🐦 New CRAN release.

* Styling.
* Fixing links.

CRAN-SUBMISSION

@@ -1,3 +1,3 @@
 Version: 1.1.1
-Date: 2022-01-23 16:03:59 UTC
-SHA: e0eb796c80240cbb920bb6a05838592f1bd3388a
+Date: 2022-01-25 13:09:13 UTC
+SHA: ea38fbf0dc9920414a9342b2c5fa8db91e1c5c7a

DESCRIPTION

@@ -31,6 +31,6 @@ Suggests:
     covr
 RoxygenNote: 7.1.2
 VignetteBuilder: knitr
-URL: https://github.com/JonasMoss/univariateML
+URL: https://github.com/JonasMoss/univariateML, https://jonasmoss.github.io/univariateML/
 BugReports: https://github.com/JonasMoss/univariateML/issues
 Roxygen: list(markdown = TRUE)

R/functions.R

@@ -39,7 +39,6 @@
 #'   from = 0, to = 20,
 #'   main = "Logarithm of Density", ylab = NA, lwd = 2
 #' )
-#'
 #' @name MaximumLikelihoodDistribution
 #' @export
 dml <- function(x, obj, log = FALSE) {

R/helpers.R

@@ -48,7 +48,8 @@ to_univariateML <- function(y, obj) {
       "obj must be either a function returning a univariateML ",
       "object or an univariateML object."
     )
-    tryCatch({
+    tryCatch(
+      {
         obj <- obj(y)
       },
       error = function(cond) stop(msg)

R/mlgumbel.R

@@ -80,7 +80,7 @@ mlgumbel <- function(x, na.rm = FALSE, ...) {
 
   ## Given the sigma, the mu is easy to compute.
   mu <- -sigma * log(mean(exp(-x / sigma)))
-  S <- mean(exp(- (x - mu) / sigma))
+  S <- mean(exp(-(x - mu) / sigma))
 
 
   object <- c(mu = mu, sigma = sigma)

R/mlinvgamma.R

@@ -43,7 +43,7 @@ mlinvgamma <- function(x, na.rm = FALSE, ...) {
   attr(object, "density") <- "extraDistr::dinvgamma"
   attr(object, "logLik") <-
     unname(length(x) * (alpha * log(beta) - log(gamma(alpha)) +
-      - (alpha + 1) * L - beta * M))
+      -(alpha + 1) * L - beta * M))
   attr(object, "support") <- c(0, Inf)
   attr(object, "n") <- length(x)
   attr(object, "call") <- match.call()

R/mlllogis.R

@@ -41,8 +41,8 @@ mlllogis <- function(x, na.rm = FALSE, ...) {
 
   object <- mllogis(y)
   object[1] <- exp(-object[1])
-  object[2] <- 1/object[2]
-  object = rev(object)
+  object[2] <- 1 / object[2]
+  object <- rev(object)
   class(object) <- "univariateML"
   names(object) <- c("shape", "rate")
 

R/mlweibull.R

@@ -75,7 +75,7 @@ mlweibull <- function(x, na.rm = FALSE, ...) {
   }
 
   ## Given the shape, the scale is easy to compute.
-  scale <- (mean(x^shape)) ^ (1 / shape)
+  scale <- (mean(x^shape))^(1 / shape)
   shape_sum <- mean(x^shape)
   n <- length(x)
   object <- c(shape = shape, scale = scale)

R/model_select.R

@@ -28,8 +28,8 @@
 #' @export
 
 model_select <- function(x, models = univariateML_models,
-                     criterion = c("aic", "bic", "loglik"),
-                     na.rm = FALSE, ...) {
+                         criterion = c("aic", "bic", "loglik"),
+                         na.rm = FALSE, ...) {
   check_models(models)
   criterion <- match.arg(criterion)
 
@@ -40,14 +40,13 @@ model_select <- function(x, models = univariateML_models,
   error_inds <- sapply(fits, function(fit) inherits(fit, "try-error"))
   if (all(error_inds)) {
     error_msgs <- sapply(fits[error_inds], as.character)
-    details <- paste0("(", names(error_msgs), ") ",  error_msgs)
+    details <- paste0("(", names(error_msgs), ") ", error_msgs)
     stop("couldn't fit any model.\n", details)
   }
 
