Ecosyste.ms: Awesome
An open API service indexing awesome lists of open source software.
https://github.com/dm13450/dirichletprocess
Build dirichletprocess objects for data analysis
https://github.com/dm13450/dirichletprocess
bayesian bayesian-inference bayesian-statistics dirichlet-process mcmc r r-package
Last synced: 6 days ago
JSON representation
Build dirichletprocess objects for data analysis
- Host: GitHub
- URL: https://github.com/dm13450/dirichletprocess
- Owner: dm13450
- Created: 2017-10-11T15:15:02.000Z (about 7 years ago)
- Default Branch: master
- Last Pushed: 2023-08-26T07:19:08.000Z (about 1 year ago)
- Last Synced: 2024-08-16T13:56:51.844Z (3 months ago)
- Topics: bayesian, bayesian-inference, bayesian-statistics, dirichlet-process, mcmc, r, r-package
- Language: R
- Homepage: https://dm13450.github.io/dirichletprocess/
- Size: 10.1 MB
- Stars: 56
- Watchers: 2
- Forks: 14
- Open Issues: 10
-
Metadata Files:
- Readme: README.Rmd
Awesome Lists containing this project
README
---
output: github_document
---
```{r echo=FALSE, message=FALSE}
set.seed(2020)
require(dirichletprocess)
require(ggplot2)
knitr::opts_chunk$set(
collapse = TRUE,
comment = "#>",
fig.path = "vignettes/img/"
)
```
# dirichletprocess
[](https://github.com/dm13450/dirichletprocess/actions)
[](https://ci.appveyor.com/project/dm13450/dirichletprocess)
[](https://app.codecov.io/gh/dm13450/dirichletprocess)
The dirichletprocess package provides tools for you to build custom Dirichlet process mixture models. You can use the pre-built Normal/Weibull/Beta distributions or create your own following the instructions in the vignette. In as little as four lines of code you can be modelling your data nonparametrically.
## Installation
You can install the stable release of dirichletprocess from CRAN:
```{r, eval=FALSE}
install.packages("dirichletprocess")
```
You can also install the development build of dirichletprocess from github with:
```{r gh-installation, eval = FALSE}
# install.packages("devtools")
devtools::install_github("dm13450/dirichletprocess")
```
For a full guide to the package and its capabilities please consult the vignette:
```{r vignette, eval=FALSE}
browseVignettes(package = "dirichletprocess")
```
## Examples
### Density Estimation
Dirichlet processes can be used for nonparametric density estimation.
```{r density, eval=FALSE}
faithfulTransformed <- faithful$waiting - mean(faithful$waiting)
faithfulTransformed <- faithfulTransformed/sd(faithful$waiting)
dp <- DirichletProcessGaussian(faithfulTransformed)
dp <- Fit(dp, 100, progressBar = FALSE)
plot(dp)
```
### Clustering
Dirichlet processes can also be used to cluster data based on their common distribution parameters.
```{r clustering, eval=FALSE}
faithfulTrans <- scale(faithful)
dpCluster <- DirichletProcessMvnormal(faithfulTrans)
dpCluster <- Fit(dpCluster, 2000, progressBar = FALSE)
plot(dpCluster)
```
For more detailed explanations and examples see the vignette.
### Tutorials
I've written a number of tutorials:
* [Non parametric priors](https://dm13450.github.io/2019/02/22/Nonparametric-Prior.html)
* [Calculating cluster probabilities](https://dm13450.github.io/2018/11/21/Cluster-Probabilities.html)
* [Clustering](https://dm13450.github.io/2018/05/30/Clustering.html)
* [Point processes](https://dm13450.github.io/2018/03/08/dirichletprocess-pointprocess.html)
* [Custom mixtures](https://dm13450.github.io/2018/02/21/Custom-Distributions-Conjugate.html)
* [Density estimation](https://dm13450.github.io/2018/02/01/Dirichlet-Density.html)
* [Checking convergence](https://dm13450.github.io/2020/01/11/Dirichlet-Convergence.html)
and some case studies:
* [State of the Market - Infinite State Hidden Markov Models](https://dm13450.github.io/2020/06/03/State-of-the-Market.html)
* [Palmer Penguins and an Introduction to Dirichlet Processes](https://dm13450.github.io/2020/09/28/PriorToPosterior.html)