Bayesian inference updates in manifest.toml and project.toml

benchmarks/BayesianInference/DiffEqBayesFitzHughNagumo.jmd

@@ -64,7 +64,7 @@ priors = [truncated(Normal(1.0,0.5),0,1.5), truncated(Normal(1.0,0.5),0,1.5), tr
 #### Stan.jl backend
 
 ```julia
-@time bayesian_result_stan = stan_inference(prob_ode_fitzhughnagumo,t,data,priors; delta = 0.65, num_samples = 10_000, print_summary=false, vars=(DiffEqBayes.StanODEData(), InverseGamma(2, 3)))
+@time bayesian_result_stan = stan_inference(prob_ode_fitzhughnagumo, :rk45, t, data, priors, nothing, Normal, vars=(DiffEqBayes.StanODEData(), InverseGamma(2, 3)), sample_u0=false, diffeq_string=nothing, output_format=:mcmcchains, print_summary=false, tmpdir=mktempdir())
 ```
 
 ### Direct Turing.jl
@@ -112,4 +112,4 @@ FitzHugh-Ngumo is a standard problem for parameter estimation studies. In the Fi
 ```julia, echo = false
 using SciMLBenchmarks
 SciMLBenchmarks.bench_footer(WEAVE_ARGS[:folder],WEAVE_ARGS[:file])
-```
+```

benchmarks/BayesianInference/DiffEqBayesLorenz.jmd

@@ -95,7 +95,7 @@ priors = [truncated(Normal(10,2),1,15),truncated(Normal(30,5),1,45),truncated(No
 Lorenz equation is a chaotic system hence requires very low tolerance to be estimated in a reasonable way, we use 1e-8 obtained from the uncertainty plots. Use of truncated priors is necessary to prevent Stan from stepping into negative and other improbable areas.
 
 ```julia
-@time bayesian_result_stan = stan_inference(prob,t,data,priors; delta = 0.65, reltol=1e-8,abstol=1e-8, vars=(DiffEqBayes.StanODEData(), InverseGamma(2, 3)))
+@time bayesian_result_stan = stan_inference(prob, :rk45, t, data, priors, nothing, Normal, vars=(DiffEqBayes.StanODEData(), InverseGamma(2, 3)), sample_u0=false, diffeq_string=nothing, output_format=:mcmcchains, print_summary=false, tmpdir=mktempdir())
 ```
 
 ### Direct Turing.jl
@@ -148,4 +148,4 @@ Its uncertainty plot points to its chaotic behaviour and goes awry for different
 ```julia, echo = false
 using SciMLBenchmarks
 SciMLBenchmarks.bench_footer(WEAVE_ARGS[:folder],WEAVE_ARGS[:file])
-```
+```

benchmarks/BayesianInference/DiffEqBayesLotkaVolterra.jmd

@@ -71,7 +71,7 @@ priors = [truncated(Normal(1.5,0.5),0.5,2.5),truncated(Normal(1.2,0.5),0,2),trun
 The solution converges for tolerance values lower than 1e-3, lower tolerance leads to better accuracy in result but is accompanied by longer warmup and sampling time, truncated normal priors are used for preventing Stan from stepping into negative values.
 
 ```julia
-@btime bayesian_result_stan = stan_inference(prob,t,data,priors,num_samples=10_000,print_summary=false,delta = 0.65, vars = (DiffEqBayes.StanODEData(), InverseGamma(2, 3)))
+@btime bayesian_result_stan = stan_inference(prob,:rk45, t, data, priors, nothing, Normal, vars=(DiffEqBayes.StanODEData(), InverseGamma(2, 3)), sample_u0=false, diffeq_string=nothing, output_format=:mcmcchains, print_summary=false, tmpdir=mktempdir())
 ```
 
 ### Direct Turing.jl
@@ -126,4 +126,4 @@ It depicts a cyclic behaviour, which is also seen in its Uncertainty Quantificat
 ```julia, echo = false
 using SciMLBenchmarks
 SciMLBenchmarks.bench_footer(WEAVE_ARGS[:folder],WEAVE_ARGS[:file])
-```
+```