Saving multiple variables inside a loop R - r

I'm using this code to do the same operation over a series of data frames. Everything seems to works ok, until the moment I try to save each data frame with a different variable in two .Rda files.
The problem is that I end up with the two .Rda files with the variables names of the data frame correctly but the content of these variables is exactly the same. It seems that is only working with the last data frame of variables. I think it's related with the loop for, but I don't know how to solve this.
#Previous steps, loading files...
setwd("path_to_files")
list.files()
files <- list.files(pattern = "toptable")
envar <- new.env()
#Load all files
for (i in files){load(i, envir = envar)}
varName <- ls(envar)
rm(i)
attach(envar)
variables <- as.list(envar)
#From now on the function
setwd("/path_to_save")
filtering_data <- function(x){
#In here I'm just filtering data frames by certain values of it's columns (P.Value column and t column)
x <- as.data.frame(x)
pval <- which(x$P.Value < 0.05)
pval <- x[pval,]
up.pval <- which(pval$t > 0)
down.pval <- which(pval$t < 0)
up.pval <- pval[up.pval,]
down.pval <- pval[down.pval,]
#Modify names to use them as variable names when saving
up_varNames <- paste0(varName, ".", "up")
down_varNames <- paste0(varName, ".", "down")
for (i in seq_along(up_varNames)){
assign(up_varNames[i], up.pval)
assign(down_varNames[i], down.pval)
}
save(list = up_varNames, file = "up.Rda" )
save(list = down_varNames, file = "down.Rda" )
}
#function
lapply(variables, filtering_data)
detach(envar)

Related

Trouble using mutate within a for loop

I'm trying to write a function called complete that takes a file directory (which has csv files titled 1-332) and the title of the file as a number to print out the number of rows without NA in the sulfate or nitrate columns. I am trying to use mutate to add a column titled nobs which returns 1 if neither column is na and then takes the sum of nobs for my answer, but I get an error message that the object nob is not found. How can I fix this? The specific file directory in question is downloaded within this block of code.
library(tidyverse)
if(!file.exists("rprog-data-specdata.zip")) {
temp <- tempfile()
download.file("https://d396qusza40orc.cloudfront.net/rprog%2Fdata%2Fspecdata.zip",temp)
unzip(temp)
unlink(temp)
}
complete <- function(directory, id = 1:332){
#create a list of files
files_full <- list.files(directory, full.names = TRUE)
#create an empty data frame
dat <- data.frame()
for(i in id){
dat <- rbind(dat, read.csv(files_full[i]))
}
mutate(dat, nob = ifelse(!is.na(dat$sulfate) & !is.na(dat$nitrate), 1, 0))
x <- summarise(dat, sum = sum(nob))
return(x)
}
When one runs the following code nobs should be 117, but I get an error message instead
complete("specdata", 1)
Error: object 'nob' not found"
I think the function below should get what you need. Rather than a loop, I prefer map (or apply) in this setting. It's difficult to say where your code went wrong without the error message or an example I can run on my machine, however.
Happy Coding,
Daniel
library(tidyverse)
complete <- function(directory, id = 1:332){
#create a list of files
files_full <- list.files(directory, full.names = TRUE)
# cycle over each file to get the number of nonmissing rows
purrr::map_int(
files_full,
~ read.csv(.x) %>% # read in datafile
dplyr::select(sulfate, nitrate) %>% # select two columns of interest
tidyr::drop_na %>% # drop missing observations
nrow() # get the number of rows with no missing data
) %>%
sum() # sum the total number of rows not missing among all files
}
As mentioned, avoid building objects in a loop. Instead, consider building a list of data frames from each csv then call rbind once. In fact, even consider base R (i.e., tinyverse) for all your needs:
complete <- function(directory, id = 1:332){
# create a list of files
files_full <- list.files(directory, full.names = TRUE)
# create a list of data frames
df_list <- lapply(files_full[id], read.csv)
# build a single data frame with nob column
dat <- transform(do.call(rbind, df_list),
nob = ifelse(!is.na(sulfate) & !is.na(nitrate), 1, 0)
)
return(sum(dat$nob))
}

