[R] Can I use group_map to iteratively process a dataframe?
Madison Bell
m@d|@on3be|| @end|ng |rom gm@||@com
Sat Jun 5 15:26:55 CEST 2021
This question had been posted on SO for a week with no response. I reached out to rhelp two days ago. I deleted the original question on SO and reposted an abbreviated version this morning.
Sorry for the cross posting, but I am urgently trying to get some ideas on how approach this problem.
Sent from my iPhone
> On Jun 5, 2021, at 09:07, Rui Barradas <ruipbarradas using sapo.pt> wrote:
>
> Hello,
>
> This is cross-posted from StackOverflow [1]. Cross posting is not well seen on R-help and the SO post is better explained (at least the data seem to be more complete). You should have waited for an answer there.
>
>
> Hope this helps,
>
> Rui Barradas
>
> Às 15:03 de 04/06/21, Madison Bell escreveu:
>> I want to iteratively process a master list of comparisons using
>> group_walk() as an alternative method to import batches of .csv files.
>> I have the code for iteratively importing batch csvs here:
>> #Import list of csv files from directory, formatted as:
>> |rownm | neg | pos |
>> |------|-----|-----|
>> |neg |19 |18 |
>> |pos |5 |141 |
>> ```
>> library(tidyverse) # for cleaning and shaping data
>> library(epiR)
>> library(irrCAC)
>> all_epi_files <- list.files("congtables", pattern = "*.csv",
>> full.names = TRUE)
>> #Make export directory
>> check_create_dir <- function(the_dir) {
>> if (!dir.exists(the_dir)) {
>> dir.create(the_dir, recursive = TRUE) } #Creates a directory if it
>> doesn't already exist
>> }
>> the_dir_ex <- "data_generated/epidata" #Name the new desired directory
>> check_create_dir(the_dir_ex) #Make the directory if it doesn't already exist
>> #Make function for the series of analyses
>> epi_analysis <- function(a_csv, the_dir){
>> #Import data as inserted variables
>> dat2 <- read_csv(a_csv)%>%
>> remove_rownames %>%
>> column_to_rownames(var="rownm") %>%
>> as.matrix()
>> #Run tests
>> rval <- epi.tests(dat2, conf.level = 0.95)
>> rkappa<-epi.kappa(dat2)
>> gwet <- gwet.ac1.table(dat2)
>> kappa2 <- kappa2.table(dat2)
>> #Export results
>> hd <- c('sensitivity', 'specificity', 'pfp', 'pfn', 'kappa', 'gwet', 'pabak')
>> ests <- c(round(rval$elements$sensitivity$est, digits = 3),
>> round(rval$elements$specificity$est, digits = 3),
>> round(rval$element$pfp$est, digits = 3),
>> round(rval$element$pfn$est, digits = 3),
>> round(kappa2$coeff.val, digits = 3),
>> round(gwet$coeff.val, digits = 3),
>> round(rkappa$pabak$est, digits = 3))
>> cis <- c(paste(round(rval$elements$sensitivity$lower, digits = 3),
>> round(rval$elements$sensitivity$upper, digits = 3), sep = ","),
>> paste(round(rval$elements$specificity$lower, digits = 3),
>> round(rval$elements$specificity$upper, digits = 3), sep = ","),
>> paste(round(rval$element$pfp$lower, digits = 3),
>> round(rval$element$pfp$upper, digits = 3), sep = ","),
>> paste(round(rval$element$pfn$lower, digits = 3),
>> round(rval$element$pfn$upper, digits = 3), sep = ","),
>> kappa2$coeff.ci,
>> gwet$coeff.ci,
>> paste(round(rkappa$pabak$lower, digits = 3),
>> round(rkappa$pabak$lower, digits = 3), sep = ","))
>> df <- data.frame(hd, ests, cis)
>> write.csv(df,
>> file = paste0(the_dir, "/", basename(a_csv)),
