P281424/AMR
1
0
Fork 0
mirror of https://github.com/msberends/AMR.git synced 2025-07-08 11:51:59 +02:00
Code Releases Activity

new g.test() and edited freq()

Browse Source
This commit is contained in:
dr. M.S. (Matthijs) Berends
2018-07-01 21:40:37 +02:00
parent f7af8a81da
commit 3527894b49
18 changed files with 893 additions and 296 deletions
Download Patch File Download Diff File Expand all files Collapse all files

395
R/freq.R
View File

@ -18,17 +18,17 @@
#' Frequency table
#'
#' Create a frequency table of a vector of data, a single column or a maximum of 9 columns of a data frame. Supports markdown for reports. \code{top_freq} can be used to get the top/bottom \emph{n} items of a frequency table, with counts as names.
#' @param x data
#' @param sort.count sort on count. Use \code{FALSE} to sort alphabetically on item.
#' @param nmax number of row to print. The default, \code{15}, uses \code{\link{getOption}("max.print.freq")}. Use \code{nmax = 0} or \code{nmax = NA} to print all rows.
#' Create a frequency table of a vector with items or a data frame. Supports quasiquotation and markdown for reports. \code{top_freq} can be used to get the top/bottom \emph{n} items of a frequency table, with counts as names.
#' @param x vector with items, or \code{data.frame}
#' @param ... up to nine different columns of \code{x} to calculate frequencies from, see Examples
#' @param sort.count sort on count, i.e. frequencies. Use \code{FALSE} to sort alphabetically on item.
#' @param nmax number of row to print. The default, \code{15}, uses \code{\link{getOption}("max.print.freq")}. Use \code{nmax = 0}, \code{nmax = NULL} or \code{nmax = NA} to print all rows.
#' @param na.rm a logical value indicating whether NA values should be removed from the frequency table. The header will always print the amount of \code{NA}s.
#' @param row.names a logical value indicating whether row indices should be printed as \code{1:nrow(x)}
#' @param markdown print table in markdown format (this forces \code{nmax = NA})
#' @param as.data.frame return frequency table without header as a \code{data.frame} (e.g. to assign the table to an object)
#' @param digits how many significant digits are to be used for numeric values (not for the items themselves, that depends on \code{\link{getOption}("digits")})
#' @param digits how many significant digits are to be used for numeric values in the header (not for the items themselves, that depends on \code{\link{getOption}("digits")})
#' @param sep a character string to separate the terms when selecting multiple columns
#' @param f a frequency table as \code{data.frame}, used as \code{freq(..., as.data.frame = TRUE)}
#' @param f a frequency table
#' @param n number of top \emph{n} items to return, use -n for the bottom \emph{n} items. It will include more than \code{n} rows if there are ties.
#' @details This package also has a vignette available about this function, run: \code{browseVignettes("AMR")} to read it.
#'
@ -54,51 +54,82 @@
#' @importFrom grDevices boxplot.stats
#' @importFrom dplyr %>% select pull n_distinct group_by arrange desc mutate summarise
#' @importFrom utils browseVignettes
#' @importFrom tibble tibble
#' @importFrom rlang ensyms
#' @keywords summary summarise frequency freq
#' @rdname freq
#' @return \itemize{
#' \item{When using \code{as.data.frame = FALSE} (default): only printed text}
#' \item{When using \code{as.data.frame = TRUE}: a \code{data.frame} object with an additional class \code{"frequency_tbl"}}
#' }
#' @name freq
#' @return A \code{data.frame} with an additional class \code{"frequency_tbl"}
#' @export
#' @examples
#' library(dplyr)
#'
#' # this all gives the same result:
#' freq(septic_patients$hospital_id)
#' freq(septic_patients[, "hospital_id"])
#' septic_patients$hospital_id %>% freq()
#' septic_patients[, "hospital_id"] %>% freq()
#' septic_patients %>% freq("hospital_id")
#' septic_patients %>% freq(hospital_id) # <- easiest to remember when used to tidyverse
#'
#' # you could use `select`...
