v1.2.0beta2

Project.toml

@@ -1,7 +1,7 @@
 name = "RedClust"
 uuid = "bf1adee6-87fe-4679-8d23-51fe99940a25"
 authors = ["Abhinav Natarajan <[email protected]>"]
-version = "1.2.0beta"
+version = "1.2.0beta2"
 
 [deps]
 Clustering = "aaaa29a8-35af-508c-8bc3-b662a17a0fe5"

README.md

@@ -47,7 +47,22 @@ A more elaborate example can be found in the detailed documentation.
 ## Citing this package
 If you want to use this package in your work, please cite it as:
 
-Natarajan, A., De Iorio, M., Heinecke, A., Mayer, E. and Glenn, S., 2022. ‘Cohesion and Repulsion in Bayesian Distance Clustering’, arXiv [2107.05414](https://arxiv.org/abs/2107.05414).
+Natarajan, A., De Iorio, M., Heinecke, A., Mayer, E. and Glenn, S., 2021. ‘Cohesion and Repulsion in Bayesian Distance Clustering’, arXiv [2107.05414](https://arxiv.org/abs/2107.05414).
+
+For BibTeX users:
+
+```latex
+@misc{https://doi.org/10.48550/arxiv.2107.05414,
+  doi = {10.48550/ARXIV.2107.05414},
+  url = {https://arxiv.org/abs/2107.05414},
+  author = {Natarajan, Abhinav and De Iorio, Maria and Heinecke, Andreas and Mayer, Emanuel and Glenn, Simon},
+  keywords = {Methodology (stat.ME), FOS: Computer and information sciences, FOS: Computer and information sciences},
+  title = {Cohesion and Repulsion in Bayesian Distance Clustering},
+  publisher = {arXiv},
+  year = {2021},
+  copyright = {arXiv.org perpetual, non-exclusive license}
+}
+```
 
 [github-CI-img]: https://img.shields.io/github/workflow/status/abhinavnatarajan/RedClust.jl/CI?label=CI&logo=github&labelColor=222222
 [github-CI-url]: https://github.com/abhinavnatarajan/RedClust.jl/actions/workflows/CI.yml

docs/Project.toml

@@ -10,6 +10,6 @@ StatsPlots = "f3b207a7-027a-5e70-b257-86293d7955fd"
 
 [compat]
 Documenter = "0.27"
-Literate = "0.3"
+Literate = "2.7"
 StatsBase = "0.33.8"
 julia = "1.7"

docs/basic_example_for_docs.jl

@@ -38,8 +38,7 @@ colorbar_tickfontsize = 12,
 legend_font_pointsize = 12, 
 plot_titlefontsize = 14
 )
-
-# seed the default RNG so that documentation remains stable 
+## seed the default RNG so that documentation remains stable 
 seed!(44)
 #!setup
 
@@ -57,13 +56,16 @@ function sqmatrixplot(X::Matrix; kwargs...)
 end
 
 ## Histogram with integer bins
-function histogram_pmf(X::AbstractVector{<:Integer}; kwargs...)
-    xvals = minimum(X):maximum(X)
-    yvals = counts(X)./length(X)
-    bar(xvals, yvals, 
-    linewidth = 0, 
-    legend = false, 
-    xticks = xvals; kwargs...)
+function histogram_pmf(X::AbstractVector{<:Integer}; binwidth::Int=1, kwargs...)
+    xmin = minimum(X)
+    xmax = maximum(X)
+    binedges = xmin:binwidth:xmax
+    c = counts(X)./length(X)
+    bincounts = map(sum, [c[(i-xmin+1):minimum([i-xmin+1+binwidth-1, xmax-xmin+1])] for i in binedges])
+    bar(binedges, bincounts,
+    linewidth = 0,
+    legend = false,
+    xticks = binedges; kwargs...)
 end
 