>> na = "999.99",
>> row.names = FALSE)
>> }
>> #Execute functions
>> lapply(all_epi_files,
>> FUN = epi_analysis,
>> the_dir = the_dir_ex)
>> ```
>> But instead I would like to input a dataset that looks like this:
>> |Test Assay | Var1 | Var2 |Freq|
>> |-----------|------|------|----|
>> |Assay1 |neg |neg |19 |
>> |Assay1 |neg |pos |5 |
>> |Assay1 |pos |neg |8 |
>> |Assay1 |pos |pos |141 |
>> |Assay2 |neg |neg |25 |
>> |Assay2 |neg |pos |6 |
>> |Assay2 |pos |neg |17 |
>> |Assay2 |pos |pos |33 |
>> |Assay3 |neg |neg |99 |
>> |Assay3 |neg |pos |20 |
>> |Assay3 |pos |neg |5 |
>> |Assay3 |pos |pos |105 |
>> I want to use the same function epi_analysis and export a csv for each
>> Test Assay (in this example Assay1, Assay2, and Assay3). So far I
>> have:
>> ```
>> #Make export directory
>> check_create_dir <- function(the_dir) {
>> if (!dir.exists(the_dir)) {
>> dir.create(the_dir, recursive = TRUE) } #Creates a directory if it
>> doesn't already exist
>> }
>> the_dir_ex <- "data_generated/epidata" #Name the new desired directory
>> check_create_dir(the_dir_ex) #Make the directory if it doesn't already exist
>> #Make function for the series of analyses
>> epi_analysis <- function(.x, the_dir){
>> #Clean data
>> dat2 <- .x %>%
>> select(c(Var1, Var2, Freq)) %>%
>> pivot_wider(Var1, names_from = Var2, values_from = Freq) %>%
>> remove_rownames %>%
>> column_to_rownames( var = "Var1") %>%
>> as.matrix()
>> #Run tests
>> rval <- epi.tests(dat2, conf.level = 0.95)
>> rkappa<-epi.kappa(dat2)
>> gwet <- gwet.ac1.table(dat2)
>> kappa2 <- kappa2.table(dat2)
>> #Export results
>> hd <- c('sensitivity', 'specificity', 'pfp', 'pfn', 'kappa', 'gwet', 'pabak')
>> ests <- c(round(rval$elements$sensitivity$est, digits = 3),
>> round(rval$elements$specificity$est, digits = 3),
>> round(rval$element$pfp$est, digits = 3),
>> round(rval$element$pfn$est, digits = 3),
>> round(kappa2$coeff.val, digits = 3),
>> round(gwet$coeff.val, digits = 3),
>> round(rkappa$pabak$est, digits = 3))
>> cis <- c(paste(round(rval$elements$sensitivity$lower, digits = 3),
>> round(rval$elements$sensitivity$upper, digits = 3), sep = ","),
>> paste(round(rval$elements$specificity$lower, digits = 3),
>> round(rval$elements$specificity$upper, digits = 3), sep = ","),
>> paste(round(rval$element$pfp$lower, digits = 3),
>> round(rval$element$pfp$upper, digits = 3), sep = ","),
>> paste(round(rval$element$pfn$lower, digits = 3),
>> round(rval$element$pfn$upper, digits = 3), sep = ","),
>> kappa2$coeff.ci,
>> gwet$coeff.ci,
>> paste(round(rkappa$pabak$lower, digits = 3),
>> round(rkappa$pabak$lower, digits = 3), sep = ","))
>> df <- data.frame(hd, ests, cis)
>> write.csv(df,
>> file = paste0(the_dir, "/", basename(.x$TestAssay)),
>> na = "999.99",
>> row.names = FALSE)
>> }
>> data <- read_csv("data_raw/EpiTest.csv") %>%
>> group_by(TestAssay)%>%
>> group_map(~ epi_analysis)
>> ```
>> But the only output I see is:
>> ```
>> [[1]]
>> function(.x, the_dir){
>> #Clean data
>> dat2 <- .x %>%
>> select(c(Var1, Var2, Freq)) %>%
>> pivot_wider(Var1, names_from = Var2, values_from = Freq) %>%
>> remove_rownames %>%
>> column_to_rownames( var = "Var1") %>%
>> as.matrix()
>> #Run tests
>> rval <- epi.tests(dat2, conf.level = 0.95)
>> rkappa<-epi.kappa(dat2)
>> gwet <- gwet.ac1.table(dat2)
