Authors
+ +Citation
+ Source:DESCRIPTION
-
-
-
-
Gordon J. Ross. Author. -
-
- -
-
Dean Markwick. Author, maintainer. -
-
- - - - -
-
-
Giovanni Sighinolfi. Contributor. -
-
-
J. Ross G, Markwick D (2026). +dirichletprocess: Build Dirichlet Process Objects for Bayesian Modelling. +R package version 0.4.2.9000, https://github.com/dm13450/dirichletprocess. +
+@Manual{,
+ title = {dirichletprocess: Build Dirichlet Process Objects for Bayesian Modelling},
+ author = {Gordon {J. Ross} and Dean Markwick},
+ year = {2026},
+ note = {R package version 0.4.2.9000},
+ url = {https://github.com/dm13450/dirichletprocess},
+}
Authors
-
The dirichletprocess package provides tools for you to build custom Dirichlet process mixture models. You can use the pre-built Normal/Weibull/Beta distributions or create your own following the instructions in the vignette. In as little as four lines of code you can be modelling your data nonparametrically.
--Installation
+Installation +
You can install the stable release of dirichletprocess from CRAN:
--install.packages("dirichletprocess") -
+install.packages("dirichletprocess")You can also install the development build of dirichletprocess from github with:
--# install.packages("devtools") -devtools::install_github("dm13450/dirichletprocess") -
+# install.packages("devtools")
+devtools::install_github("dm13450/dirichletprocess")For a full guide to the package and its capabilities please consult the vignette:
--browseVignettes(package = "dirichletprocess") -
-Examples
--Density Estimation
+
+browseVignettes(package = "dirichletprocess")Examples +
+Density Estimation +
Dirichlet processes can be used for nonparametric density estimation.
--faithfulTransformed <- faithful$waiting - mean(faithful$waiting) -faithfulTransformed <- faithfulTransformed/sd(faithful$waiting) -dp <- DirichletProcessGaussian(faithfulTransformed) -dp <- Fit(dp, 100, progressBar = FALSE) -plot(dp) -
+faithfulTransformed <- faithful$waiting - mean(faithful$waiting)
+faithfulTransformed <- faithfulTransformed/sd(faithful$waiting)
+dp <- DirichletProcessGaussian(faithfulTransformed)
+dp <- Fit(dp, 100, progressBar = FALSE)
+plot(dp)
-Clustering
+Clustering +
Dirichlet processes can also be used to cluster data based on their common distribution parameters.
--faithfulTrans <- scale(faithful) -dpCluster <- DirichletProcessMvnormal(faithfulTrans) -dpCluster <- Fit(dpCluster, 2000, progressBar = FALSE) -plot(dpCluster) -
+faithfulTrans <- scale(faithful)
+dpCluster <- DirichletProcessMvnormal(faithfulTrans)
+dpCluster <- Fit(dpCluster, 2000, progressBar = FALSE)
+plot(dpCluster)
For more detailed explanations and examples see the vignette.
-Tutorials
+Tutorials +
I’ve written a number of tutorials:
-
-
- Non parametric priors -
- Calculating cluster probabilities -
- Clustering -
- Point processes -
- Custom mixtures -
- Density estimation -
- Checking convergence +
- Non parametric priors +
- Calculating cluster probabilities +
- Clustering +
- Point processes +
- Custom mixtures +
- Density estimation +
- Checking convergence
and some case studies:
-dirichletprocess 0.4.0.9000 Unreleased -
--
-
- Added PriorFunction and PriorClusters to draw from the base measure. -
-dirichletprocess 0.4.0 2020-06-13 -
--
-
- Hierarchical Normal Models added by Giovanni Sighinolfi +
- Updated GitHub Actions +
- Fixed ggplot deprecation +
- Added some missing tests +
- Added PriorFunction and PriorClusters to draw from the base measure. +
- Fixed a bug in the likelihood calculation (#21) by Filippo Fiocchi. +
- Added hierarchical print statement method. +
- Hierarchical Normal Models added by Giovanni Sighinolfi
- Added Giovanni Sighinolfi as a contributor.
- Added params chain to Hidden Markov Models
- Updated the vignette for hierarchical normal models. -
- Fixed matrix class checking for R 4.0.0
- Corrected typos in vignette
- Added a parameter for the number of initial clusters in DirichletProcessMvnormal.
- Various refactoring. -
- Added Hidden Markov models.
- Fixed bug in PosteriorClusters and PosteriorFunction.
- Added in new Beta mixture model for avoiding boundary.
- Fixed a bug in ChangeObservations when using more than one dimension.
- Added in Burn, Print and Diagnostic Plots. -
- Added a likelihood variable for the
dirichletprocessclass that is calculate with each fit iteration.
+ - Added a likelihood variable for the
dirichletprocessclass that is calculate with each fit iteration. - Added option to change how many Metropolis-Hasting steps are used in each iteration.