#' septic_patients %>%
#' filter(hospital_id == "A") %>%
#' select(bactid) %>%
#' freq()
#'
#' # ... or you use `freq` to select it immediately
#' septic_patients %>%
#' filter(hospital_id == "A") %>%
#' freq(bactid)
#'
#' # select multiple columns; they will be pasted together
#' septic_patients %>%
#' left_join_microorganisms %>%
#' filter(hospital_id == "A") %>%
#' select(genus, species) %>%
#' freq()
#' freq(genus, species)
#'
#' # save frequency table to an object
#' years <- septic_patients %>%
#' mutate(year = format(date, "%Y")) %>%
#' select(year) %>%
#' freq(as.data.frame = TRUE)
#' freq(year)
#' years %>% pull(item)
#'
#' # get top 10 bugs of hospital A as a vector
#' septic_patients %>%
#' filter(hospital_id == "A") %>%
#' select(bactid) %>%
#' freq(as.data.frame = TRUE) %>%
#' freq(bactid) %>%
#' top_freq(10)
freq <- function(x,
sort.count = TRUE,
nmax = getOption("max.print.freq"),
na.rm = TRUE,
row.names = TRUE,
markdown = FALSE,
as.data.frame = FALSE,
digits = 2,
sep = " ") {
frequency_tbl <- function(x,
...,
sort.count = TRUE,
nmax = getOption("max.print.freq"),
na.rm = TRUE,
row.names = TRUE,
markdown = FALSE,
digits = 2,
sep = " ") {
if (any(class(x) == 'data.frame')) {
x.name <- deparse(substitute(x))
if (x.name == ".") {
x.name <- NULL
}
dots <- rlang::ensyms(...)
ndots <- length(dots)
if (ndots > 0 & ndots < 10) {
cols <- as.character(dots)
x <- x[, cols]
} else if (ndots >= 10) {
stop('A maximum of 9 columns can be analysed at the same time.', call. = FALSE)
} else {
cols <- NULL
}
} else {
x.name <- NULL
cols <- NULL
}
mult.columns <- 0
@ -117,64 +148,64 @@ freq <- function(x,
colnames(x) <- LETTERS[1:ncol(x)]
if (ncol(x) == 2) {
x$total <- paste(x$A %>% as.character(),
x$B %>% as.character(),
sep = sep)
x$B %>% as.character(),
sep = sep)
} else if (ncol(x) == 3) {
x$total <- paste(x$A %>% as.character(),
x$B %>% as.character(),
x$C %>% as.character(),
sep = sep)
x$B %>% as.character(),
x$C %>% as.character(),
sep = sep)
} else if (ncol(x) == 4) {
x$total <- paste(x$A %>% as.character(),
x$B %>% as.character(),
x$C %>% as.character(),
x$D %>% as.character(),
sep = sep)
x$B %>% as.character(),
x$C %>% as.character(),
x$D %>% as.character(),
sep = sep)
} else if (ncol(x) == 5) {
x$total <- paste(x$A %>% as.character(),
x$B %>% as.character(),
x$C %>% as.character(),
x$D %>% as.character(),
x$E %>% as.character(),
sep = sep)
x$B %>% as.character(),
x$C %>% as.character(),
x$D %>% as.character(),
x$E %>% as.character(),
sep = sep)
} else if (ncol(x) == 6) {
x$total <- paste(x$A %>% as.character(),
x$B %>% as.character(),
x$C %>% as.character(),
x$D %>% as.character(),
x$E %>% as.character(),
x$F %>% as.character(),
sep = sep)
x$B %>% as.character(),
x$C %>% as.character(),
x$D %>% as.character(),
x$E %>% as.character(),
x$F %>% as.character(),
sep = sep)
} else if (ncol(x) == 7) {
x$total <- paste(x$A %>% as.character(),
x$B %>% as.character(),
x$C %>% as.character(),
x$D %>% as.character(),
x$E %>% as.character(),
x$F %>% as.character(),
x$G %>% as.character(),
sep = sep)
x$B %>% as.character(),
x$C %>% as.character(),
x$D %>% as.character(),
x$E %>% as.character(),
x$F %>% as.character(),
x$G %>% as.character(),
sep = sep)
} else if (ncol(x) == 8) {
x$total <- paste(x$A %>% as.character(),
x$B %>% as.character(),
x$C %>% as.character(),
x$D %>% as.character(),
x$E %>% as.character(),
x$F %>% as.character(),
x$G %>% as.character(),
x$H %>% as.character(),
sep = sep)
x$B %>% as.character(),
x$C %>% as.character(),
x$D %>% as.character(),
x$E %>% as.character(),
x$F %>% as.character(),
x$G %>% as.character(),
x$H %>% as.character(),
sep = sep)
} else if (ncol(x) == 9) {
x$total <- paste(x$A %>% as.character(),
x$B %>% as.character(),
x$C %>% as.character(),
x$D %>% as.character(),
x$E %>% as.character(),
x$F %>% as.character(),
x$G %>% as.character(),
x$H %>% as.character(),
x$I %>% as.character(),
sep = sep)
x$B %>% as.character(),
x$C %>% as.character(),
x$D %>% as.character(),
x$E %>% as.character(),
x$F %>% as.character(),
x$G %>% as.character(),
x$H %>% as.character(),
x$I %>% as.character(),
sep = sep)
}
x <- x$total
@ -183,9 +214,6 @@ freq <- function(x,
stop('A maximum of 9 columns can be analysed at the same time.', call. = FALSE)
}
}
if (markdown == TRUE & as.data.frame == TRUE) {
warning('`as.data.frame = TRUE` will be ignored when `markdown = TRUE`.')
