More fixes; I think the remaining failures are pMCMC related

Author: penelopeysm

src/Turing.jl

@@ -71,7 +71,6 @@ using DynamicPPL:
     unfix,
     prefix,
     conditioned,
-    @submodel,
     to_submodel,
     LogDensityFunction,
     @addlogprob!
@@ -81,7 +80,6 @@ using OrderedCollections: OrderedDict
 # Turing essentials - modelling macros and inference algorithms
 export
     # DEPRECATED
-    @submodel,
     generated_quantities,
     # Modelling - AbstractPPL and DynamicPPL
     @model,

src/mcmc/emcee.jl

@@ -85,7 +85,10 @@ function AbstractMCMC.step(
     # Generate a log joint function.
     vi = state.vi
     densitymodel = AMH.DensityModel(
-        Base.Fix1(LogDensityProblems.logdensity, DynamicPPL.LogDensityFunction(model, vi))
+        Base.Fix1(
+            LogDensityProblems.logdensity,
+            DynamicPPL.LogDensityFunction(model, DynamicPPL.getlogjoint, vi),
+        ),
     )
 
     # Compute the next states.

src/mcmc/ess.jl

@@ -106,7 +106,7 @@ struct ESSLikelihood{M<:Model,V<:AbstractVarInfo}
     ldf::DynamicPPL.LogDensityFunction{M,V}
 
     # Force usage of `getloglikelihood` in inner constructor
-    function ESSLogLikelihood(model::Model, varinfo::AbstractVarInfo)
+    function ESSLikelihood(model::Model, varinfo::AbstractVarInfo)
         ldf = DynamicPPL.LogDensityFunction(model, DynamicPPL.getloglikelihood, varinfo)
         return new{typeof(model),typeof(varinfo)}(ldf)
     end

src/mcmc/sghmc.jl

@@ -61,7 +61,7 @@ function DynamicPPL.initialstep(
     # Transform the samples to unconstrained space and compute the joint log probability.
     if !DynamicPPL.islinked(vi)
         vi = DynamicPPL.link!!(vi, model)
-        vi = last(DynamicPPL.evaluate!!(model, vi, DynamicPPL.SamplingContext(rng, spl)))
+        vi = last(DynamicPPL.evaluate!!(model, vi))
     end
 
     # Compute initial sample and state.
@@ -100,7 +100,7 @@ function AbstractMCMC.step(
 
     # Save new variables and recompute log density.
     vi = DynamicPPL.unflatten(vi, θ)
-    vi = last(DynamicPPL.evaluate!!(model, vi, DynamicPPL.SamplingContext(rng, spl)))
+    vi = last(DynamicPPL.evaluate!!(model, vi))
 
     # Compute next sample and state.
     sample = Transition(model, vi)
@@ -224,7 +224,7 @@ function DynamicPPL.initialstep(
     # Transform the samples to unconstrained space and compute the joint log probability.
     if !DynamicPPL.islinked(vi)
         vi = DynamicPPL.link!!(vi, model)
-        vi = last(DynamicPPL.evaluate!!(model, vi, DynamicPPL.SamplingContext(rng, spl)))
+        vi = last(DynamicPPL.evaluate!!(model, vi))
     end
 
     # Create first sample and state.
@@ -254,7 +254,7 @@ function AbstractMCMC.step(
 
     # Save new variables and recompute log density.
     vi = DynamicPPL.unflatten(vi, θ)
-    vi = last(DynamicPPL.evaluate!!(model, vi, DynamicPPL.SamplingContext(rng, spl)))
+    vi = last(DynamicPPL.evaluate!!(model, vi))
 
     # Compute next sample and state.
     sample = SGLDTransition(model, vi, stepsize)