Issue 408: ARMA and ARIMA models (#438)

* draft MA method

* draft MA methd

* use IDD for epsilon in all models

* add MA benchmark

* Add docs and  tests for IDD

* make episilon_t a arg of the latent model constructors

* improve MA correctness

* fully import EpiAwareUtils

* add a test for IDD

* add tests for MA.jl

* add doc tests and unit tests + start on helper fn

* more updatres to AR appraoc

* chase down partial arg changes

* clean up AR

* clean up and add arma and arima helpers

* Contributions towards Arma/Arima models (#531)

* Patch: Switch to fork of benchmarkCI (#520)

* patch to fork of benchmarkCI

* put fork version of BenchmarkCI in [sources]

* swap order

* add EpiAware [source]

* fix path

* rm benchmarkCI from project

* Patch fix: add `Manifest.toml` to benchmarking (#524)

* trigger

* Update benchmark.yaml

* Update benchmark.yaml

* commit benchmark Manifest

* try alternate approach

* Update benchmark.yaml

* Update EpiMethod.jl

* Update benchmark.yaml

* change baseline to origin/main

* remove trigger

* rm other trigger

* Issue 465: Add an infection generating model for ODE problems (#510)

* CompatHelper: bump compat for Turing to 0.35 for package EpiAware, (drop existing compat) (#516)

* CompatHelper: bump compat for Turing to 0.35 for package EpiAware, (drop existing compat)

* Update Project.toml

* fix Project.toml

---------

Co-authored-by: CompatHelper Julia <[email protected]>
Co-authored-by: Sam Abbott <[email protected]>
Co-authored-by: Samuel Brand <[email protected]>
Co-authored-by: Samuel Brand <[email protected]>

* CompatHelper: bump compat for DynamicPPL to 0.30 for package EpiAware, (drop existing compat) (#528)

Co-authored-by: CompatHelper Julia <[email protected]>

* rename IDD -> IID

* rename test file

* Issue 529: Create null Latent model (#530)

* Null Latent model

* Null Latent model

* fix doctest

* fix generate_epiaware unit tests

New usage of RW

* fix turing method test

underlying std of step size changed name

* fix broadcast test

Underlying std param changed name

* fix HN unit test

Default std prior had changed

* fix AR unit tests

---------

Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: CompatHelper Julia <[email protected]>
Co-authored-by: Sam Abbott <[email protected]>

* revert define_ namming

* clean out repeated utils from merge

* fix MA tests

* fix RW tests - feel made about RandomWalk vs AR naming

* fix remaining unit tests that aren't doctests

* update latent recovery test

* try and fix doctests automatically

* update all doctests to output nothing - this is awful

* add doctests for arima and arma

* fix doctest

* clean up deps

* update replication studies

* add interface tests for combination functions and add benchmarks

* add some basic theoretical properties tests

* name change IDD -> IID benchmarks

* moving all the constructors because this PR is too contained

* catch missing using

* update iid benchmark:

* update extraction

* remove old param namme from case study

* get the dot

* get the dot

* fix initial guess point for MAP opt

* Update index.jl

* add a compile time branch for HN

* add a compile time branch for HN

* update test

* add a new constructor to get old default behaviour

* update docs

* update docs - using the structs for priors is very brittle

* reorder prior plots

---------

Co-authored-by: Samuel Brand <[email protected]>
Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: CompatHelper Julia <[email protected]>
Co-authored-by: Samuel Brand <[email protected]>

Author: 4 people

EpiAware/docs/src/showcase/replications/chatzilena-2019/index.jl

@@ -1,5 +1,5 @@
 ### A Pluto.jl notebook ###
-# v0.20.0
+# v0.20.3
 
 using Markdown
 using InteractiveUtils
@@ -428,8 +428,8 @@ We define the AR(1) process by matching means of `HalfNormal` prior distribution
 # ╔═╡ 71a26408-1c26-46cf-bc72-c6ba528dfadd
 ar = AR(
     damp_priors = [HalfNormal(mean(sampled_AR_damps))],
-    std_prior = HalfNormal(mean(sampled_AR_stds)),
-    init_priors = [Normal(0, 0.001)]
+    init_priors = [Normal(0, 0.001)],
+    ϵ_t = HierarchicalNormal(std_prior = HalfNormal(mean(sampled_AR_stds)))
 )
 
 # ╔═╡ e1ffdaf6-ca2e-405d-8355-0d8848d005b0
@@ -578,9 +578,10 @@ rand(stochastic_mdl)
 initial_guess = [[mean(chn[:β]),
                      mean(chn[:γ]),
                      mean(chn[:S₀]),
-                     mean(ar.std_prior),
                      mean(ar.init_prior)[1],
-                     mean(ar.damp_prior)[1]]
+                     mean(ar.damp_prior)[1],
+                     mean(ar.ϵ_t.std_prior)
+                 ]
                  zeros(13)]
 
