From bcb8c9af49199bf80adab21f41b42fb7eb0a94c7 Mon Sep 17 00:00:00 2001
From: itsdfish <itsdfish@gmail.com>
Date: Sat, 30 Sep 2023 14:57:59 -0400
Subject: [PATCH] update type system

---
 Project.toml                    | 2 +-
 docs/src/bayes_factor.md        | 9 +++++++--
 src/SequentialSamplingModels.jl | 1 +
 src/type_system.jl              | 6 +++++-
 4 files changed, 14 insertions(+), 4 deletions(-)

diff --git a/Project.toml b/Project.toml
index f57b59f2..dd0191ba 100644
--- a/Project.toml
+++ b/Project.toml
@@ -1,7 +1,7 @@
 name = "SequentialSamplingModels"
 uuid = "0e71a2a6-2b30-4447-8742-d083a85e82d1"
 authors = ["itsdfish"]
-version = "0.7.1"
+version = "0.7.2"
 
 [deps]
 Distributions = "31c24e10-a181-5473-b8eb-7969acd0382f"
diff --git a/docs/src/bayes_factor.md b/docs/src/bayes_factor.md
index 42d1e102..af016988 100644
--- a/docs/src/bayes_factor.md
+++ b/docs/src/bayes_factor.md
@@ -8,8 +8,13 @@ In this tutorial, we will use the Bayes factor to compare the evidence for one m
 In the tutorial below, we will compare two models which differ only in terms of assumptions about drift rate variability: the LBA and the RDM. The LBA assumes that the drift rate varies across trials and is otherwise deterministic, whereas the RDM assumes the drift rate varies within a trial as Gaussian noise, but not across trials. The difference between the models can be visualized with SSMPlots.jl:
 
 ### RDM
+```@setup bayes_factor
+using Random
+using SequentialSamplingModels
+using SSMPlots
+```
 
-```julia
+```@example bayes_factor 
 using SequentialSamplingModels
 using SSMPlots
 using Random
@@ -20,7 +25,7 @@ density_kwargs=(;t_range=range(.20, 1.0, length=100),)
 plot_model(dist; n_sim=1, density_kwargs, xlims=(0,1.0))
 ```
 ### LBA
-```julia
+```@example bayes_factor 
 using SequentialSamplingModels
 using SSMPlots
 using Random
diff --git a/src/SequentialSamplingModels.jl b/src/SequentialSamplingModels.jl
index 29defd58..967ee941 100644
--- a/src/SequentialSamplingModels.jl
+++ b/src/SequentialSamplingModels.jl
@@ -31,6 +31,7 @@ module SequentialSamplingModels
     import StatsAPI: params
 
     export AbstractaDDM
+    export AbstractCDDM
     export AbstractLBA
     export AbstractLCA
     export AbstractLNR
diff --git a/src/type_system.jl b/src/type_system.jl
index 2bf94fd2..f95f327d 100644
--- a/src/type_system.jl
+++ b/src/type_system.jl
@@ -83,6 +83,7 @@ struct Approximate <: PDFType end
 
 get_pdf_type(d::SSM1D) = Exact
 get_pdf_type(d::SSM2D) = Exact
+get_pdf_type(d::ContinuousMultivariateSSM) = Exact
 
 minimum(d::SSM1D) = 0.0
 maximum(d::SSM1D) = Inf
@@ -94,6 +95,7 @@ insupport(d::SSM2D, data) = data.rt ≥ minimum(d) && data.rt ≤ maximum(d)
 
 Base.broadcastable(x::SSM1D) = Ref(x)
 Base.broadcastable(x::SSM2D) = Ref(x)
+Base.broadcastable(x::ContinuousMultivariateSSM) = Ref(x)
 
 vectorize(d::SSM2D, r::NamedTuple) = [r...]
 reconstruct(d::SSM2D, v::NamedTuple) = deepcopy(v)
@@ -185,4 +187,6 @@ Returns 1 for the number of choice options
 
 - `d::SSM1D`: a sub-type of `SSM1D`
 """
-n_options(d::SSM1D) = 1
\ No newline at end of file
+n_options(d::SSM1D) = 1
+
+n_options(d::ContinuousMultivariateSSM) = length(d.ν)
\ No newline at end of file