Add example data loading (#212)

* Add local example datasets * Add DataDeps as dependency * Define utility types for file metadata * Define all example datasets * Register data on initialization * Define load_example_data function * Test load_example_data * Deprecate load_arviz_data * Update load_arviz_data tests * Rename load_arviz_data to load_example_data * Increment patch number * Add arviz_example_data as git submodule * Remove local data from repo * Add JSON3 as dependency * Load example data metadata from submodule * Run formatter * Checkout submodules in GitHub Actions * Simplify code to load from JSON * Declare correct defaults * Avoid missing constant * Add additional tests * Increment version number
arviz-devs · Aug 17, 2022 · 931c3ec · 931c3ec · sethaxen · Aug 17, 2022
1 parent 50950ea
commit 931c3ec
Show file tree

Hide file tree

Showing 24 changed files with 273 additions and 62 deletions.
diff --git a/.github/workflows/ci.yml b/.github/workflows/ci.yml
@@ -23,6 +23,8 @@ jobs:
         os: [ubuntu-latest]
     steps:
       - uses: actions/checkout@v2
+        with:
+          submodules: true
       - uses: julia-actions/setup-julia@v1
         with:
           version: ${{ matrix.julia-version }}

diff --git a/.github/workflows/documenter.yml b/.github/workflows/documenter.yml
@@ -17,6 +17,8 @@ jobs:
     runs-on: ubuntu-latest
     steps:
       - uses: actions/checkout@v2
+        with:
+          submodules: true
       - uses: julia-actions/setup-julia@v1
       - name: Cache CmdStan
         id: cache-cmdstan

diff --git a/.github/workflows/futures.yml b/.github/workflows/futures.yml
@@ -28,6 +28,8 @@ jobs:
             arviz_version: "release"
     steps:
       - uses: actions/checkout@v2
+        with:
+          submodules: true
       - uses: julia-actions/setup-julia@v1
         with:
           version: ${{ matrix.julia-version }}

diff --git a/.gitmodules b/.gitmodules
@@ -0,0 +1,3 @@
+[submodule "deps/data/example_data"]
+	path = deps/data/example_data
+	url = https://github.com/arviz-devs/arviz_example_data
diff --git a/Project.toml b/Project.toml
@@ -1,14 +1,16 @@
 name = "ArviZ"
 uuid = "131c737c-5715-5e2e-ad31-c244f01c1dc7"
 authors = ["Seth Axen <[email protected]>"]
-version = "0.6.3"
+version = "0.6.4"
 
 [deps]
 Conda = "8f4d0f93-b110-5947-807f-2305c1781a2d"
+DataDeps = "124859b0-ceae-595e-8997-d05f6a7a8dfe"
 DataFrames = "a93c6f00-e57d-5684-b7b6-d8193f3e46c0"
 Dates = "ade2ca70-3891-5945-98fb-dc099432e06a"
 DimensionalData = "0703355e-b756-11e9-17c0-8b28908087d0"
 InferenceObjects = "b5cf5a8d-e756-4ee3-b014-01d49d192c00"
+JSON3 = "0f8b85d8-7281-11e9-16c2-39a750bddbf1"
 LogExpFunctions = "2ab3a3ac-af41-5b50-aa03-7779005ae688"
 Markdown = "d6f4376e-aef5-505a-96c1-9c027394607a"
 OrderedCollections = "bac558e1-5e72-5ebc-8fee-abe8a469f55d"
@@ -21,9 +23,11 @@ StatsBase = "2913bbd2-ae8a-5f71-8c99-4fb6c76f3a91"
 