 # ╔═╡ 685221ea-f268-4ddc-937f-e7620d065c28
@@ -611,7 +612,7 @@ chn2 = sample(
 describe(chn2)
 
 # ╔═╡ 37a016d8-8384-41c9-abdd-23e88b1f988d
-pairplot(chn2[[:β, :γ, :S₀, Symbol(mdl_prefix * ".σ_AR"),
+pairplot(chn2[[:β, :γ, :S₀, Symbol(mdl_prefix * ".std"),
     Symbol(mdl_prefix * ".ar_init[1]"), Symbol(mdl_prefix * ".damp_AR[1]")]])
 
 # ╔═╡ 7df5d669-d3a2-4a66-83c3-f8618e39bec6

EpiAware/docs/src/showcase/replications/mishra-2020/index.jl

@@ -1,5 +1,5 @@
 ### A Pluto.jl notebook ###
-# v0.20.0
+# v0.20.3
 
 using Markdown
 using InteractiveUtils
@@ -114,10 +114,10 @@ In _Mishra et al_ the standard deviation of the _stationary distribution_ of $Z_
 
 # ╔═╡ c88bbbd6-0101-4c04-97c9-c5887ef23999
 ar = AR(
-    damp_priors = reverse([truncated(Normal(0.8, 0.05), 0, 1),
-        truncated(Normal(0.1, 0.05), 0, 1)]),
-    std_prior = HalfNormal(0.5),
-    init_priors = [Normal(-1.0, 0.1), Normal(-1.0, 0.5)]
+    damp_priors = [truncated(Normal(0.1, 0.05), 0, 1),
+        truncated(Normal(0.8, 0.05), 0, 1)],
+    init_priors = [Normal(-1.0, 0.1), Normal(-1.0, 0.5)],
+    ϵ_t = HierarchicalNormal(std_prior = HalfNormal(0.5))
 )
 
 # ╔═╡ 31ee2757-0409-45df-b193-60c552797a3d
@@ -561,11 +561,11 @@ let
     sub_chn = inference_results.samples[inference_results.samples.name_map.parameters[[1:5;
                                                                                        end]]]
     fig = pairplot(sub_chn)
-    lines!(fig[1, 1], ar.std_prior, label = "Prior")
-    lines!(fig[2, 2], ar.init_prior.v[1], label = "Prior")
-    lines!(fig[3, 3], ar.init_prior.v[2], label = "Prior")
-    lines!(fig[4, 4], ar.damp_prior.v[1], label = "Prior")
-    lines!(fig[5, 5], ar.damp_prior.v[2], label = "Prior")
+    lines!(fig[1, 1], ar.init_prior.v[1], label = "Prior")
+    lines!(fig[2, 2], ar.init_prior.v[2], label = "Prior")
+    lines!(fig[3, 3], ar.damp_prior.v[1], label = "Prior")
+    lines!(fig[4, 4], ar.damp_prior.v[2], label = "Prior")
+    lines!(fig[5, 5], ar.ϵ_t.std_prior, label = "Prior")
     lines!(fig[6, 6], epi.initialisation_prior, label = "Prior")
 
     fig

EpiAware/src/EpiAwareUtils/HalfNormal.jl

@@ -11,49 +11,62 @@ Create a half-normal prior distribution with the specified mean.
 
 # Examples:
 
-```jldoctest HalfNormal
+```jldoctest HalfNormal; output = false
 using EpiAware, Distributions
 
 hn = HalfNormal(1.0)
+nothing
+
 # output
-EpiAware.EpiAwareUtils.HalfNormal{Float64}(μ=1.0)
+
 ```
 
-# filter out all the values that are less than 0
-```jldoctest HalfNormal; filter = r\"\b\d+(\.\d+)?\b\" => \"*\"
+```jldoctest HalfNormal; output = false
 rand(hn)
+nothing
+
 # output
-0.4508533245229199
+
 ```
 
-```jldoctest HalfNormal
+```jldoctest HalfNormal; output = false
 cdf(hn, 2)
+nothing
+
 # output
-0.8894596502772643
+
 ```
 
-```jldoctest HalfNormal
+```jldoctest HalfNormal; output = false
 quantile(hn, 0.5)
+nothing
+
 # output
-0.8453475393951495
+
 ```
 
-```jldoctest HalfNormal
+```jldoctest HalfNormal; output = false
 logpdf(hn, 2)
+nothing
+
 # output
--3.1111166111445083
+
 ```
 
-```jldoctest HalfNormal
+```jldoctest HalfNormal; output = false
 mean(hn)
+nothing
+
 # output
-1.0
+
 ```
 
-```jldoctest HalfNormal
+```jldoctest HalfNormal; output = false
 var(hn)
+nothing
+
 # output
-0.5707963267948966
+
 ```
 "
 struct HalfNormal{T <: Real} <: ContinuousUnivariateDistribution

EpiAware/src/EpiAwareUtils/SafeNegativeBinomial.jl

@@ -27,7 +27,7 @@ parameterisation is useful for specifying the distribution in a way that is easi
 
 # Examples:
 
-```jldoctest SafeNegativeBinomial
+```jldoctest SafeNegativeBinomial; output = false
 using EpiAware, Distributions
 
 bigμ = exp(48.0) #Large value of μ
@@ -37,32 +37,42 @@ bigμ = exp(48.0) #Large value of μ
 p = bigμ / σ²
 r = bigμ * p / (1 - p)
 d = SafeNegativeBinomial(r, p)
+nothing
+
 # output
-EpiAware.EpiAwareUtils.SafeNegativeBinomial{Float64}(r=20.0, p=2.85032816548187e-20)
+
 ```
 
