问题描述
我想使用 group_walk() 或 group_map() 作为导入批量 .csv 文件的替代方法来迭代处理比较的主列表。
我想输入一个如下所示的数据集:
测试分析 | Var1 | Var2 | 频率 |
---|---|---|---|
检测 1 | 否定 | 否定 | 19 |
检测 1 | 否定 | 位置 | 5 |
检测 1 | 位置 | 否定 | 8 |
检测 1 | 位置 | 位置 | 141 |
Assay2 | 否定 | 否定 | 25 |
Assay2 | 否定 | 位置 | 6 |
Assay2 | 位置 | 否定 | 17 |
Assay2 | 位置 | 位置 | 33 |
Assay3 | 否定 | 否定 | 99 |
Assay3 | 否定 | 位置 | 20 |
Assay3 | 位置 | 否定 | 5 |
Assay3 | 位置 | 位置 | 105 |
我想使用函数epi_analysis 并为每个测试分析(在本例中为Assay1、Assay2 和Assay3)导出一个csv。到目前为止,我有:
#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,round(rval$element$pfp$est,round(rval$element$pfn$est,round(kappa2$coeff.val,round(gwet$coeff.val,round(rkappa$pabak$est,digits = 3))
cis <- c(paste(round(rval$elements$sensitivity$lower,round(rval$elements$sensitivity$upper,sep = ","),paste(round(rval$elements$specificity$lower,round(rval$elements$specificity$upper,paste(round(rval$element$pfp$lower,round(rval$element$pfp$upper,paste(round(rval$element$pfn$lower,round(rval$element$pfn$upper,kappa2$coeff.ci,gwet$coeff.ci,paste(round(rkappa$pabak$lower,round(rkappa$pabak$lower,"))
df <- data.frame(hd,ests,cis)
write.csv(df,file = paste0(the_dir,"/",basename(.x$TestAssay)),na = "999.99",row.names = FALSE)
}
#Use group_map or group_walk to iterate through the different assays in the dataset.
data <- read_csv("data_raw/EpiTest.csv") %>%
group_by(TestAssay)%>%
group_map(~ epi_analysis)
但是我的 Epidata 文件夹中没有 csv。欢迎提出任何建议/更正。
解决方法
您需要在 group_map
中调用您的函数。该函数还需要两个参数,因此也传递 the_dir_ex
。
使用这个功能-
library(tidyverse)
library(epiR)
library(irrCAC)
epi_analysis <- function(.x,the_dir){
dat2 <- .x %>%
select(c(Var1,Var2,Freq)) %>%
pivot_wider(Var1,names_from = Var2,values_from = Freq) %>%
remove_rownames %>%
column_to_rownames( var = "Var1") %>%
as.matrix()
#Run tests
rval <- epi.tests(dat2,conf.level = 0.95)
rkappa<-epi.kappa(dat2)
gwet <- gwet.ac1.table(dat2)
kappa2 <- kappa2.table(dat2)
#Export results
hd <- c('sensitivity','specificity','pfp','pfn','kappa','gwet','pabak')
ests <- c(round(rval$elements$sensitivity$est,digits = 3),round(rval$elements$specificity$est,round(rval$element$pfp$est,round(rval$element$pfn$est,round(kappa2$coeff.val,round(gwet$coeff.val,round(rkappa$pabak$est,digits = 3))
cis <- c(paste(round(rval$elements$sensitivity$lower,round(rval$elements$sensitivity$upper,sep = ","),paste(round(rval$elements$specificity$lower,round(rval$elements$specificity$upper,paste(round(rval$element$pfp$lower,round(rval$element$pfp$upper,paste(round(rval$element$pfn$lower,round(rval$element$pfn$upper,kappa2$coeff.ci,gwet$coeff.ci,paste(round(rkappa$pabak$lower,round(rkappa$pabak$lower,"))
df <- data.frame(hd,ests,cis)
write.csv(df,file = sprintf('%s/%s.csv',the_dir,.x$TestAssay[1]),na = "999.99",row.names = FALSE)
}
并用 -
调用它read_csv("data_raw/EpiTest.csv") %>%
group_by(TestAssay)%>%
group_map(~epi_analysis(.,the_dir_ex),.keep = TRUE)
,
我们可以使用
library(dplyr)
library(readr)
library(purrr)
read_csv("data_raw/EpiTest.csv") %>%
group_split(TestAssay) %>%
map(~ epi_analysis(.x,the_dir_ex))