 ## Combine two symmetric square matrices together into the upper and lower triangle of a square matrix
@@ -137,17 +139,17 @@ params = fitprior(points, "k-means", false)
 begin 
     pred_intracluster = sampledist(params, "intracluster", 10000)
     pred_intercluster = sampledist(params, "intercluster", 10000)
-    density(pred_intracluster, 
-    label="Simulated WCD", xlabel = "Distance", ylabel = "Density", 
+    density(pred_intercluster, 
+    label="Simulated ICD", xlabel = "Distance", ylabel = "Density", 
     linewidth = 2, linestyle = :dash)
-    density!(empirical_intracluster, 
-    label="Empirical WCD", 
-    color = 1, linewidth = 2)
-    density!(pred_intercluster, 
-    label="Simulated ICD", 
-    linewidth = 2, linestyle = :dash, color = 2)
     density!(empirical_intercluster, 
     label="Empirical ICD", 
+    color = 1, linewidth = 2)
+    density!(pred_intracluster, 
+    label="Simulated WCD", 
+    linewidth = 2, linestyle = :dash, color = 2)
+    density!(empirical_intracluster, 
+    label="Empirical WCD", 
     linewidth = 2, color = 2)
     title!("Distances: Prior Predictive vs Empirical Distribution")
 end
@@ -195,10 +197,10 @@ begin
     ylabel = "Density", xlabel = "\$p\$",
     title = "Posterior Distribution of \$p\$",
     label = "Empirical density",
-    legend_font_pointsize=12,
-    legend_position = :topleft)
+    legend_font_pointsize=12)
     density!(result.p, color=:black, linewidth = 2, linestyle=:dash,
-    label = "Kernel estimate")
+    label = "Kernel estimate",
+    legend_position = :topleft)
 end
 #md # ## Convergence statistics
 # Plot the traceplot of the autocorrelation function of ``K``:

docs/src/changelog.md

@@ -3,8 +3,11 @@
 ## [1.2.0]
 ### Added
 - added function [`fitprior2`](@ref), alternative method to fit prior hyperparameters.
-- updated the basic_example file
-- added individual example files for each example shown in the paper, except for the numismatic example (for data privacy reasons).
+
+### Changed
+- pretty print for [`MCMCResult`](@ref) also shows whether the model includes repulsion.
+- moved `basic_example.jl` from the `examples` folder to `docs`. 
+- removed `examples` (added to a separate branch). 
 
 ## [1.1.0]
 ### Added

docs/src/cite.md

@@ -1,4 +1,19 @@
 # Citation Information
 If you want to use this package in your work, please cite it as:
 
-Natarajan, A., De Iorio, M., Heinecke, A., Mayer, E. and Glenn, S., 2021. ‘Cohesion and Repulsion in Bayesian Distance Clustering’, arXiv [2107.05414](https://arxiv.org/abs/2107.05414).
+Natarajan, A., De Iorio, M., Heinecke, A., Mayer, E. and Glenn, S., 2021. ‘Cohesion and Repulsion in Bayesian Distance Clustering’, arXiv [2107.05414](https://arxiv.org/abs/2107.05414).
+
+For BibTeX users:
+
+```latex
+@misc{https://doi.org/10.48550/arxiv.2107.05414,
+  doi = {10.48550/ARXIV.2107.05414},
+  url = {https://arxiv.org/abs/2107.05414},
+  author = {Natarajan, Abhinav and De Iorio, Maria and Heinecke, Andreas and Mayer, Emanuel and Glenn, Simon},
+  keywords = {Methodology (stat.ME), FOS: Computer and information sciences, FOS: Computer and information sciences},
+  title = {Cohesion and Repulsion in Bayesian Distance Clustering},
+  publisher = {arXiv},
+  year = {2021},
+  copyright = {arXiv.org perpetual, non-exclusive license}
+}
+```

docs/src/funding.md

@@ -2,4 +2,4 @@
 We are grateful to the following funding organisations for their financial support for the research that led to the main publication behind this package.
  - National University of Singapore, HSS Seed Fund R-607-000-449-646
  - Yale-NUS College, grant IG20-RA001
- - Singapore Ministry of Education, Academic Research Fund Tier 2 Grant MOE-T2EP40121-0021.
+ - Singapore Ministry of Education, Academic Research Fund Tier 2 Grant MOE-T2EP40121-0021