Merge pull request #194 from hneth/master

Maintenance

DESCRIPTION

@@ -1,8 +1,8 @@
 Package: FFTrees
 Type: Package
 Title: Generate, Visualise, and Evaluate Fast-and-Frugal Decision Trees
-Version: 1.9.0.9027
-Date: 2023-05-13
+Version: 1.9.0.9028
+Date: 2023-05-15
 Authors@R: c(person("Nathaniel", "Phillips", role = c("aut"), email = "Nathaniel.D.Phillips.is@gmail.com", comment = c(ORCID = "0000-0002-8969-7013")),
              person("Hansjoerg", "Neth", role = c("aut", "cre"), email = "h.neth@uni.kn", comment = c(ORCID = "0000-0001-5427-3141")),
              person("Jan", "Woike", role = "aut", comment = c(ORCID = "0000-0002-6816-121X")),

NEWS.md

@@ -1,7 +1,7 @@
 
 # FFTrees 1.9
 
-## 1.9.0.9027
+## 1.9.0.9028
 
 This is the current development version of **FFTrees**, available at <https://github.com/ndphillips/FFTrees>.
 
@@ -473,6 +473,6 @@ Thus, the main tree building function is now `FFTrees()` and the new tree object
 
 ------ 
 
-[File `NEWS.md` last updated on 2023-05-10.]
+[File `NEWS.md` last updated on 2023-05-14.]
 
 <!-- eof. -->

R/FFTreesdata_doc.R

@@ -7,21 +7,28 @@
 
 #' Blood donation data
 #'
+#' Data taken from the Blood Transfusion Service Center in Hsin-Chu City in Taiwan
+#'
 #' @format A data frame containing 748 rows and 5 columns.
 #'
 #' \describe{
 #'   \item{recency}{Months since last donation}
 #'   \item{frequency}{Total number of donations}
-#'   \item{total}{Total blood donated in c.c.}
+#'   \item{total}{Total blood donated (in c.c.)}
 #'   \item{time}{Months since first donation}
-#'   \item{donation.crit}{Did he/she donated blood in March 2007?}
-#'
-#'   ...
+#'   \item{donation.crit}{\emph{Criterion}: Did the person donate blood (in March 2007)?
+#'   Values: \code{0}/no vs. \code{1}/yes (76.2\% vs.\ 23.8\%).}
 #' }
 #'
 #' @family datasets
 #'
 #' @source https://archive.ics.uci.edu/ml/datasets/Blood+Transfusion+Service+Center
+#'
+#' Original owner and donor:
+#' Prof. I-Cheng Yeh
+#' Department of Information Management
+#' Chung-Hua University
+#'
 
 "blood"
 
@@ -43,14 +50,18 @@
 #'   \item{chromatin}{Bland Chromatin}
 #'   \item{nucleoli}{Normal Nucleoli}
 #'   \item{mitoses}{Mitoses}
-#'   \item{diagnosis}{Is cancer present? TRUE or FALSE}
-#'
-#'   ...
+#'   \item{diagnosis}{\emph{Criterion}: Absence/presence of breast cancer.
+#'   Values: \code{FALSE} vs. \code{TRUE} (65.0\% vs.\ 35.0\%).}
 #' }
 #'
 #' @family datasets
 #'
-#' @source https://archive.ics.uci.edu/ml/datasets/Breast+Cancer+Wisconsin+(Original)
+#' @source \url{https://archive.ics.uci.edu/ml/datasets/Breast+Cancer+Wisconsin+(Original)}
+#'
+#' Original creator:
+#' Dr. William H. Wolberg (physician)
+#' University of Wisconsin Hospitals
+#' Madison, Wisconsin, USA
 
 "breastcancer"
 