>> kappa2 <- kappa2.table(dat2)
>> #Export results
>> hd <- c('sensitivity', 'specificity', 'pfp', 'pfn', 'kappa', 'gwet', 'pabak')
>> ests <- c(round(rval$elements$sensitivity$est, digits = 3),
>> round(rval$elements$specificity$est, digits = 3),
>> round(rval$element$pfp$est, digits = 3),
>> round(rval$element$pfn$est, digits = 3),
>> round(kappa2$coeff.val, digits = 3),
>> round(gwet$coeff.val, digits = 3),
>> round(rkappa$pabak$est, digits = 3))
>> cis <- c(paste(round(rval$elements$sensitivity$lower, digits = 3),
>> round(rval$elements$sensitivity$upper, digits = 3), sep = ","),
>> paste(round(rval$elements$specificity$lower, digits = 3),
>> round(rval$elements$specificity$upper, digits = 3), sep = ","),
>> paste(round(rval$element$pfp$lower, digits = 3),
>> round(rval$element$pfp$upper, digits = 3), sep = ","),
>> paste(round(rval$element$pfn$lower, digits = 3),
>> round(rval$element$pfn$upper, digits = 3), sep = ","),
>> kappa2$coeff.ci,
>> gwet$coeff.ci,
>> paste(round(rkappa$pabak$lower, digits = 3),
>> round(rkappa$pabak$lower, digits = 3), sep = ","))
>> df <- data.frame(hd, ests, cis)
>> write.csv(df,
>> file = paste0(the_dir, "/", basename(.x$TestAssay)),
>> na = "999.99",
>> row.names = FALSE)
>> }
>> [[2]]
>> function(.x, the_dir){
>> #Clean data
>> dat2 <- .x %>%
>> select(c(Var1, Var2, Freq)) %>%
>> pivot_wider(Var1, names_from = Var2, values_from = Freq) %>%
>> remove_rownames %>%
>> column_to_rownames( var = "Var1") %>%
>> as.matrix()
>> #Run tests
>> rval <- epi.tests(dat2, conf.level = 0.95)
>> rkappa<-epi.kappa(dat2)
>> gwet <- gwet.ac1.table(dat2)
>> kappa2 <- kappa2.table(dat2)
>> #Export results
>> hd <- c('sensitivity', 'specificity', 'pfp', 'pfn', 'kappa', 'gwet', 'pabak')
>> ests <- c(round(rval$elements$sensitivity$est, digits = 3),
>> round(rval$elements$specificity$est, digits = 3),
>> round(rval$element$pfp$est, digits = 3),
>> round(rval$element$pfn$est, digits = 3),
>> round(kappa2$coeff.val, digits = 3),
>> round(gwet$coeff.val, digits = 3),
>> round(rkappa$pabak$est, digits = 3))
>> cis <- c(paste(round(rval$elements$sensitivity$lower, digits = 3),
>> round(rval$elements$sensitivity$upper, digits = 3), sep = ","),
>> paste(round(rval$elements$specificity$lower, digits = 3),
>> round(rval$elements$specificity$upper, digits = 3), sep = ","),
>> paste(round(rval$element$pfp$lower, digits = 3),
>> round(rval$element$pfp$upper, digits = 3), sep = ","),
>> paste(round(rval$element$pfn$lower, digits = 3),
>> round(rval$element$pfn$upper, digits = 3), sep = ","),
>> kappa2$coeff.ci,
>> gwet$coeff.ci,
>> paste(round(rkappa$pabak$lower, digits = 3),
>> round(rkappa$pabak$lower, digits = 3), sep = ","))
>> df <- data.frame(hd, ests, cis)
>> write.csv(df,
>> file = paste0(the_dir, "/", basename(.x$TestAssay)),
>> na = "999.99",
>> row.names = FALSE)
>> }
>> [[3]]
>> function(.x, the_dir){
>> #Clean data
>> dat2 <- .x %>%
>> select(c(Var1, Var2, Freq)) %>%
>> pivot_wider(Var1, names_from = Var2, values_from = Freq) %>%
>> remove_rownames %>%
>> column_to_rownames( var = "Var1") %>%
>> as.matrix()
>> #Run tests
>> rval <- epi.tests(dat2, conf.level = 0.95)
>> rkappa<-epi.kappa(dat2)
>> gwet <- gwet.ac1.table(dat2)
>> kappa2 <- kappa2.table(dat2)
>> #Export results