-```jldoctest SafeNegativeBinomial
+```jldoctest SafeNegativeBinomial; output = false
 cdf(d, 100)
+nothing
+
 # output
-0.0
+
 ```
 
-```jldoctest SafeNegativeBinomial
+```jldoctest SafeNegativeBinomial; output = false
 logpdf(d, 100)
+nothing
+
 # output
--850.1397180331871
+
 ```
 
-```jldoctest SafeNegativeBinomial
+```jldoctest SafeNegativeBinomial; output = false
 mean(d)
+nothing
+
 # output
-7.016735912097631e20
+
 ```
 
-```jldoctest SafeNegativeBinomial
+```jldoctest SafeNegativeBinomial; output = false
 var(d)
+nothing
+
 # output
-2.4617291430060293e40
+
 ```
 "
 struct SafeNegativeBinomial{T <: Real} <: SafeDiscreteUnivariateDistribution

EpiAware/src/EpiAwareUtils/SafePoisson.jl

@@ -12,37 +12,47 @@ when the mean is too large.
 
 # Examples:
 
-```jldoctest SafePoisson
+```jldoctest SafePoisson; output = false
 using EpiAware, Distributions
 
 bigλ = exp(48.0) #Large value of λ
 d = SafePoisson(bigλ)
+nothing
+
 # output
-EpiAware.EpiAwareUtils.SafePoisson{Float64}(λ=7.016735912097631e20)
+
 ```
 
-```jldoctest SafePoisson
+```jldoctest SafePoisson; output = false
 cdf(d, 2)
+nothing
+
 # output
-0.0
+
 ```
 
-```jldoctest SafePoisson
+```jldoctest SafePoisson; output = false
 logpdf(d, 100)
+nothing
+
 # output
--7.016735912097631e20
+
 ```
 
-```jldoctest SafePoisson
+```jldoctest SafePoisson; output = false
 mean(d)
+nothing
+
 # output
-7.016735912097631e20
+
 ```
 
-```jldoctest SafePoisson
+```jldoctest SafePoisson; output = false
 var(d)
+nothing
+
 # output
-7.016735912097631e20
+
 ```
 "
 struct SafePoisson{T <: Real} <: SafeDiscreteUnivariateDistribution

EpiAware/src/EpiAwareUtils/censored_pmf.jl

@@ -23,27 +23,17 @@ Raises:
 
 # Examples
 
-```jldoctest filter
+```jldoctest; output = false
 using Distributions
 using EpiAware.EpiAwareUtils
 
 dist = Exponential(1.0)
 
-censored_pmf(dist, Val(:single_censored); D = 10) |>
-    p -> round.(p, digits=3)
+censored_pmf(dist, Val(:single_censored); D = 10)
+nothing
 
 # output
-10-element Vector{Float64}:
- 0.393
- 0.383
- 0.141
- 0.052
- 0.019
- 0.007
- 0.003
- 0.001
- 0.0
- 0.0
+
 ```
 "
 function censored_pmf(dist::Distribution,
@@ -122,28 +112,17 @@ to nearest multiple of `Δd`.
 
 # Examples
 
-```jldoctest filter
+```jldoctest filter; output = false
 using Distributions
 using EpiAware.EpiAwareUtils
 
 dist = Exponential(1.0)
 
-censored_cdf(dist; D = 10) |>
-    p -> round.(p, digits=3)
+censored_cdf(dist; D = 10)
+nothing
 
 # output
-11-element Vector{Float64}:
- 0.0
- 0.368
- 0.767
- 0.914
- 0.969
- 0.988
- 0.996
- 0.998
- 0.999
- 1.0
- 1.0
+
 ```
 "
 function censored_cdf(dist::Distribution; Δd = 1.0, D = nothing, upper = 0.999)
@@ -184,27 +163,17 @@ to nearest multiple of `Δd`.
 
 # Examples
 
-```jldoctest filter
+```jldoctest filter; output = false
 using Distributions
 using EpiAware.EpiAwareUtils
 
 dist = Exponential(1.0)
 
-censored_pmf(dist; D = 10) |>
-    p -> round.(p, digits=3)
+censored_pmf(dist; D = 10)
+nothing
 
 # output
-10-element Vector{Float64}:
- 0.368
- 0.4
- 0.147
- 0.054
- 0.02
- 0.007
- 0.003
- 0.001
- 0.0
- 0.0
+
 ```
 "
 function censored_pmf(dist::Distribution; Δd = 1.0, D = nothing, upper = 0.99)