}
if (mult.columns > 1) {
NAs <- x[is.na(x) | x == trimws(strrep('NA ', mult.columns))]
@ -264,22 +292,12 @@ freq <- function(x,
x <- x %>% format(formatdates)
}
if (as.data.frame == FALSE) {
cat(header)
}
if (all(is.na(x))) {
cat('\n\nNo observations.\n')
return(invisible())
}
if (n_distinct(x) == length(x)) {
warning('All observations are unique.', call. = FALSE)
}
nmax.set <- !missing(nmax)
if (is.null(nmax) & is.null(base::getOption("max.print.freq", default = NULL))) {
if (!nmax.set & is.null(nmax) & is.null(base::getOption("max.print.freq", default = NULL))) {
# default for max print setting
nmax <- 15
} else if (is.null(nmax)) {
nmax <- length(x)
}
if (nmax == 0 | is.na(nmax) | is.null(nmax)) {
@ -290,26 +308,25 @@ freq <- function(x,
# create table with counts and percentages
column_names <- c('Item', 'Count', 'Percent', 'Cum. Count', 'Cum. Percent', '(Factor Level)')
column_names_df <- c('item', 'count', 'percent', 'cum_count', 'cum_percent', 'factor_level')
if (any(class(x) == 'factor')) {
df <- tibble::tibble(Item = x,
Fctlvl = x %>% as.integer()) %>%
group_by(Item, Fctlvl)
df <- tibble::tibble(item = x,
fctlvl = x %>% as.integer()) %>%
group_by(item, fctlvl)
column_align <- c('l', 'r', 'r', 'r', 'r', 'r')
} else {
df <- tibble::tibble(Item = x) %>%
group_by(Item)
df <- tibble::tibble(item = x) %>%
group_by(item)
# strip factor lvl from col names
column_names <- column_names[1:length(column_names) - 1]
column_names_df <- column_names_df[1:length(column_names_df) - 1]
column_align <- c(x_align, 'r', 'r', 'r', 'r')
}
df <- df %>%
summarise(Count = n(),
Percent = (n() / length(x)) %>% percent(force_zero = TRUE))
df <- df %>% summarise(count = n())
if (df$Item %>% paste(collapse = ',') %like% '\033') {
if (df$item %>% paste(collapse = ',') %like% '\033') {
df <- df %>%
mutate(Item = Item %>%
mutate(item = item %>%
# remove escape char
# see https://en.wikipedia.org/wiki/Escape_character#ASCII_escape_character
gsub('\033', ' ', ., fixed = TRUE))
@ -317,95 +334,54 @@ freq <- function(x,
# sort according to setting
if (sort.count == TRUE) {
df <- df %>% arrange(desc(Count), Item)
df <- df %>% arrange(desc(count), item)
} else {
if (any(class(x) == 'factor')) {
df <- df %>% arrange(Fctlvl, Item)
df <- df %>% arrange(fctlvl, item)
} else {
df <- df %>% arrange(Item)
df <- df %>% arrange(item)
}
}
# add cumulative values
df$Cum <- cumsum(df$Count)
df$CumTot <- (df$Cum / sum(df$Count, na.rm = TRUE)) %>% percent(force_zero = TRUE)
df$Cum <- df$Cum %>% format()
df <- as.data.frame(df, stringsAsFactors = FALSE)
df$percent <- df$count / base::sum(df$count, na.rm = TRUE)
df$cum_count <- base::cumsum(df$count)
df$cum_percent <- df$cum_count / base::sum(df$count, na.rm = TRUE)
if (any(class(x) == 'factor')) {
# put factor last
df <- df %>% select(Item, Count, Percent, Cum, CumTot, Fctlvl)
df <- df %>% select(item, count, percent, cum_count, cum_percent, fctlvl)
}
if (as.data.frame == TRUE) {
# assign to object
df[, 3] <- df[, 2] / sum(df[, 2], na.rm = TRUE)
df[, 4] <- cumsum(df[, 2])
df[, 5] <- df[, 4] / sum(df[, 2], na.rm = TRUE)
colnames(df) <- column_names_df
df <- as.data.frame(df, stringsAsFactors = FALSE)
class(df) <- c('frequency_tbl', class(df))
return(df)
}
colnames(df) <- column_names_df
class(df) <- c('frequency_tbl', class(df))
