Skip to content

Updating to compatability with new Turing Major versions #388

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
odunbar merged 3 commits into from
Nov 26, 2025
Merged

Updating to compatability with new Turing Major versions #388

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
ee14f61
updated compat for MCMC (and indirectly ForwardDiff/GP), along with c…
odunbar Nov 26, 2025
2a8394c
format
odunbar Nov 26, 2025
f2c9c5a
use the current density calc.
odunbar Nov 26, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
8 changes: 4 additions & 4 deletions Project.toml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -31,17 +31,17 @@ StatsBase = "2913bbd2-ae8a-5f71-8c99-4fb6c76f3a91"

[compat]
AbstractGPs = "0.5.21"
AbstractMCMC = "3.3, 4, 5"
AdvancedMH = "0.6, 0.7, 0.8"
AbstractMCMC = "5"
AdvancedMH = "0.8"
ChunkSplitters = "3.1.2"
Conda = "1.7"
Distributions = "0.24, 0.25"
DocStringExtensions = "0.8, 0.9"
EnsembleKalmanProcesses = "2"
ForwardDiff = "0.10.38, 1"
ForwardDiff = "1"
GaussianProcesses = "0.12"
KernelFunctions = "0.10.64"
MCMCChains = "4.14, 5, 6, 7"
MCMCChains = "7"
Printf = "1"
ProgressBars = "1"
PyCall = "1.93"
Expand Down
13 changes: 9 additions & 4 deletions src/MarkovChainMonteCarlo.jl
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -379,9 +379,14 @@ function AbstractMCMC.step(
new_params = AdvancedMH.propose(rng, sampler, model, current_state; stepsize = stepsize)
# Calculate the log acceptance probability and the log density of the candidate.
new_log_density = AdvancedMH.logdensity(model, new_params)

# Just to initialize: if you pass state, it just reads the old log_density (initialized as false). in this case, compute it by passing the actual parameter values
current_log_density =
isa(AdvancedMH.logdensity(model, current_state), Bool) ? AdvancedMH.logdensity(model, current_state.params) :
AdvancedMH.logdensity(model, current_state)

log_α =
new_log_density - AdvancedMH.logdensity(model, current_state) +
AdvancedMH.logratio_proposal_density(sampler, current_state, new_params)
new_log_density - current_log_density + AdvancedMH.logratio_proposal_density(sampler, current_state, new_params)

# Decide whether to return the previous params or the new one.
new_state = if -Random.randexp(rng) < log_α
Expand Down Expand Up @@ -573,7 +578,7 @@ function MCMCWrapper(
end

sample_kwargs = (; # set defaults here
:init_params => deepcopy(init_params),
:initial_params => deepcopy(init_params),
:param_names => param_names,
:discard_initial => burnin,
:chain_type => MCMCChains.Chains,
Expand Down Expand Up @@ -641,7 +646,7 @@ end

function _find_mcmc_step_log(mcmc::MCMCWrapper)
str_ = @sprintf "%d starting params:" 0
for p in zip(mcmc.sample_kwargs.param_names, mcmc.sample_kwargs.init_params)
for p in zip(mcmc.sample_kwargs.param_names, mcmc.sample_kwargs.initial_params)
str_ *= @sprintf " %s: %.3g" p[1] p[2]
end
println(str_)
Expand Down