@@ -73,15 +84,15 @@
 #'   \item{persons}{Numeric}
 #'   \item{luggage}{Numeric}
 #'   \item{safety}{Factor}
-#'   \item{acceptability}{Factor}
-#'
-#'   ...
+#'   \item{acceptability}{\emph{Criterion}: Category of acceptability rating (as factor).
+#'   Values: \code{unacc}/\code{acc}/\code{good}/\code{vgood} (70.0\%/22.2\%/4.0\%/3.8\%).}
 #' }
 #'
 #' @family datasets
 #'
 #' @references
-#' Bohanec, M., Rajkovic, V. (1990): Expert system for decision making. Sistemica 1 (1), pp. 145-157.
+#' Bohanec, M., Rajkovic, V. (1990): Expert system for decision making.
+#' \emph{Sistemica}, \emph{1} (1), 145--157.
 #'
 #' @source \url{http://archive.ics.uci.edu/ml/datasets/Car+Evaluation}
 #'
@@ -96,12 +107,14 @@
 #'
 #' A subset of the 1987 National Indonesia Contraceptive Prevalence Survey.
 #'
-#' The samples describe married women who were either not pregnant or do not know if they were at the time of interview.
+#' The samples describe married women who were either not pregnant
+#' or do not know if they were pregnant at the time of the interview.
 #'
-#' The problem consists in predicting a woman's current contraceptive method choice (here: binarized \code{cont.crit})
+#' The problem consists in predicting a woman's current contraceptive method choice
+#' (here: binarized \code{cont.crit})
 #' based on her demographic and socio-economic characteristics.
 #'
-#' @format A data frame containing 1473 rows and 10 columns.
+#' @format A data frame containing 1473 cases (rows) and 10 variables (columns).
 #'
 #' \describe{
 #'   \item{wife.age}{Numeric}
@@ -113,9 +126,8 @@
 #'   \item{hus.occ}{Factor}
 #'   \item{sol}{Factor}
 #'   \item{media}{Numeric}
-#'   \item{cont.crit}{numeric}
-#'
-#'   ...
+#'   \item{cont.crit}{\emph{Criterion}: Use of a contraceptive (as logical).
+#'   Values: \code{FALSE} vs. \code{TRUE} (42.7\% vs.\ 57.3\%).}
 #' }
 #'
 #' @family datasets
@@ -126,12 +138,37 @@
 "contraceptive"
 
 
-
 #  5. creditapproval: ------
 
 #' Credit approval data
 #'
-#' @format A data frame containing 690 rows and 15 columns
+#' This data reports predictors and the result of credit card applications.
+#' Its attribute names and values have been changed to symbols to protect confidentiality.
+#'
+#' This dataset contains a mix of attributes -- continuous, nominal with small Ns,
+#' and nominal with larger Ns. There are also a few missing values.
+#'
+#' @format A data frame containing 690 cases (rows) and 15 variables (columns).
+#'
+#' \describe{
+#'  \item{c.1}{categorical: b, a}
+#'  \item{c.2}{continuous}
+#'  \item{c.3}{continuous}
+#'  \item{c.4}{categorical: u, y, l, t}
+#'  \item{c.5}{categorical: g, p, gg}
+#'  \item{c.6}{categorical: c, d, cc, i, j, k, m, r, q, w, x, e, aa, ff}
+#'  \item{c.7}{categorical: v, h, bb, j, n, z, dd, ff, o}
+#'  \item{c.8}{continuous}
+#'  \item{c.9}{categorical: t, f}
+#'  \item{c.10}{categorical: t, f}
+#'  \item{c.11}{continuous}
+#'  \item{c.12}{categorical: t, f}
+#'  \item{c.13}{categorical: g, p, s}
+#'  \item{c.14}{continuous}
+#'  \item{c.15}{continuous}
+#'  \item{crit}{\emph{Criterion}: Credit approval.
+#'  Values: \code{TRUE}/$+$ vs. \code{FALSE}/$-$ (44.5\% vs. 55.5\%).}
+#'  }
 #'
 #' @family datasets
 #'
@@ -140,6 +177,8 @@
 "creditapproval"
 
 
+# +++ here now +++
+
 
 #  6. fertility: ------
 

R/util_data.R

@@ -450,7 +450,10 @@ replace_NA_num <- function(df){
 
 # ToDo: ------
 
+# - Create describe_data() analogous to handle_NA_data():
+#   dims / criterion / predictors (by type) / NA values (by type)
 # - Handle the consequences of allowing NAs in numeric predictors.
 # - Handle NAs in the criterion variable.
 
+
 # eof.

