Fix imports

Author: penelopeysm

Project.toml

@@ -5,6 +5,7 @@ version = "0.39.1"
 [deps]
 ADTypes = "47edcb42-4c32-4615-8424-f2b9edc5f35b"
 AbstractMCMC = "80f14c24-f653-4e6a-9b94-39d6b0f70001"
+AbstractPPL = "7a57a42e-76ec-4ea3-a279-07e840d6d9cf"
 Accessors = "7d9f7c33-5ae7-4f3b-8dc6-eff91059b697"
 AdvancedHMC = "0bf59076-c3b1-5ca4-86bd-e02cd72cde3d"
 AdvancedMH = "5b7e9947-ddc0-4b3f-9b55-0d8042f74170"
@@ -49,6 +50,7 @@ TuringOptimExt = "Optim"
 [compat]
 ADTypes = "1.9"
 AbstractMCMC = "5.5"
+AbstractPPL = "0.11.0"
 Accessors = "0.1"
 AdvancedHMC = "0.3.0, 0.4.0, 0.5.2, 0.6, 0.7, 0.8"
 AdvancedMH = "0.8"

src/mcmc/Inference.jl

@@ -1,9 +1,13 @@
 module Inference
 
 using DynamicPPL:
+    DynamicPPL,
     @model,
     Metadata,
     VarInfo,
+    LogDensityFunction,
+    SimpleVarInfo,
+    AbstractVarInfo,
     # TODO(mhauru) all_varnames_grouped_by_symbol isn't exported by DPPL, because it is only
     # implemented for NTVarInfo. It is used by mh.jl. Either refactor mh.jl to not use it
     # or implement it for other VarInfo types and export it from DPPL.
@@ -24,6 +28,7 @@ using DynamicPPL:
     DefaultContext,
     PriorContext,
     LikelihoodContext,
+    SamplingContext,
     set_flag!,
     unset_flag!
 using Distributions, Libtask, Bijectors
@@ -32,14 +37,14 @@ using LinearAlgebra
 using ..Turing: PROGRESS, Turing
 using StatsFuns: logsumexp
 using Random: AbstractRNG
-using DynamicPPL
 using AbstractMCMC: AbstractModel, AbstractSampler
 using DocStringExtensions: FIELDS, TYPEDEF, TYPEDFIELDS
-using DataStructures: OrderedSet
+using DataStructures: OrderedSet, OrderedDict
 using Accessors: Accessors
 
 import ADTypes
 import AbstractMCMC
+import AbstractPPL
 import AdvancedHMC
 const AHMC = AdvancedHMC
 import AdvancedMH
@@ -74,8 +79,6 @@ export InferenceAlgorithm,
     PG,
     RepeatSampler,
     Prior,
-    assume,
-    observe,
     predict,
     externalsampler
 

src/mcmc/gibbs.jl

@@ -124,7 +124,7 @@ function get_conditioned_gibbs(context::GibbsContext, vns::AbstractArray{<:VarNa
 end
 
 function is_target_varname(ctx::GibbsContext, vn::VarName)
-    return any(Base.Fix2(subsumes, vn), ctx.target_varnames)
+    return any(Base.Fix2(AbstractPPL.subsumes, vn), ctx.target_varnames)
 end
 
 function is_target_varname(context::GibbsContext, vns::AbstractArray{<:VarName})
@@ -660,7 +660,7 @@ function gibbs_step_recursive(
 
     # Construct the conditional model and the varinfo that this sampler should use.
     conditioned_model, context = make_conditional(model, varnames, global_vi)
-    vi = subset(global_vi, varnames)
+    vi = DynamicPPL.subset(global_vi, varnames)
     vi = match_linking!!(vi, state, model)
 
     # TODO(mhauru) The below may be overkill. If the varnames for this sampler are not

src/mcmc/mh.jl

@@ -289,7 +289,7 @@ end
 
 function maybe_link!!(varinfo, sampler, proposal, model)
     return if should_link(varinfo, sampler, proposal)
-        link!!(varinfo, model)
+        DynamicPPL.link!!(varinfo, model)
     else
         varinfo
     end

src/mcmc/particle_mcmc.jl

@@ -193,10 +193,10 @@ function DynamicPPL.initialstep(
     kwargs...,
 )
     # Reset the VarInfo.
-    reset_num_produce!(vi)
-    set_retained_vns_del!(vi)
-    resetlogp!!(vi)
-    empty!!(vi)
+    DynamicPPL.reset_num_produce!(vi)
+    DynamicPPL.set_retained_vns_del!(vi)
+    DynamicPPL.resetlogp!!(vi)
+    DynamicPPL.empty!!(vi)
 
     # Create a new set of particles.
     particles = AdvancedPS.ParticleContainer(
@@ -327,9 +327,9 @@ function DynamicPPL.initialstep(
     kwargs...,
 )
     # Reset the VarInfo before new sweep
-    reset_num_produce!(vi)
-    set_retained_vns_del!(vi)
-    resetlogp!!(vi)
+    DynamicPPL.reset_num_produce!(vi)
+    DynamicPPL.set_retained_vns_del!(vi)
+    DynamicPPL.resetlogp!!(vi)
 
     # Create a new set of particles
     num_particles = spl.alg.nparticles
@@ -359,14 +359,14 @@ function AbstractMCMC.step(
 )
     # Reset the VarInfo before new sweep.
     vi = state.vi
-    reset_num_produce!(vi)
-    resetlogp!!(vi)
+    DynamicPPL.reset_num_produce!(vi)
+    DynamicPPL.resetlogp!!(vi)
 
     # Create reference particle for which the samples will be retained.
     reference = AdvancedPS.forkr(AdvancedPS.Trace(model, spl, vi, state.rng))
 
     # For all other particles, do not retain the variables but resample them.
-    set_retained_vns_del!(vi)
+    DynamicPPL.set_retained_vns_del!(vi)
 
     # Create a new set of particles.
     num_particles = spl.alg.nparticles
@@ -429,23 +429,19 @@ function trace_local_rng_maybe(rng::Random.AbstractRNG)
 end
 
 function DynamicPPL.assume(
-    rng,
-    spl::Sampler{<:Union{PG,SMC}},
-    dist::Distribution,
-    vn::VarName,
-    _vi::AbstractVarInfo,
+    rng, ::Sampler{<:Union{PG,SMC}}, dist::Distribution, vn::VarName, _vi::AbstractVarInfo
 )
     vi = trace_local_varinfo_maybe(_vi)
     trng = trace_local_rng_maybe(rng)
 
     if ~haskey(vi, vn)
         r = rand(trng, dist)
         push!!(vi, vn, r, dist)
-    elseif is_flagged(vi, vn, "del")
-        unset_flag!(vi, vn, "del") # Reference particle parent
+    elseif DynamicPPL.is_flagged(vi, vn, "del")
+        DynamicPPL.unset_flag!(vi, vn, "del") # Reference particle parent
         r = rand(trng, dist)
         vi[vn] = DynamicPPL.tovec(r)
-        setorder!(vi, vn, get_num_produce(vi))
+        DynamicPPL.setorder!(vi, vn, DynamicPPL.get_num_produce(vi))
     else
         r = vi[vn]
     end