 [compat]
 Conda = "1.0"
+DataDeps = "0.7"
 DataFrames = "0.20, 0.21, 0.22, 1.0"
 DimensionalData = "0.20, 0.21"
 InferenceObjects = "0.1"
+JSON3 = "1"
 LogExpFunctions = "0.2.0, 0.3"
 OrderedCollections = "1"
 PSIS = "0.2, 0.3, 0.4, 0.5"

diff --git a/deps/data/example_data b/deps/data/example_data
diff --git a/docs/src/api/data.md b/docs/src/api/data.md
@@ -31,5 +31,5 @@ extract_dataset
 ## Example data
 
 ```@docs
-load_arviz_data
+load_example_data
 ```
diff --git a/docs/src/creating_custom_plots.jl b/docs/src/creating_custom_plots.jl
@@ -50,7 +50,7 @@ In this parameterization, the model has some sampling issues.
 """
 
 # ╔═╡ cbd81558-e355-4e7a-ba51-0ba9299cb558
-idata = load_arviz_data("centered_eight")
+idata = load_example_data("centered_eight")
 
 # ╔═╡ 898d83d1-cd3a-47a4-84b1-f2cf0f7bf959
 idata.posterior

diff --git a/docs/src/mpl_examples.md b/docs/src/mpl_examples.md
@@ -9,7 +9,7 @@ using ArviZ
 
 ArviZ.use_style("arviz-darkgrid")
 
-data = load_arviz_data("centered_eight")
+data = load_example_data("centered_eight")
 plot_autocorr(data; var_names=[:tau, :mu])
 
 gcf()
@@ -26,7 +26,7 @@ using ArviZ
 
 ArviZ.use_style("arviz-darkgrid")
 
-data = load_arviz_data("regression1d")
+data = load_example_data("regression1d")
 plot_bpv(data)
 
 gcf()
@@ -43,7 +43,7 @@ using ArviZ
 
 ArviZ.use_style("arviz-darkgrid")
 
-data = load_arviz_data("regression1d")
+data = load_example_data("regression1d")
 plot_bpv(data; kind=:t_stat, t_stat="0.5")
 
 gcf()
@@ -62,8 +62,8 @@ ArviZ.use_style("arviz-darkgrid")
 
 model_compare = compare(
     Dict(
-        "Centered 8 schools" => load_arviz_data("centered_eight"),
-        "Non-centered 8 schools" => load_arviz_data("non_centered_eight"),
+        "Centered 8 schools" => load_example_data("centered_eight"),
+        "Non-centered 8 schools" => load_example_data("non_centered_eight"),
     ),
 )
 plot_compare(model_compare; figsize=(12, 4))
@@ -82,8 +82,8 @@ using ArviZ
 
 ArviZ.use_style("arviz-darkgrid")
 
-centered_data = load_arviz_data("centered_eight")
-non_centered_data = load_arviz_data("non_centered_eight")
+centered_data = load_example_data("centered_eight")
+non_centered_data = load_example_data("non_centered_eight")
 plot_density(
     [centered_data, non_centered_data];
     data_labels=["Centered", "Non Centered"],
@@ -129,8 +129,8 @@ using ArviZ
 
 ArviZ.use_style("arviz-darkgrid")
 
-d1 = load_arviz_data("centered_eight")
-d2 = load_arviz_data("non_centered_eight")
+d1 = load_example_data("centered_eight")
+d2 = load_example_data("non_centered_eight")
 plot_elpd(Dict("Centered eight" => d1, "Non centered eight" => d2); xlabels=true)
 
 gcf()
@@ -147,7 +147,7 @@ using ArviZ
 
 ArviZ.use_style("arviz-darkgrid")
 
-data = load_arviz_data("centered_eight")
+data = load_example_data("centered_eight")
 plot_energy(data; figsize=(12, 8))
 
 gcf()
@@ -164,7 +164,7 @@ using ArviZ
 
 ArviZ.use_style("arviz-darkgrid")
 
-idata = load_arviz_data("radon")
+idata = load_example_data("radon")
 plot_ess(idata; var_names=[:b], kind=:evolution)
 
 gcf()
@@ -181,7 +181,7 @@ using ArviZ
 
 ArviZ.use_style("arviz-darkgrid")
 