R/util_gfft.R

@@ -1757,7 +1757,7 @@ reorder_nodes <- function(fft, order = NA, quiet = FALSE){
 # Goal: Apply reorder_nodes(fft) to get all possible permutations of cues for a fft.
 #
 # Input:
-#   fft: 1 FFT (as df, 1 row per cue)
+#   fft: 1 FFT (as tidy df, 1 row per cue)
 #
 # Output:
 #   A set of FFT definitions in all possible cue orders (predicting 1/Signal/TRUE for all changed cues, as reorder_nodes())
@@ -1840,7 +1840,7 @@ all_node_orders <- function(fft, quiet = FALSE){
 #
 # Method: Use flip_exits() on nodes = `all_combinations()` for all length values of 1:(n_cues - 1).
 #
-# Input: fft: 1 FFT (as df, 1 row per cue).
+# Input: fft: 1 FFT (as tidy df, 1 row per cue).
 # Output: A set of FFT definitions (ffts_df).
 
 
@@ -1919,9 +1919,10 @@ all_exit_structures <- function(fft, quiet = FALSE){
 
 # Goal: Get all subtrees of an FFT.
 #
-# Input: fft: 1 FFT (as df, 1 row per cue).
+# Input: fft: 1 FFT (as tidy df, 1 row per cue).
 # Output: A set of FFT definitions (ffts_df).
 
+
 all_node_subsets <- function(fft, quiet = FALSE){
 
   # Prepare: ----
@@ -1994,7 +1995,7 @@ all_node_subsets <- function(fft, quiet = FALSE){
 #       3. all_exit_structures()
 #       to get ALL possible variants of a given FFT.
 #
-# Input: fft: 1 FFT (as df, 1 row per cue).
+# Input: fft: 1 FFT (as tidy df, 1 row per cue).
 # Output: A set of FFT definitions (ffts_df).
 
 

README.Rmd

@@ -41,14 +41,12 @@ url_JDM_doi <- "https://doi.org/10.1017/S1930297500006239"
 <!-- Devel badges end. -->
 
 
-
 <!-- Release badges start: -->
 <!-- [![CRAN status](https://www.r-pkg.org/badges/version/FFTrees)](https://CRAN.R-project.org/package=FFTrees) -->
 <!-- [![Total downloads](https://cranlogs.r-pkg.org/badges/grand-total/FFTrees?color='00a9e0')](https://www.r-pkg.org/pkg/FFTrees) -->
 <!-- Release badges end. -->
 
 
-
 <!-- ALL badges start: --> 
 <!-- [![CRAN status](https://www.r-pkg.org/badges/version/FFTrees)](https://CRAN.R-project.org/package=FFTrees) -->
 <!-- [![Build Status](https://travis-ci.org/ndphillips/FFTrees.svg?branch=master)](https://travis-ci.org/ndphillips/FFTrees) -->

README.md

@@ -2,7 +2,7 @@
 <!-- README.md is generated from README.Rmd. Please only edit the .Rmd file! -->
 <!-- Title, version and logo: -->
 
-# FFTrees 1.9.0.9027 <img src = "./inst/FFTrees_Logo.jpg" align = "right" alt = "FFTrees" width = "225" />
+# FFTrees 1.9.0.9028 <img src = "./inst/FFTrees_Logo.jpg" align = "right" alt = "FFTrees" width = "225" />
 
 <!-- Devel badges start: -->
 
@@ -333,6 +333,6 @@ Examples include:
 
 ------------------------------------------------------------------------
 
-\[File `README.Rmd` last updated on 2023-05-04.\]
+\[File `README.Rmd` last updated on 2023-05-14.\]
 
 <!-- eof. -->

inst/WORDLIST

@@ -22,6 +22,7 @@ Gundle
 Haehner
 Hunink
 ISI
+Interpretable
 Kagan
 Klement
 Lepiota
@@ -42,6 +43,7 @@ SDT
 Seedat
 Sistemica
 Sonke
+ToDo
 UCI
 Virginica
 Visualise
@@ -63,7 +65,9 @@ cp
 cr
 data's
 data’s
+datur
 dec
+df
 dfan
 discriminability
 dl
@@ -79,20 +83,18 @@ fft
 flourosopy
 fourier
 gilled
-github
-glm
 heartdisease
 https
 ics
 ifan
+ijrobp
 jan
 laplace
-lr
 mV
+magrittr
 mcu
 mon
 nd
-ndphillips
 np
 npv
 oldpeak
@@ -104,14 +106,12 @@ ppv
 px
 randomForest
 restecg
-rf
-rlr
 rpart
 socio
 specificities
 stereotactic
 subpanels
-svm
+tertium
 testthat
 th
 thal