- Added a likelihood calculation with each iteration.
- Added and refactored some tests.
- Updated vignette.
- Additional options to univariate plotting.
- Added Kees Mulder as a contributor. -
- Added AppVeyor, Travis-CI and codecov.io badges.
- Added penalised log-likelihood step for posterior cluster parameter inference.
- Added exponential mixture model
DirichletProcessExponential. - Updated
plot. Multivariate Gaussian models can now be plotted. - Various bug fixes.
- Updated description. -
dirichletprocess 0.4.2.9000
+dirichletprocess 0.4.22023-08-25
+dirichletprocess 0.4.02020-06-13
+dirichletprocess 0.3.12019-12-11
+dirichletprocess 0.3.02019-05-03
+-dirichletprocess 0.2.2 2018-11-23 -
--
-
dirichletprocess 0.2.22018-11-23
+dirichletprocess 0.2.12018-04-18
+Create a Beta mixture with zeros at the boundaries.
- Source:R/beta_uniform_pareto.R
+ Source: R/beta_uniform_pareto.R
BetaMixture2Create.RdCreate a Beta mixture with zeros at the boundaries.
-BetaMixture2Create(priorParameters = 2, mhStepSize = c(1, 1), - maxT = 1)- -
Arguments
-| priorParameters | -The prior parameters for the base measure. |
-
|---|---|
| mhStepSize | -The Metropolis Hastings step size. A numeric vector of length 2. |
-
| maxT | -The upper bound of the Beta distribution. Defaults to 1 for the standard Beta distribution. |
-
Value
+BetaMixture2Create(priorParameters = 2, mhStepSize = c(1, 1), maxT = 1)Arguments
+ + +Value
A mixing distribution object.
- +Create a Beta mixing distribution.
- Source:R/beta_uniform_gamma.R
+ Source: R/beta_uniform_gamma.R
BetaMixtureCreate.RdSee DirichletProcessBeta for the default prior and hyper prior distributions.
See DirichletProcessBeta for the default prior and hyper prior distributions.
BetaMixtureCreate(priorParameters = c(2, 8), mhStepSize = c(1, 1), - maxT = 1, hyperPriorParameters = c(1, 0.125))- -
Arguments
-| priorParameters | -The prior parameters for the base measure. |
-
|---|---|
| mhStepSize | -The Metropolis Hastings step size. A numeric vector of length 2. |
-
| maxT | -The upper bound of the Beta distribution. Defaults to 1 for the standard Beta distribution. |
-
| hyperPriorParameters | -The parameters for the hyper prior. |
-
Value
+Arguments
+ + +- priorParameters +
The prior parameters for the base measure.
+
+- mhStepSize +
The Metropolis Hastings step size. A numeric vector of length 2.
+
+
+- maxT +
The upper bound of the Beta distribution. Defaults to 1 for the standard Beta distribution.
+
+
+- hyperPriorParameters +
The parameters for the hyper prior.
+
+
Value
A mixing distribution object.
- +Add burn-in to a dirichletprocess object
-Burn(dpobj, niter)- -
Arguments
-| dpobj | -A dirichletprocess object. |
-
|---|---|
| niter | -Number of iterations to burn. |
-
Value
+Burn(dpobj, niter)Value
A dirichletprocess object where all chain objects have the first
niter iterations are removed.
Examples
-+
Examples
+dp <- Fit(DirichletProcessGaussian(rnorm(10)), 100)
+DiagnosticPlots(dp)
+
+burned_dp <- Burn(dp, 50)
+DiagnosticPlots(burned_dp)
+
+Change the observations of fitted Dirichlet Process.
- Source:R/change_observations.R
+ Source: R/change_observations.R
ChangeObservations.RdUsing a fitted Dirichlet process object include new data. The new data will be assigned to the best fitting cluster for each point.
-ChangeObservations(dpobj, newData)- -
Arguments
-| dpobj | -The Dirichlet process object. |
-
|---|---|
| newData | -New data to be included |
-
Value
+ChangeObservations(dpobj, newData)Changed Dirichlet process object
- +Arguments
+ + +Value
+Changed Dirichlet process object
+Examples
+
+y <- rnorm(10)
+dp <- DirichletProcessGaussian(y)
+dp <- ChangeObservations(dp, rnorm(10))
+
+Update the component of the Dirichlet process
- Source:R/cluster_component_update.R
+ Source: R/cluster_component_update.R
ClusterComponentUpdate.RdUpdate the cluster assignment for each data point.
-ClusterComponentUpdate(dpObj) - -# S3 method for conjugate -ClusterComponentUpdate(dpObj) - -# S3 method for hierarchical -ClusterComponentUpdate(dpObj)- -
Arguments
-| dpObj | -Dirichlet Process object |
-
|---|
Value
+ClusterComponentUpdate(dpObj)
+
+# S3 method for class 'conjugate'
+ClusterComponentUpdate(dpObj)
+
+# S3 method for class 'hierarchical'
+ClusterComponentUpdate(dpObj)Dirichlet process object with update components.