attr(df, 'package') <- 'AMR'
attr(df, 'package.version') <- packageDescription('AMR')$Version
if (markdown == TRUE) {
tblformat <- 'markdown'
tbl_format <- 'markdown'
} else {
tblformat <- 'pandoc'
tbl_format <- 'pandoc'
}
# save old NA setting for kable
opt.old <- options()$knitr.kable.NA
options(knitr.kable.NA = "<NA>")
attr(df, 'opt') <- list(data = x.name,
vars = cols,
header = header,
row_names = row.names,
column_names = column_names,
column_align = column_align,
tbl_format = tbl_format,
nmax = nmax,
nmax.set = nmax.set)
Count.rest <- sum(df[nmax.1:nrow(df), 'Count'], na.rm = TRUE)
if (any(class(x) %in% c('double', 'integer', 'numeric', 'raw', 'single'))) {
df <- df %>% mutate(Item = format(Item))
}
df <- df %>% mutate(Count = format(Count))
if (nrow(df) > nmax.1 & markdown == FALSE) {
df2 <- df[1:nmax,]
print(
knitr::kable(df2,
format = tblformat,
row.names = row.names,
col.names = column_names,
align = column_align,
padding = 1)
)
if (nmax.set == TRUE) {
cat('[ reached `nmax = ', nmax, '`', sep = '')
} else {
cat('[ reached getOption("max.print.freq")')
}
cat(' -- omitted ',
format(nrow(df) - nmax),
' entries, n = ',
format(Count.rest),
' (',
(Count.rest / length(x)) %>% percent(force_zero = TRUE),
') ]\n', sep = '')
} else {
print(
knitr::kable(df,
format = tblformat,
row.names = row.names,
col.names = column_names,
align = column_align,
padding = 1)
)
}
cat('\n')
# reset old kable setting
options(knitr.kable.NA = opt.old)
return(invisible())
df
}
#' @rdname freq
#' @export
frequency_tbl <- freq
freq <- frequency_tbl
#' @rdname freq
#' @export
@ -426,4 +402,95 @@ top_freq <- function(f, n) {
vect
}
#' @rdname print
#' @exportMethod print.frequency_tbl
#' @importFrom knitr kable
#' @importFrom dplyr n_distinct
#' @export
print.frequency_tbl <- function(x, ...) {
opt <- attr(x, 'opt')
if (!is.null(opt$data) & !is.null(opt$vars)) {
title <- paste0("of `", paste0(opt$vars, collapse = "` and `"), "` from ", opt$data)
} else if (!is.null(opt$data) & is.null(opt$vars)) {
title <- paste("of", opt$data)
} else if (is.null(opt$data) & !is.null(opt$vars)) {
title <- paste0("of `", paste0(opt$vars, collapse = "` and `"), "`")
} else {
title <- ""
}
cat("Frequency table", title, "\n\n")
if (!is.null(opt$header)) {
cat(opt$header)
}
if (NROW(x) == 0) {
cat('\n\nNo observations.\n')
return(invisible())
}
if (all(x$count == 1)) {
warning('All observations are unique.', call. = FALSE)
}
# save old NA setting for kable
opt.old <- options()$knitr.kable.NA
options(knitr.kable.NA = "<NA>")
if (nrow(x) > opt$nmax & opt$tbl_format != "markdown") {
x.rows <- nrow(x)
x.unprinted <- base::sum(x[(opt$nmax + 1):nrow(x), 'count'], na.rm = TRUE)
x.printed <- base::sum(x$count) - x.unprinted
x <- x[1:opt$nmax,]
if (opt$nmax.set == TRUE) {
footer <- paste('[ reached `nmax = ', opt$nmax, '`', sep = '')
} else {
footer <- '[ reached getOption("max.print.freq")'
}
footer <- paste(footer,
' -- omitted ',
format(x.rows - opt$nmax),
' entries, n = ',
format(x.unprinted),
' (',
(x.unprinted / (x.unprinted + x.printed)) %>% percent(force_zero = TRUE),
') ]\n', sep = '')
} else {
footer <- NULL
}
if (any(class(x$item) %in% c('double', 'integer', 'numeric', 'raw', 'single'))) {
x$item <- format(x$item)
}
x$count <- format(x$count)
x$percent <- percent(x$percent, force_zero = TRUE)