-idata = load_arviz_data("non_centered_eight")
+idata = load_example_data("non_centered_eight")
 plot_ess(idata; var_names=[:mu], kind=:local, marker="_", ms=20, mew=2, rug=true)
 
 gcf()
@@ -198,7 +198,7 @@ using ArviZ
 
 ArviZ.use_style("arviz-darkgrid")
 
-idata = load_arviz_data("radon")
+idata = load_example_data("radon")
 plot_ess(idata; var_names=[:sigma], kind=:quantile, color="C4")
 
 gcf()
@@ -215,8 +215,8 @@ using ArviZ
 
 ArviZ.use_style("arviz-darkgrid")
 
-centered_data = load_arviz_data("centered_eight")
-non_centered_data = load_arviz_data("non_centered_eight")
+centered_data = load_example_data("centered_eight")
+non_centered_data = load_example_data("non_centered_eight")
 plot_forest(
     [centered_data, non_centered_data];
     model_names=["Centered", "Non Centered"],
@@ -238,7 +238,7 @@ using ArviZ
 
 ArviZ.use_style("arviz-darkgrid")
 
-rugby_data = load_arviz_data("rugby")
+rugby_data = load_example_data("rugby")
 plot_forest(
     rugby_data;
     kind=:ridgeplot,
@@ -288,7 +288,7 @@ using ArviZ
 
 ArviZ.use_style("arviz-darkgrid")
 
-data = load_arviz_data("non_centered_eight")
+data = load_example_data("non_centered_eight")
 plot_pair(
     data;
     var_names=[:theta],
@@ -312,7 +312,7 @@ using ArviZ
 
 ArviZ.use_style("arviz-darkgrid")
 
-data = load_arviz_data("centered_eight")
+data = load_example_data("centered_eight")
 
 ## Combine different posterior draws from different chains
 obs = data.posterior_predictive.obs
@@ -381,7 +381,7 @@ using ArviZ
 
 ArviZ.use_style("arviz-darkgrid")
 
-idata = load_arviz_data("radon")
+idata = load_example_data("radon")
 loo_data = loo(idata)
 plot_khat(loo_data; show_bins=true)
 
@@ -399,7 +399,7 @@ using ArviZ
 
 ArviZ.use_style("arviz-darkgrid")
 
-idata = load_arviz_data("radon")
+idata = load_example_data("radon")
 
 plot_loo_pit(idata; y=:y, ecdf=true, color=:maroon)
 
@@ -417,7 +417,7 @@ using ArviZ
 
 ArviZ.use_style("arviz-darkgrid")
 
-idata = load_arviz_data("non_centered_eight")
+idata = load_example_data("non_centered_eight")
 plot_loo_pit(; idata, y=:obs, color=:indigo)
 
 gcf()
@@ -434,7 +434,7 @@ using ArviZ
 
 ArviZ.use_style("arviz-darkgrid")
 
-data = load_arviz_data("centered_eight")
+data = load_example_data("centered_eight")
 plot_mcse(data; var_names=[:tau, :mu], rug=true, extra_methods=true)
 
 gcf()
@@ -451,7 +451,7 @@ using ArviZ
 
 ArviZ.use_style("arviz-darkgrid")
 
-data = load_arviz_data("radon")
+data = load_example_data("radon")
 plot_mcse(data; var_names=[:sigma_a], color="C4", errorbar=true)
 
 gcf()
@@ -468,7 +468,7 @@ using ArviZ
 
 ArviZ.use_style("arviz-darkgrid")
 
-centered = load_arviz_data("centered_eight")
+centered = load_example_data("centered_eight")
 coords = Dict(:school => ["Choate", "Deerfield"])
 plot_pair(
     centered; var_names=[:theta, :mu, :tau], coords, divergences=true, textsize=22
@@ -488,7 +488,7 @@ using ArviZ
 
