Sleek implementations of the ZigZag, Boomerang and other assorted piecewise deterministic Markov processes for Markov Chain Monte Carlo including Sticky PDMPs for variable selection
MIT License
101
stars
7
forks
source link
Unable to run example from package announcement #90
On Julia 1.6.1, in a new environment and after running the code from zigzag.jl, I get the following error when trying to run the example of using ZigZagBoomerang with Soss
julia> trace, final, (num, acc) = @time zigzag(posterior, T) # sample Soss posterior
ERROR: MethodError: objects of type TransformVariables.TransformTuple{NamedTuple{(:β, :α), Tuple{TransformVariables.Identity, TransformVariables.Identity}}} are not callable
Stacktrace:
[1] zigzag(m::ConditionalModel{NamedTuple{(:x,), T} where T<:Tuple, GeneralizedGenerated.NGG.TypeLevel{Expr, "Buf{23}()"}, GeneralizedGenerated.NGG.TypeLevel{Module, "Buf{17}()"}, NamedTuple{(:x,), Tuple{Vector{Float64}}},
NamedTuple{(:y,), Tuple{Vector{Float64}}}}, T::Float64; c::Float64, adapt::Bool)
@ Main .\REPL[63]:21
[2] zigzag(m::ConditionalModel{NamedTuple{(:x,), T} where T<:Tuple, GeneralizedGenerated.NGG.TypeLevel{Expr, "Buf{23}()"}, GeneralizedGenerated.NGG.TypeLevel{Module, "Buf{17}()"}, NamedTuple{(:x,), Tuple{Vector{Float64}}},
NamedTuple{(:y,), Tuple{Vector{Float64}}}}, T::Float64)
@ Main .\REPL[63]:2
[3] top-level scope
@ .\timing.jl:210 [inlined]
[4] top-level scope
@ .\REPL[65]:0
On Julia 1.6.1, in a new environment and after running the code from zigzag.jl, I get the following error when trying to run the example of using ZigZagBoomerang with Soss