Read multiple xlsx files with multiple sheets into one R data frame

Question

I have been reading up on how to read and combine multiple xlsx files into one R data frame and have come across some very good suggestions like, How to read multiple xlsx f

Answer 1

openxlsx solution:

filename <-"myFilePath"

sheets <- openxlsx::getSheetNames(filename)
SheetList <- lapply(sheets,openxlsx::read.xlsx,xlsxFile=filename)
names(SheetList) <- sheets

Answer 2

Here's a tidyverse and readxl driven option that returns a data frame with columns for file and sheet names for each file.

In this example, not every file has the same sheets or columns; test2.xlsx has only one sheet and test3.xlsx sheet1 does not have col3.

library(tidyverse)
library(readxl)

dir_path <- "~/test_dir/"         # target directory path where the xlsx files are located. 
re_file <- "^test[0-9]\\.xlsx"    # regex pattern to match the file name format, in this case 'test1.xlsx', 'test2.xlsx' etc, but could simply be 'xlsx'.

read_sheets <- function(dir_path, file){
  xlsx_file <- paste0(dir_path, file)
  xlsx_file %>%
    excel_sheets() %>%
    set_names() %>%
    map_df(read_excel, path = xlsx_file, .id = 'sheet_name') %>% 
    mutate(file_name = file) %>% 
    select(file_name, sheet_name, everything())
}

df <- list.files(dir_path, re_file) %>% 
  map_df(~ read_sheets(dir_path, .))

# A tibble: 15 x 5
   file_name  sheet_name  col1  col2  col3
   <chr>      <chr>      <dbl> <dbl> <dbl>
 1 test1.xlsx Sheet1         1     2     4
 2 test1.xlsx Sheet1         3     2     3
 3 test1.xlsx Sheet1         2     4     4
 4 test1.xlsx Sheet2         3     3     1
 5 test1.xlsx Sheet2         2     2     2
 6 test1.xlsx Sheet2         4     3     4
 7 test2.xlsx Sheet1         1     3     5
 8 test2.xlsx Sheet1         4     4     3
 9 test2.xlsx Sheet1         1     2     2
10 test3.xlsx Sheet1         3     9    NA
11 test3.xlsx Sheet1         4     7    NA
12 test3.xlsx Sheet1         5     3    NA
13 test3.xlsx Sheet2         1     3     4
14 test3.xlsx Sheet2         2     5     9
15 test3.xlsx Sheet2         4     3     1

Answer 3

One more solution from this "rio" package :

library("rio")

# import and rbind all worksheets
DT <- import_list(SINGLE_XLSX_PATH, rbind = TRUE)

source : rdrr.io

Answer 4

I would use a nested loop like this to go through each sheet of each file. It might not be the fastest solution but it is the simplest.

require(xlsx)    
file.list <- list.files(recursive=T,pattern='*.xlsx')  #get files list from folder

for (i in 1:length(files.list)){                                           
  wb <- loadWorkbook(files.list[i])           #select a file & load workbook
  sheet <- getSheets(wb)                      #get sheet list

  for (j in 1:length(sheet)){ 
    tmp<-read.xlsx(files.list[i], sheetIndex=j, colIndex= c(1:6,8:10,12:17,19),
                   sheetName=NULL, startRow=4, endRow=NULL,
                   as.data.frame=TRUE, header=F)   
    if (i==1&j==1) dataset<-tmp else dataset<-rbind(dataset,tmp)   #happend to previous

  }
}

You can clean NA values after the loading phase.