 ArviZ.use_style("arviz-darkgrid")
 
-centered = load_arviz_data("centered_eight")
+centered = load_example_data("centered_eight")
 coords = Dict(:school => ["Choate", "Deerfield"])
 plot_pair(
     centered;
@@ -513,7 +513,7 @@ using ArviZ
 
 ArviZ.use_style("arviz-darkgrid")
 
-centered = load_arviz_data("centered_eight")
+centered = load_example_data("centered_eight")
 coords = Dict(:school => ["Choate", "Deerfield"])
 plot_pair(
     centered;
@@ -538,7 +538,7 @@ using ArviZ
 
 ArviZ.use_style("arviz-darkgrid")
 
-centered = load_arviz_data("centered_eight")
+centered = load_example_data("centered_eight")
 coords = Dict(:school => ["Choate", "Deerfield"])
 plot_pair(
     centered;
@@ -565,7 +565,7 @@ using ArviZ
 
 ArviZ.use_style("arviz-darkgrid")
 
-data = load_arviz_data("centered_eight")
+data = load_example_data("centered_eight")
 ax = plot_parallel(data; var_names=[:theta, :tau, :mu])
 ax.set_xticklabels(ax.get_xticklabels(); rotation=70)
 draw()
@@ -584,7 +584,7 @@ using ArviZ
 
 ArviZ.use_style("arviz-darkgrid")
 
-data = load_arviz_data("centered_eight")
+data = load_example_data("centered_eight")
 coords = Dict(:school => ["Choate"])
 plot_posterior(data; var_names=[:mu, :theta], coords, rope=(-1, 1))
 
@@ -602,7 +602,7 @@ using ArviZ
 
 ArviZ.use_style("arviz-darkgrid")
 
-data = load_arviz_data("non_centered_eight")
+data = load_example_data("non_centered_eight")
 plot_ppc(data; data_pairs=Dict(:obs => :obs), alpha=0.03, figsize=(12, 6), textsize=14)
 
 gcf()
@@ -619,7 +619,7 @@ using ArviZ
 
 ArviZ.use_style("arviz-darkgrid")
 
-data = load_arviz_data("non_centered_eight")
+data = load_example_data("non_centered_eight")
 plot_ppc(data; alpha=0.3, kind=:cumulative, figsize=(12, 6), textsize=14)
 
 gcf()
@@ -636,7 +636,7 @@ using ArviZ
 
 ArviZ.use_style("arviz-darkgrid")
 
-data = load_arviz_data("centered_eight")
+data = load_example_data("centered_eight")
 plot_rank(data; var_names=[:tau, :mu])
 
 gcf()
@@ -653,7 +653,7 @@ using ArviZ
 
 ArviZ.use_style("arviz-darkgrid")
 
-data = load_arviz_data("classification10d")
+data = load_example_data("classification10d")
 plot_separation(data; y=:outcome, y_hat=:outcome, figsize=(8, 1))
 
 gcf()
@@ -670,7 +670,7 @@ using ArviZ
 
 ArviZ.use_style("arviz-darkgrid")
 
-data = load_arviz_data("non_centered_eight")
+data = load_example_data("non_centered_eight")
 plot_trace(data; var_names=[:tau, :mu])
 
 gcf()
@@ -687,7 +687,7 @@ using ArviZ
 
 ArviZ.use_style("arviz-darkgrid")
 
-data = load_arviz_data("non_centered_eight")
+data = load_example_data("non_centered_eight")
 plot_violin(data; var_names=[:mu, :tau])
 
 gcf()

diff --git a/docs/src/working_with_inference_data.md b/docs/src/working_with_inference_data.md
@@ -11,7 +11,7 @@ Let's load one of ArviZ's example datasets.
 In this HTML view, you can click a group name to expand a summary of the group.
 
 ```@example wwid
-idata = load_arviz_data("centered_eight")
+idata = load_example_data("centered_eight")
 ```
 
 !!! info