- + +Value
+Dirichlet process object with update components.
+Examples
+dp <- DirichletProcessGaussian(rnorm(10))
+dp <- ClusterComponentUpdate(dp)
+
+Predict the cluster labels of some new data.
- Source:R/cluster_label_predict.R
+ Source: R/cluster_label_predict.R
ClusterLabelPredict.RdGiven a fitted Dirichlet process object and some new data use this function to predict what clusters the new data belong to and associated cluster parameters.
-ClusterLabelPredict(dpobj, newData)- -
Arguments
-| dpobj | -Fitted Dirichlet Process |
-
|---|---|
| newData | -New data to have cluster labels predicted. |
-
Value
+ClusterLabelPredict(dpobj, newData)A list of the predicted cluster labels of some new unseen data.
- +Arguments
+ + +- dpobj +
Fitted Dirichlet Process
- - newData +
New data to have cluster labels predicted.
+
+
Examples
-+y <- rnorm(10) -dp <- DirichletProcessGaussian(y) -dp <- Fit(dp, 5) -newY <- rnorm(10, 1) -pred <- ClusterLabelPredict(dp, newY) -
Value
+A list of the predicted cluster labels of some new unseen data.
+Examples
+y <- rnorm(10)
+dp <- DirichletProcessGaussian(y)
+dp <- Fit(dp, 5)
+newY <- rnorm(10, 1)
+pred <- ClusterLabelPredict(dp, newY)
+
+Update the cluster parameters of the Dirichlet process.
- Source:R/cluster_parameter_update.R
+ Source: R/cluster_parameter_update.R
ClusterParameterUpdate.RdUpdate the parameters of each individual cluster using all the data assigned to the particular cluster. A sample is taken from the posterior distribution using a direct sample if the mixing distribution is conjugate or the Metropolis Hastings algorithm for non-conjugate mixtures.
-ClusterParameterUpdate(dpObj)- -
Arguments
-| dpObj | -Dirichlet process object |
-
|---|
Value
+ClusterParameterUpdate(dpObj)Dirichlet process object with update cluster parameters
- + +Value
+Dirichlet process object with update cluster parameters
+Examples
+dp <- DirichletProcessGaussian(rnorm(10))
+dp <- ClusterParameterUpdate(dp)
+
+Diagnostic plots for dirichletprocess objects
- Source:R/diagnostic_plots.R
+ Source: R/diagnostic_plots.R
DiagnosticPlots.RdPlot several diagnostic plots for dirichletprocess objects. Because the dimension of the dirichletprocess mixture is constantly changing, it is not simple to create meaningful plots of the sampled parameters. Therefore, the plots focus on the likelihood, alpha, and the number of clusters.
-DiagnosticPlots(dpobj, gg = FALSE) +++ ++DiagnosticPlots(dpobj, gg = FALSE) + +AlphaTraceplot(dpobj, gg = TRUE) + +AlphaPriorPosteriorPlot( + dpobj, + prior_color = "#2c7fb8", + post_color = "#d95f02", + gg = TRUE +) + +ClusterTraceplot(dpobj, gg = TRUE) + +LikelihoodTraceplot(dpobj, gg = TRUE)++Arguments
-AlphaTraceplot(dpobj, gg = TRUE) -AlphaPriorPosteriorPlot(dpobj, prior_color = "#2c7fb8", - post_color = "#d95f02", gg = TRUE) +
- dpobj
+- -ClusterTraceplot(dpobj, gg = TRUE) -LikelihoodTraceplot(dpobj, gg = TRUE) - -
A dirichletprocess object that was fit.
Arguments
-Value
+given one-by-one, while base plots can be arranged in a grid. + + +- prior_color
+- + +
For
AlphaPriorPosteriorPlot, the color of the prior +function.- post_color
+- + +
For
AlphaPriorPosteriorPlot, the color of the +posterior histogram.++Value
If
- -gg = TRUE, a ggplot2 object. Otherwise, nothing is returned and a base plot is plotted.Functions
- - --
- -
AlphaTraceplot: Trace plot of alpha.- -
AlphaPriorPosteriorPlot: Plot of the prior and posterior of alpha.- -
ClusterTraceplot: Trace plot of the number of clusters.
LikelihoodTraceplot: Trace plot of the likelihood of the data for +++ +Functions
+ +- - -
- +
AlphaTraceplot(): Trace plot of alpha.- +
AlphaPriorPosteriorPlot(): Plot of the prior and posterior of alpha.- +
ClusterTraceplot(): Trace plot of the number of clusters.- -
LikelihoodTraceplot(): Trace plot of the likelihood of the data for each iteration.Examples
-+-+Examples
++dp <- Fit(DirichletProcessGaussian(rnorm(10)), 100) +DiagnosticPlots(dp) ++ +