x$cum_count <- format(x$cum_count)
x$cum_percent <- percent(x$cum_percent, force_zero = TRUE)
print(
knitr::kable(x,
format = opt$tbl_format,
row.names = opt$row_names,
col.names = opt$column_names,
align = opt$column_align,
padding = 1)
)
if (!is.null(footer)) {
cat(footer)
}
cat('\n')
# reset old kable setting
options(knitr.kable.NA = opt.old)
return(invisible())
}

264
R/g.test.R Normal file
View File

@ -0,0 +1,264 @@
# ==================================================================== #
# TITLE #
# Antimicrobial Resistance (AMR) Analysis #
# #
# AUTHORS #
# Berends MS (m.s.berends@umcg.nl), Luz CF (c.f.luz@umcg.nl) #
# #
# LICENCE #
# This program is free software; you can redistribute it and/or modify #
# it under the terms of the GNU General Public License version 2.0, #
# as published by the Free Software Foundation. #
# #
# This program is distributed in the hope that it will be useful, #
# but WITHOUT ANY WARRANTY; without even the implied warranty of #
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the #
# GNU General Public License for more details. #
# ==================================================================== #
#' \emph{G}-test of matrix or vector
#'
#' A \emph{G}-test can be used to see whether the number of observations in each category fits a theoretical expectation (called a \strong{\emph{G}-test of goodness-of-fit}), or to see whether the proportions of one variable are different for different values of the other variable (called a \strong{\emph{G}-test of independence}).
#' @param x numeric vector or matrix
#' @param y expected value of \code{x}. Leave empty to determine automatically. This can also be ratios of \code{x}, e.g. calculated with \code{\link{vector2ratio}}.
#' @param alpha value to test the p value against
#' @param info logical to determine whether the analysis should be printed
#' @param minimum the test with fail if any of the observed values is below this value. Use \code{minimum = 30} for microbial epidemiology, to prevent calculating a p value when less than 30 isolates are available.
#' @section \emph{G}-test of goodness-of-fit (likelihood ratio test):
#' Use the \emph{G}-test of goodness-of-fit when you have one nominal variable with two or more values (such as male and female, or red, pink and white flowers). You compare the observed counts of numbers of observations in each category with the expected counts, which you calculate using some kind of theoretical expectation (such as a 1:1 sex ratio or a 1:2:1 ratio in a genetic cross).
#'
#' If the expected number of observations in any category is too small, the \emph{G}-test may give inaccurate results, and you should use an exact test instead. See the web page on small sample sizes for discussion of what "small" means.
#'
#' The \emph{G}-test of goodness-of-fit is an alternative to the chi-square test of goodness-of-fit; each of these tests has some advantages and some disadvantages, and the results of the two tests are usually very similar.
#'
#' @section \emph{G}-test of independence:
#' Use the \emph{G}-test of independence when you have two nominal variables, each with two or more possible values. You want to know whether the proportions for one variable are different among values of the other variable.