>> hd <- c('sensitivity', 'specificity', 'pfp', 'pfn', 'kappa', 'gwet', 'pabak')
>> ests <- c(round(rval$elements$sensitivity$est, digits = 3),
>> round(rval$elements$specificity$est, digits = 3),
>> round(rval$element$pfp$est, digits = 3),
>> round(rval$element$pfn$est, digits = 3),
>> round(kappa2$coeff.val, digits = 3),
>> round(gwet$coeff.val, digits = 3),
>> round(rkappa$pabak$est, digits = 3))
>> cis <- c(paste(round(rval$elements$sensitivity$lower, digits = 3),
>> round(rval$elements$sensitivity$upper, digits = 3), sep = ","),
>> paste(round(rval$elements$specificity$lower, digits = 3),
>> round(rval$elements$specificity$upper, digits = 3), sep = ","),
>> paste(round(rval$element$pfp$lower, digits = 3),
>> round(rval$element$pfp$upper, digits = 3), sep = ","),
>> paste(round(rval$element$pfn$lower, digits = 3),
>> round(rval$element$pfn$upper, digits = 3), sep = ","),
>> kappa2$coeff.ci,
>> gwet$coeff.ci,
>> paste(round(rkappa$pabak$lower, digits = 3),
>> round(rkappa$pabak$lower, digits = 3), sep = ","))
>> df <- data.frame(hd, ests, cis)
>> write.csv(df,
>> file = paste0(the_dir, "/", basename(.x$TestAssay)),
>> na = "999.99",
>> row.names = FALSE)
>> }
>> [[4]]
>> function(.x, the_dir){
>> #Clean data
>> dat2 <- .x %>%
>> select(c(Var1, Var2, Freq)) %>%
>> pivot_wider(Var1, names_from = Var2, values_from = Freq) %>%
>> remove_rownames %>%
>> column_to_rownames( var = "Var1") %>%
>> as.matrix()
>> #Run tests
>> rval <- epi.tests(dat2, conf.level = 0.95)
>> rkappa<-epi.kappa(dat2)
>> gwet <- gwet.ac1.table(dat2)
>> kappa2 <- kappa2.table(dat2)
>> #Export results
>> hd <- c('sensitivity', 'specificity', 'pfp', 'pfn', 'kappa', 'gwet', 'pabak')
>> ests <- c(round(rval$elements$sensitivity$est, digits = 3),
>> round(rval$elements$specificity$est, digits = 3),
>> round(rval$element$pfp$est, digits = 3),
>> round(rval$element$pfn$est, digits = 3),
>> round(kappa2$coeff.val, digits = 3),
>> round(gwet$coeff.val, digits = 3),
>> round(rkappa$pabak$est, digits = 3))
>> cis <- c(paste(round(rval$elements$sensitivity$lower, digits = 3),
>> round(rval$elements$sensitivity$upper, digits = 3), sep = ","),
>> paste(round(rval$elements$specificity$lower, digits = 3),
>> round(rval$elements$specificity$upper, digits = 3), sep = ","),
>> paste(round(rval$element$pfp$lower, digits = 3),
>> round(rval$element$pfp$upper, digits = 3), sep = ","),
>> paste(round(rval$element$pfn$lower, digits = 3),
>> round(rval$element$pfn$upper, digits = 3), sep = ","),
>> kappa2$coeff.ci,
>> gwet$coeff.ci,
>> paste(round(rkappa$pabak$lower, digits = 3),
>> round(rkappa$pabak$lower, digits = 3), sep = ","))
>> df <- data.frame(hd, ests, cis)
>> write.csv(df,
>> file = paste0(the_dir, "/", basename(.x$TestAssay)),
>> na = "999.99",
>> row.names = FALSE)
>> }
>> ```
>> and there are no csvs in my epidata folder. Any
>> suggestions/corrections welcomed. I haven't used group_map() before,
>> but I am keen to use it.
>> ______________________________________________
>> R-help using r-project.org mailing list -- To UNSUBSCRIBE and more, see
>> https://stat.ethz.ch/mailman/listinfo/r-help
>> PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
>> and provide commented, minimal, self-contained, reproducible code.
More information about the R-help
mailing list