   ## select best model
   fits <- fits[!error_inds]
-  crits <- switch(
-    criterion,
+  crits <- switch(criterion,
     "loglik" = -sapply(fits, stats::logLik),
     "aic"    = sapply(fits, stats::AIC),
     "bic"    = sapply(fits, stats::BIC)
@@ -67,7 +66,8 @@ check_models <- function(models) {
   if (any(!is_implemented)) {
     stop(
       "The following families are not implemented: ",
-         paste0(models[!is_implemented], collapse = ", "),
-         ".\n See `print(univariateML_models)` for allowed values.")
+      paste0(models[!is_implemented], collapse = ", "),
+      ".\n See `print(univariateML_models)` for allowed values."
+    )
   }
-}
+}

R/probability_plots.R

@@ -96,9 +96,7 @@ qqmlline <- function(y, obj, datax = FALSE, probs = c(0.25, 0.75), qtype = 7,
   if (datax) {
     slope <- diff(x) / diff(y)
     int <- x[1L] - slope * y[1L]
-  }
-
-  else {
+  } else {
     slope <- diff(y) / diff(x)
     int <- y[1L] - slope * x[1L]
   }

README.Rmd

@@ -28,9 +28,9 @@ set.seed(313)
 ```
 
 ## Overview
-[`univariateML`](https://jonasmoss.github.io/index.html) is an `R`-package for
+[`univariateML`](https://jonasmoss.github.io/univariateML/index.html) is an `R`-package for
 user-friendly maximum likelihood estimation of a
-[selection](https://jonasmoss.github.io/articles/distributions.html) of parametric univariate densities. In addition to basic estimation capabilities,
+[selection](https://jonasmoss.github.io/univariateML/articles/distributions.html) of parametric univariate densities. In addition to basic estimation capabilities,
 this package support visualization through `plot` and `qqmlplot`, model selection
 by `AIC` and `BIC`, confidence sets through the parametric bootstrap with
 `bootstrapml`, and convenience functions such as the density, distribution 
@@ -124,9 +124,9 @@ testing, see the `tests` folder for details.
 
 ## Documentation
 For an overview of the package and its features see the 
-[overview vignette](https://jonasmoss.github.io/articles/overview.html). 
+[overview vignette](https://jonasmoss.github.io/univariateML/articles/overview.html). 
 For an illustration of how this package can make an otherwise long and 
-laborious process much simpler, see the [copula vignette](https://jonasmoss.github.io/articles/copula.html).
+laborious process much simpler, see the [copula vignette](https://jonasmoss.github.io/univariateML/articles/copula.html).
 
 ## How to Contribute or Get Help
 

README.md

@@ -14,10 +14,10 @@ developed.](https://www.repostatus.org/badges/latest/active.svg)](https://www.re
 
 ## Overview
 
-[`univariateML`](https://jonasmoss.github.io/index.html) is an
-`R`-package for user-friendly maximum likelihood estimation of a
-[selection](https://jonasmoss.github.io/articles/distributions.html) of
-parametric univariate densities. In addition to basic estimation
+[`univariateML`](https://jonasmoss.github.io/univariateML/index.html) is
+an `R`-package for user-friendly maximum likelihood estimation of a
+[selection](https://jonasmoss.github.io/univariateML/articles/distributions.html)
+of parametric univariate densities. In addition to basic estimation
 capabilities, this package support visualization through `plot` and
 `qqmlplot`, model selection by `AIC` and `BIC`, confidence sets through
 the parametric bootstrap with `bootstrapml`, and convenience functions
@@ -123,10 +123,10 @@ to testing, see the `tests` folder for details.
 ## Documentation
 
 For an overview of the package and its features see the [overview
-vignette](https://jonasmoss.github.io/articles/overview.html). For an
-illustration of how this package can make an otherwise long and
+vignette](https://jonasmoss.github.io/univariateML/articles/overview.html).
+For an illustration of how this package can make an otherwise long and
 laborious process much simpler, see the [copula
-vignette](https://jonasmoss.github.io/articles/copula.html).
+vignette](https://jonasmoss.github.io/univariateML/articles/copula.html).
 
 ## How to Contribute or Get Help