#'
#' It is also possible to do a \emph{G}-test of independence with more than two nominal variables. For example, Jackson et al. (2013) also had data for children under 3, so you could do an analysis of old vs. young, thigh vs. arm, and reaction vs. no reaction, all analyzed together.
#'
#' Fisher's exact test is more accurate than the \emph{G}-test of independence when the expected numbers are small, so it is recommend to only use the \emph{G}-test if your total sample size is greater than 1000.
#'
#' The \emph{G}-test of independence is an alternative to the chi-square test of independence, and they will give approximately the same results.
#' @section How the test works:
#' Unlike the exact test of goodness-of-fit, the \emph{G}-test does not directly calculate the probability of obtaining the observed results or something more extreme. Instead, like almost all statistical tests, the \emph{G}-test has an intermediate step; it uses the data to calculate a test statistic that measures how far the observed data are from the null expectation. You then use a mathematical relationship, in this case the chi-square distribution, to estimate the probability of obtaining that value of the test statistic.
#'
#' The \emph{G}-test uses the log of the ratio of two likelihoods as the test statistic, which is why it is also called a likelihood ratio test or log-likelihood ratio test. The formula to calculate a \emph{G}-statistic is:
#'
#' \code{G <- 2 * sum(x * log(x / x.expected))}
#'
#' Since this is chi-square distributed, the p value can be calculated with:
#'
#' \code{p <- 1 - stats::pchisq(G, df))}
#'
#' where \code{df} are the degrees of freedom: \code{max(NROW(x) - 1, 1) * max(NCOL(x) - 1, 1)}.
#'
#' If there are more than two categories and you want to find out which ones are significantly different from their null expectation, you can use the same method of testing each category vs. the sum of all categories, with the Bonferroni correction. You use \emph{G}-tests for each category, of course.
#' @keywords chi
#' @seealso \code{\link{chisq.test}}
#' @references McDonald, J.H. 2014. \strong{Handbook of Biological Statistics (3rd ed.)}. Sparky House Publishing, Baltimore, Maryland. \url{http://www.biostathandbook.com/gtestgof.html}.
#' @export
#' @importFrom stats pchisq
#' @importFrom dplyr %>%
#' @examples
#' # = EXAMPLE 1 =
#' # Shivrain et al. (2006) crossed clearfield rice (which are resistant
#' # to the herbicide imazethapyr) with red rice (which are susceptible to
#' # imazethapyr). They then crossed the hybrid offspring and examined the
#' # F2 generation, where they found 772 resistant plants, 1611 moderately
#' # resistant plants, and 737 susceptible plants. If resistance is controlled
#' # by a single gene with two co-dominant alleles, you would expect a 1:2:1
#' # ratio.
#'
#' x <- c(772, 1611, 737)
#' x.expected <- vector2ratio(x, ratio = "1:2:1")
#' x.expected
#' # 780 1560 780
#'
#' g.test(x, x.expected)
#' # p = 0.12574.
#'
#' # There is no significant difference from a 1:2:1 ratio.
#' # Meaning: resistance controlled by a single gene with two co-dominant
#' # alleles, is plausible.
#'
#'
#' # = EXAMPLE 2 =
#' # Red crossbills (Loxia curvirostra) have the tip of the upper bill either
#' # right or left of the lower bill, which helps them extract seeds from pine
#' # cones. Some have hypothesized that frequency-dependent selection would
#' # keep the number of right and left-billed birds at a 1:1 ratio. Groth (1992)
#' # observed 1752 right-billed and 1895 left-billed crossbills.
#'
#' x <- c(1752, 1895)
#' x.expected <- vector2ratio(x, ratio = c(1, 1))
#' x.expected
#' # 1823.5 1823.5
#'
#' g.test(x, x.expected)
#' # p = 0.01787343
#'
#' # There is a significant difference from a 1:1 ratio.
#' # Meaning: there are significantly more left-billed birds.
#'
g.test <- function(x,
y = NULL,
alpha = 0.05,
info = TRUE,
minimum = 0) {
if (sum(x) < 1000) {
warning('the sum of all observations is < 1000, consider using a Fishers Exact test instead.')
}
if (!is.numeric(x)) {
stop('`x` must be a vector or matrix with numeric values.')
}
if (!is.matrix(x) & is.null(y)) {
stop('if `x` is not a matrix, `y` must be given.')
