collect such algorithms in one place.+description:         General-purpose sampling approaches like Gibbs sampling are very useful for models that have not been studied extensively. But for some cases, specialized algorithms are available because of the model's commonality (/e.g./, linear regression) or niche popularity (/e.g./, Latent Dirichlet Allocation). This package is an effort to collect such algorithms in one place.  -- URL for the project homepage or repository. homepage:            https://github.com/cscherrer/fastbayes@@ -36,11 +36,14 @@   other-extensions:    UnicodeSyntax, BangPatterns      -- Other library packages from which modules are imported.-  build-depends:       base >=4.7 && <4.8, vector >=0.10 && <0.11, hmatrix >=0.16 && <0.17+  build-depends:       base >=4.6 && <4.8, vector >=0.10 && <0.11, hmatrix >=0.16 && <0.17      -- Directories containing source files.   hs-source-dirs:      src      -- Base language which the package is written in.   default-language:    Haskell2010-  ++source-repository head+  type: git+  location: git://github.com/cscherrer/fastbayes.git

@@ -25,7 +25,7 @@   , response   , priorPrecision           , noisePrecision        -  , numEffectiveParameters+  , effectiveNumParameters   , logEvidence              , mapWeights               , hessian@@ -41,9 +41,9 @@   , response               :: Vector Double -- ^The response vector used for the fit   , priorPrecision         :: Double        -- ^The precision (inverse variance) of the prior distribution, determined by maximizing the marginal likelihood   , noisePrecision         :: Double        -- ^The precision (inverse variance) of the noise-  , numEffectiveParameters :: Double        -- ^The number of effective parameters in the model+  , effectiveNumParameters :: Double        -- ^The effective number of parameters in the model   , logEvidence            :: Double        -- ^The log of the evidence, which is useful for model comparison (different features, same response)-  , mapWeights             :: Vector Double -- ^The MAP (maximum a posteriori) values for the paramter weights+  , mapWeights             :: Vector Double -- ^The MAP (maximum a posteriori) values for the parameter weights   , hessian                :: Matrix Double -- ^The Hessian (matrix of second derivatives) for the posterior distribution   }   deriving Show