Bayesian Inference of TKTD Models.

morseTKTD

Advanced methods for a valuable quantitative environmental risk assessment using Bayesian inference of Survival TKTD models (like the Generalized Unified Threshold model of Survival (GUTS)).

Submission

Before a submission, you can look at prepare-for-cran , which is an open and collaborative list of things you have to check before submitting your package to the CRAN.

Otherwise, check "as-cran"" using the source package:

library(devtools)
# create documentation
devtools::document(roclets = c('rd', 'collate', 'namespace'))

Once the archive is done, check that .Rbuildignore was applied. Try to have a low size archive (< 2Mb)

Either directly

# build and check the archive
devtools::check()

Or in 2 steps:

# 1. build the package. 
devtools::build()
# 2. check the archive. 
devtools::check_built("../morseTKTD_0.1.0.tar.gz")

See the CRAN status of your sumbmission:

• incoming R CRAN packages: Index of /incoming
• incoming dashboard: incoming dashboard

Install from gitlab repository

library('remotes')
remotes::install_gitlab("mosaic-software/morsetktd", host = "gitlab.in2p3.fr")

Build the manual and vignettes

library('devtools')
devtools::document(roclets = c('rd', 'collate', 'namespace'))
devtools::build_manual()
devtools::build_vignettes()

building the package

Note add to .buildignore

# remove files .rds in fixtures
rds_files <- list.files(path = "tests/testthat/fixtures", pattern = "\.rds$", full.names = TRUE)
use_build_ignore(rds_files, escape = TRUE)

library(devtools)
devtools::build()

Add dependencies

usethis::use_package("ggplot2")

Coverage

From R session

library(covr)
cov <- package_coverage("morseTKTD")

Style of process

The succession of steps

1. data: load the data set.
2. BinaryData, CountData or ContinuousData: make a ModelData object for binary, count and quantitative continuous data, respectively.
3. The above-mentioned objects inherit of data.frame
4. plot: plot a ModelData object.
5. summary: provides a summary of a ModelData object.
6. doseResponse: return a DoseResponse object.
7. plot: plot a DoseResponse object.
8. fit: fit a ModelData object and return a Fit object.
9. plot: plot a Fit object.
10. ppc: return a PPC object.
11. plot: plot a PPC object.

Coding Style

Object: BigCamelCase

class(x) <- append("ObjectCamelCase", class(x))

Methods: small_snake_case

methods_snake_case <- function(object, ...){
  UseMethod("methods_snake_case")
}

methods_snake_case.ObjectCamelCase <- function(...){}

Function (no methods - not linked to object): smallCamelCase

smallCamelCase <- function(...){}