}
# if (!is.matrix(x)) {
# x <- matrix(x, dimnames = list(rep("", length(x)), ""))
# }
x.expected <- y
# if (!is.null(x.expected) & !is.matrix(x.expected)) {
# x.expected <- matrix(x.expected, dimnames = list(rep("", length(x.expected)), ""))
# }
if (NCOL(x) > 1) {
matrix2tbl <- function(x) {
if (!is.matrix(x)) {
x <- matrix(x, dimnames = list(rep("", length(x)), ""))
}
x <- rbind(cbind(x, rowSums(x)), colSums(cbind(x, rowSums(x)))) %>%
as.data.frame()
colnames(x) <- c(paste0('c', 1:(NCOL(x) - 1)), 'Total')
rownames(x) <- c(strrep(" ", 1:(NROW(x) - 1)), 'Total')
x
}
x.with_totals <- matrix2tbl(x)
if (is.null(x.expected)) {
x.expected <- outer(rowSums(x), colSums(x), "*") / sum(x)
x.expected.with_totals <- matrix2tbl(x.expected)
}
} else {
x.with_totals <- x
if (is.null(x.expected)) {
x.expected <- matrix(rep(mean(x), length(x)), dimnames = list(rep("", length(x)), ""))
warning('Expected values set to the mean of `x`, because it consists of only one column.')
}
x.expected.with_totals <- x.expected
}
if (any(x < minimum)) {
warning('One of the observed values is lower than the required minimum of ', minimum, '.')
return(NA_real_)
}
if (any(x.expected < 5)) {
warning('One of the expected values is lower than 5, thus G-statistic approximation may be incorrect.',
'\n Consider doing an Exact test (exact.test).')
}
Gstat <- 2 * base::sum(x * log(x / x.expected), na.rm = TRUE)
df <- base::max(NROW(x) - 1, 1, na.rm = TRUE) * base::max(NCOL(x) - 1, 1, na.rm = TRUE)
pval <- 1 - stats::pchisq(Gstat, df = df)
if (info == TRUE) {
if (NROW(x) == 2 & NCOL(x) == 2) {
cat('G-test of independence\n\n')
} else {
cat('G-test of goodness-of-fit\n')
cat('(likelihood ratio test)\n\n')
}
cat(paste0("(O) Observed values:\n"))
print(x.with_totals %>% round(2))
cat('\n')
cat('(E) Expected values under null hypothesis:\n')
print(x.expected.with_totals %>% round(2))
cat('\n============[G-test]============\n')
cat(' G-statistic :', round(Gstat, 4), '\n')
cat(' Degrees of freedom :', df, '\n')
cat(' P value :', round(pval, 4), '\n')
cat(' Alpha :', round(alpha, 2), '\n')
cat(' Significance :', p.symbol(pval, "-"), '\n')
cat('================================\n\n')
}
pval
}
#' Transform vector to ratio
#' @param x vector of values
#' @param ratio vector with ratios of \code{x} and with same length (like \code{ratio = c(1, 2, 1)}) or a text with characters \code{":"}, \code{"-"} or \code{","} (like \code{ratio = "1:2:1"} or even \code{ratio = "1:2:1.25"})
#' @export
#' @seealso \code{\link{g.test}}
#' @references McDonald, J.H. 2014. \strong{Handbook of Biological Statistics (3rd ed.)}. Sparky House Publishing, Baltimore, Maryland.
#' @importFrom dplyr %>%
#' @examples
#' # = EXAMPLE 1 =
#' # Shivrain et al. (2006) crossed clearfield rice (which are resistant
#' # to the herbicide imazethapyr) with red rice (which are susceptible to
#' # imazethapyr). They then crossed the hybrid offspring and examined the
#' # F2 generation, where they found 772 resistant plants, 1611 moderately
#' # resistant plants, and 737 susceptible plants. If resistance is controlled
#' # by a single gene with two co-dominant alleles, you would expect a 1:2:1
#' # ratio.
#'
#' x <- c(772, 1611, 737)
#' x.expected <- vector2ratio(x, ratio = "1:2:1")
#' x.expected
#' # 780 1560 780
#'
#' g.test(x, x.expected)
#' # p = 0.12574.
#'
#' # There is no significant difference from a 1:2:1 ratio.
#' # Meaning: resistance controlled by a single gene with two co-dominant
#' # alleles, is plausible.
