MIIC v2.0.1: Preparation of CRAN update submission, group all breaking changes.

DESCRIPTION

@@ -1,6 +1,6 @@
 Package: miic
 Title: Learning Causal or Non-Causal Graphical Models Using Information Theory
-Version: 2.0.0
+Version: 2.0.1
 Authors@R:
     c(person(given = "Franck",
              family = "Simon",

NEWS.md

@@ -2,31 +2,43 @@
 
 # v2.0.1
 
+## Features
+
+- New release to CRAN.
+
 ## Fixes and improvements
 
-- Updated version published on CRAN.
+- Faster post-processing in R for datasets with large number of variables.
+
+## Breaking changes
+
+Consolidating long-pending breaking changes:
+
+- Harmonization of exported function names using camel case.
+
+- Harmonization of parameters and return values using snake case.
 
-- Standardization of exported function names, parameters and return values.
+- Harmonization of abbreviations.
 
 ## Known issues
 
-- A (very) large number of contributors can lead to a memory fault.
-  Initial fix has been reverted due to side effects.
+- Conditioning on a (very) large number of contributors can lead to a memory 
+  fault.
 
 # v2.0.0
 
 ## Features
 
 - tMIIC version for temporal causal discovery on stationary time series: 
-  new mode of MIIC to reconstruct networks from temporal stationary datasets.
+  new mode of `miic()` to reconstruct networks from temporal stationary datasets.
   [Simon et al., eLife, reviewed preprint]
   (https://www.biorxiv.org/content/10.1101/2024.02.06.579177v1.abstract)
 
 # v1.8.1
 
 ## Fixes and improvements
 
-- The discretization of continuous variables has been modified when dealing 
+- The discretization of continuous variables has been improved when dealing 
   with variables having a large number of identical values.
 
 - Fix for memory overflow on shared memory space.
@@ -58,7 +70,7 @@
   [Cabeli et al., Why21 at NeurIPS 2021]
   (http://kinefold.curie.fr/isambertlab/PAPERS/cabeli_Why21-NeurIPS2021.pdf)
 
-- By default, MIIC does not propagate orientations anymore
+- By default, `miic()` does not propagate orientations anymore
   and allows latent variables discovery during orientation step. 
 
 # v1.5.3

R/computeInformation.R

@@ -35,10 +35,10 @@
 #' \item Affeldt et al., \emph{Bioinformatics 2016}
 #' }
 #'
-#' @param X [a vector]
-#' A vector that contains the observational data of the first variable.
-#' @param Y [a vector]
-#' A vector that contains the observational data of the second variable.
+#' @param x [a vector]
+#' The \eqn{X} vector that contains the observational data of the first variable.
+#' @param y [a vector]
+#' The \eqn{Y} vector that contains the observational data of the second variable.
 #' @param df_conditioning [a data frame]
 #' The data frame of the observations of the conditioning variables.
 #' @param maxbins [an integer]
@@ -74,11 +74,12 @@
 #'   the cutpoints for the partitioning of \eqn{X}.
 #' \item cutpoints2: Only when \eqn{Y} is continuous, a vector containing
 #'   the cutpoints for the partitioning of \eqn{Y}.
-#' \item niterations: Only when at least one of the input variables is
+#' \item n_iterations: Only when at least one of the input variables is
 #'   continuous, the number of iterations it takes to reach the convergence of
 #'   the estimated information.
-#' \item iterationN: Only when at least one of the input variables is
-#'   continuous, the list of vectors of cutpoints of each iteration.
+#' \item iteration1, iteration2, ... Only when at least one of the input
+#'   variables is continuous, the list of vectors of cutpoints of each
+#'   iteration.
 #' \item info: The estimation of (conditional) mutual information without the
 #' complexity cost.
 #' \item infok: The estimation of (conditional) mutual information with the
@@ -122,7 +123,7 @@
 #' message("I(X;Y|Z) = ", res$info)
 #' }
 #'
-computeMutualInfo <- function(X, Y,
+computeMutualInfo <- function(x, y,
                               df_conditioning = NULL,
                               maxbins = NULL,
                               cplx = c("nml", "mdl"),
@@ -142,7 +143,7 @@ computeMutualInfo <- function(X, Y,
   )
   cplx <- match.arg(cplx)
 
-  input_data = data.frame(X, Y)
+  input_data = data.frame(x, y)
   if (!is.null(df_conditioning)) {
     input_data <- data.frame(input_data, df_conditioning)
   }
@@ -151,7 +152,7 @@ computeMutualInfo <- function(X, Y,
     stop(paste(
       "Differing number of rows between `sample_weights` and input data:",
       length(sample_weights),
-      length(X)
+      length(x)
     ))
   }
 
@@ -239,7 +240,7 @@ computeMutualInfo <- function(X, Y,
     # Parse cutpointsmatrix
     epsilon <- min(c(sd(X_num), sd(Y_num))) / 100
     niterations <- nrow(rescpp$cutpointsmatrix) / maxbins
-    result$niterations <- niterations
+    result$n_iterations <- niterations
     for (i in 0:(niterations - 1)) {
       result[[paste0("iteration", i + 1)]] <- list()
       for (l in 1:2) {
@@ -281,8 +282,8 @@ computeMutualInfo <- function(X, Y,
   }
 
   if (plot) {
-    nameDist1 <- deparse(substitute(X))
-    nameDist2 <- deparse(substitute(Y))
+    nameDist1 <- deparse(substitute(x))
+    nameDist2 <- deparse(substitute(y))
     if (base::requireNamespace("ggplot2", quietly = TRUE) &&
         base::requireNamespace("gridExtra", quietly = TRUE)) {
       if (all(is_continuous[1:2])) {
@@ -335,12 +336,12 @@ computeMutualInfo <- function(X, Y,
 #' \item Affeldt et al., \emph{Bioinformatics 2016}
 #' }
 #'
-#' @param X [a vector]
-#' A vector that contains the observational data of the first variable.
-#' @param Y [a vector]
-#' A vector that contains the observational data of the second variable.
-#' @param Z [a vector]
-#' A vector that contains the observational data of the third variable.
+#' @param x [a vector]
+#' The \eqn{X} vector that contains the observational data of the first variable.
+#' @param y [a vector]
+#' The \eqn{Y} vector that contains the observational data of the second variable.
+#' @param z [a vector]
+#' The \eqn{Z} vector that contains the observational data of the third variable.
 #' @param df_conditioning [a data frame]
 #' The data frame of the observations of the set of conditioning variables
 #' \eqn{U}.
@@ -404,7 +405,7 @@ computeMutualInfo <- function(X, Y,
 #' message("Ik(X;Y;Z) = ", res$i3k)
 #' }
 #'
-computeThreePointInfo <- function(X, Y, Z,
+computeThreePointInfo <- function(x, y, z,
                               df_conditioning = NULL,
                               maxbins = NULL,
                               cplx = c("nml", "mdl"),
@@ -423,7 +424,7 @@ computeThreePointInfo <- function(X, Y, Z,
   )
   cplx <- match.arg(cplx)
 
-  input_data = data.frame(X, Y, Z)
+  input_data = data.frame(x, y, z)
   if (!is.null(df_conditioning)) {
     input_data <- data.frame(input_data, df_conditioning)
   }
@@ -432,7 +433,7 @@ computeThreePointInfo <- function(X, Y, Z,
     stop(paste(
       "Differing number of rows between `sample_weights` and input data:",
       length(sample_weights),
-      length(X)
+      length(x)
     ))
   }