nhppp

https://github.com/bladder-ca/nhppp

Science Score: 36.0%

This score indicates how likely this project is to be science-related based on various indicators:

○
CITATION.cff file
✓
codemeta.json file
Found codemeta.json file
✓
.zenodo.json file
Found .zenodo.json file
○
DOI references
✓
Academic publication links
Links to: arxiv.org
○
Academic email domains
○
Institutional organization owner
○
JOSS paper metadata
○
Scientific vocabulary similarity
Low similarity (19.2%) to scientific vocabulary

Last synced: 10 months ago · JSON representation

Repository

Basic Info

Host: GitHub
Owner: bladder-ca
Language: TeX
Default Branch: main
Homepage: https://bladder-ca.github.io/nhppp/
Size: 109 MB

Statistics

Stars: 3
Watchers: 2
Forks: 0
Open Issues: 2
Releases: 4

Created almost 4 years ago · Last pushed 10 months ago

Metadata Files

Readme Changelog

README.Rmd

---
output: github_document
---



```{r, include = FALSE}
knitr::opts_chunk$set(
  collapse = TRUE,
  comment = "#>",
  fig.path = "man/figures/README-",
  out.width = "100%"
)
set.seed(2024)
```

# nhppp  


[![Codecov test coverage](https://codecov.io/gh/bladder-ca/nhppp/branch/main/graph/badge.svg)](https://app.codecov.io/gh/bladder-ca/nhppp?branch=main)
[![R-CMD-check](https://github.com/bladder-ca/nhppp/actions/workflows/R-CMD-check.yaml/badge.svg)](https://github.com/bladder-ca/nhppp/actions/workflows/R-CMD-check.yaml)


nhppp is a package for simulating events from one dimensional nonhomogeneous Poisson point processes (NHPPPs). Its functions are based on three algorithms that provably sample from a target NHPPP: the time-transformation of a homogeneous Poisson process (of intensity one) via the inverse of the integrated intensity function; the generation of a Poisson number of order statistics from a fixed density function; and the thinning of a majorizing NHPPP via an acceptance-rejection scheme. It was developed to provide fast and memory efficient functions for discrete event and statistical simulations. For a description of the algorithms and a numerical comparison with other R packages, see Trikalinos and Sereda (2024), accessible at [https://arxiv.org/abs/2402.00358](https://arxiv.org/abs/2402.00358). 

## Installation

You can install the release version of nhppp from [CRAN](https://cran.r-project.org) with:

``` r
install.packages("nhppp")
```

You can install the development version of nhppp from [GitHub](https://github.com/) with:

``` r
# install.packages("devtools")
devtools::install_github("bladder-ca/nhppp")
```

## Example

These examples use the generic function `draw()`, which is a wrapper for the packages specific functions. `draw()` is a non-vectorized function, but `nhppp` includes vectorized functions that are fast and have small memory footprint. 

Consider the time varying intensity function $\lambda(t) = e^{(0.2t)} (1 + \sin t)$, which is a sinusoidal intensity function with an exponential amplitude. To draw samples over the interval $(0, 6\pi]$ execute 

```{r example_lambda}
l <- function(t) (1 + sin(t)) * exp(0.2 * t)
nhppp::draw(
  lambda = l,
  line_majorizer_intercept = l(6 * pi),
  line_majorizer_slope = 0,
  t_min = 0,
  t_max = 6 * pi
) |>
  head(n = 20)
```

where `line_majorizer_intercept` and `line_majorizer_slope` define a majorizer constant. 

When available, the integrated intensity function $\Lambda(t) = \int_0^t \lambda(s) \ ds$ and its inverse $\Lambda^{-1}(z)$ result in faster simulation times. For this example, $\Lambda(t) = \frac{e^{0.2t}(0.2 \sin t - \cos t)+1}{1.04} + \frac{e^{0.2t} - 1}{0.2}$; $\Lambda^{-1}(z)$ is constructed numerically upfront (or can be calculated numerically by the function, at a computational cost). 

```{r example_big_lambda}
L <- function(t) {
  exp(0.2 * t) * (0.2 * sin(t) - cos(t)) / 1.04 +
    exp(0.2 * t) / 0.2 - 4.038462
}
Li <- stats::approxfun(x = L(seq(0, 6 * pi, 10^-3)), y = seq(0, 6 * pi, 10^-3), rule = 2)

nhppp::draw(Lambda = L, Lambda_inv = Li, t_min = 0, t_max = 6 * pi) |>
  head(n = 20)
```

## Vectorized functions 

See the vignette "Log-linear times".

Owner

Name: Bladder Cancer Site
Login: bladder-ca
Kind: organization

Repositories: 1
Profile: https://github.com/bladder-ca

GitHub Events

Total

Create event: 5
Release event: 2
Issues event: 12
Watch event: 2
Delete event: 1
Issue comment event: 4
Push event: 71
Pull request event: 20

Last Year

Create event: 5
Release event: 2
Issues event: 12
Watch event: 2
Delete event: 1
Issue comment event: 4
Push event: 71
Pull request event: 20

Issues and Pull Requests

Last synced: 10 months ago

All Time

Total issues: 4
Total pull requests: 2
Average time to close issues: 4 months
Average time to close pull requests: 9 days
Total issue authors: 1
Total pull request authors: 1
Average comments per issue: 0.5
Average comments per pull request: 0.5
Merged pull requests: 1
Bot issues: 0
Bot pull requests: 0

Past Year

Issues: 3
Pull requests: 2
Average time to close issues: about 1 month
Average time to close pull requests: 9 days
Issue authors: 1
Pull request authors: 1
Average comments per issue: 0.33
Average comments per pull request: 0.5
Merged pull requests: 1
Bot issues: 0
Bot pull requests: 0

View more stats

Top Authors

Issue Authors

ttrikalin (12)
yuliia-sereda (1)

Pull Request Authors

ttrikalin (13)

Top Labels

Issue Labels

bug (2)

Pull Request Labels

Packages

Total packages: 1
Total downloads:
- cran 304 last-month
Total docker downloads: 32

Total dependent packages: 0
Total dependent repositories: 0
Total versions: 4
Total maintainers: 1

cran.r-project.org: nhppp

Simulating Nonhomogeneous Poisson Point Processes

Homepage: https://bladder-ca.github.io/nhppp/
Documentation: http://cran.r-project.org/web/packages/nhppp/nhppp.pdf
License: GPL (≥ 3)
Latest release: 1.0.2
published over 1 year ago

Versions: 4
Dependent Packages: 0
Dependent Repositories: 0
Downloads: 304 Last month
Docker Downloads: 32

Rankings

Dependent packages count: 28.2%

Dependent repos count: 36.1%

Average: 49.6%

Downloads: 84.4%

Maintainers (1)

thomas_trikalinos@brown.edu