#'
#'
#' # = EXAMPLE 2 =
#' # Red crossbills (Loxia curvirostra) have the tip of the upper bill either
#' # right or left of the lower bill, which helps them extract seeds from pine
#' # cones. Some have hypothesized that frequency-dependent selection would
#' # keep the number of right and left-billed birds at a 1:1 ratio. Groth (1992)
#' # observed 1752 right-billed and 1895 left-billed crossbills.
#'
#' x <- c(1752, 1895)
#' x.expected <- vector2ratio(x, ratio = c(1, 1))
#' x.expected
#' # 1823.5 1823.5
#'
#' g.test(x, x.expected)
#' # p = 0.01787343
#'
#' # There is a significant difference from a 1:1 ratio.
#' # Meaning: there are significantly more left-billed birds.
#'
vector2ratio <- function(x, ratio) {
if (!all(is.numeric(x))) {
stop('`x` must be a vector of numeric values.')
}
if (length(ratio) == 1) {
if (ratio %like% '^([0-9]+([.][0-9]+)?[-,:])+[0-9]+([.][0-9]+)?$') {
# support for "1:2:1", "1-2-1", "1,2,1" and even "1.75:2:1.5"
ratio <- ratio %>% base::strsplit("[-,:]") %>% base::unlist() %>% base::as.double()
} else {
stop('Invalid `ratio`: ', ratio, '.')
}
}
if (length(x) != length(ratio)) {
stop('`x` and `ratio` must be of same size.')
}
base::sum(x, na.rm = TRUE) * (ratio / base::sum(ratio, na.rm = TRUE))
}

9
R/globals.R
View File

@ -20,18 +20,16 @@ globalVariables(c('abname',
'atc',
'bactid',
'cnt',
'Count',
'count',
'Cum',
'CumTot',
'cum_count',
'cum_percent',
'date_lab',
'days_diff',
'Fctlvl',
'fctlvl',
'first_isolate_row_index',
'fullname',
'genus',
'gramstain',
'Item',
'item',
'key_ab',
'key_ab_lag',
@ -43,7 +41,6 @@ globalVariables(c('abname',
'n',
'other_pat_or_mo',
'patient_id',
'Percent',
'quantile',
'real_first_isolate',
'species',

57
R/p.symbol.R Normal file
View File

@ -0,0 +1,57 @@
# ==================================================================== #
# TITLE #
# Antimicrobial Resistance (AMR) Analysis #
# #
# AUTHORS #
# Berends MS (m.s.berends@umcg.nl), Luz CF (c.f.luz@umcg.nl) #
# #
# LICENCE #
# This program is free software; you can redistribute it and/or modify #
# it under the terms of the GNU General Public License version 2.0, #
# as published by the Free Software Foundation. #
# #
# This program is distributed in the hope that it will be useful, #
# but WITHOUT ANY WARRANTY; without even the implied warranty of #
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the #
# GNU General Public License for more details. #
# ==================================================================== #
#' Symbol of a p value
#'
#' Return the symbol related to the p value: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
#' @param p p value
#' @param emptychar text to show when \code{p > 0.1}
#' @return Text
#' @export
p.symbol <- function(p, emptychar = " ") {
instelling.oud <- options()$scipen
options(scipen = 999)
s <- ''
s[1:length(p)] <- ''
for (i in 1:length(p)) {
if (is.na(p[i])) {
s[i] <- NA
next
}
if (p[i] > 1) {
s[i] <- NA
next
} else {
p_test <- p[i]
}
if (p_test > 0.1) {
s[i] <- emptychar
} else if (p_test > 0.05) {
s[i] <- '.'
} else if (p_test > 0.01) {
s[i] <- '*'
} else if (p_test > 0.001) {
s[i] <- '**'
} else if (p_test >= 0) {
s[i] <- '***'
}
}
options(scipen = instelling.oud)
s
}

7
R/print.R
View File

@ -74,13 +74,6 @@ print.tbl <- function(x, ...) {
prettyprint_df(x, ...)
}
#' @rdname print
#' @exportMethod print.frequency_tbl
#' @export
print.frequency_tbl <- function(x, ...) {
prettyprint_df(x, ...)
}
#' @rdname print
#' @exportMethod print.data.table
#' @export