Select CSV files and read in pairs

I am comparing two pairs of csv files each at a time. The files I have each end with a number like cars_file2.csv, Lorries_file3.csv, computers_file4.csv, phones_file5.csv. I have like 70 files per folder and the way I am comparing is, I compare cars_file2.csv and Lorries_file3.csv then Lorries_file3.csv and
computers_file4.csv, and the pattern is 2,3,3,4,4,5 like that. Is there a smart way I can handle this instead of manually coming back and change file like the way I am reading here or I can use the last number on each csv to read them smartly. NOTE the files have same suffixes _file:
library(daff)
setwd("path")
# Load csvs to compare into data frames
x_original <- read.csv("cars_file2.csv", strip.white=TRUE, stringsAsFactors = FALSE)
x_changed <- read.csv("Lorries_file3.csv", strip.white=TRUE, stringsAsFactors = FALSE)
render(diff_data(x_original,x_changed ,ignore_whitespace=TRUE,count_like_a_spreadsheet = FALSE))
My intention is to compare each two pairs of csv and recorded, Field additions, deletions and modified
You may want to load all files at once and do your comparison with a full list of files.
This may help:
# your path
path <- "insert your path"
# get folders in this path
dir_data <- as.list(list.dirs(path))
# get all filenames
dir_data <- lapply(dir_data,function(x){
# list of folders
files <- list.files(x)
files <- paste(x,files,sep="/")
# only .csv files
files <- files[substring(files,nchar(files)-3,nchar(files)) %in% ".csv"]
# remove possible errors
files <- files[!is.na(files)]
# save if there are files
if(length(files) >= 1){
return(files)
}
})
# delete NULL-values
dir_data <- compact(dir_data)
# make it a named vector
dir_data <- unique(unlist(dir_data))
names(dir_data) <- sub(pattern = "(.*)\\..*$", replacement = "\\1", basename(dir_data))
names(dir_data) <- as.numeric(substring(names(dir_data),nchar(names(dir_data)),nchar(names(dir_data))))
# remove possible NULL-values
dir_data <- dir_data[!is.na(names(dir_data))]
# make it a list again
dir_data <- as.list(dir_data)
# load data
data_upload <- lapply(dir_data,function(x){
if(file.exists(x)){
data <- read.csv(x,header=T,sep=";")
}else{
data <- "file not found"
}
return(data)
})
# setup for comparison
diffs <- lapply(as.character(sort(as.numeric(names(data_upload)))),function(x){
# check if the second dataset exists
if(as.character(as.numeric(x)+1) %in% names(data_upload)){
# first dataset
print(data_upload[[x]])
# second dataset
print(data_upload[[as.character(as.numeric(x)+1)]])
# do your operations here
comparison <- render(diff_data(data_upload[[x]],
data_upload[[as.character(as.numeric(x)+1)]],
ignore_whitespace=T,count_like_a_spreadsheet = F))
numbers <- c(x, as.numeric(x)+1)
# save both the comparison data and the numbers of the datasets
return(list(comparison,numbers))
}
})
# you can find the differences here
diffs
This script loads all csv-files in a folder and its sub-folders and puts them into a list by their numbers. In case there are no doubles, this will work. If you have doubles, you will have to adjust the part where the vector is named so that you can index the full names of the files afterwards.
A simple for- loop using paste will read-in the pairs:
for (i in 1:70) { # assuming the last pair is cars_file70.csv and Lorries_file71.csv
x_original <- read.csv(paste0("cars_file",i,".csv"), strip.white=TRUE, stringsAsFactors = FALSE)
x_changed <- read.csv(paste0("Lorries_file3",i+1,".csv"), strip.white=TRUE, stringsAsFactors = FALSE)
render(diff_data(x_original,x_changed ,ignore_whitespace=TRUE,count_like_a_spreadsheet = FALSE))
}
For simplicity I used 2 .csv files.
csv_1
1,2,4
csv_2
1,8,10
Load all the .csv files from folder,
files <- dir("Your folder path", pattern = '\\.csv', full.names = TRUE)
tables <- lapply(files, read.csv)
#create empty list to store comparison output
diff <- c()
Loop through all loaded files and compare,
for (pos in 1:length(csv)) {
if (pos != length(csv)) { #ignore last one
#save comparison output
diff[[pos]] <- diff_data(as.data.frame(csv[pos]), as.data.frame(csv[pos + 1]), ignore_whitespace=TRUE,count_like_a_spreadsheet = FALSE)
}
}
Compared output by diff
[[1]]
Daff Comparison: ‘as.data.frame(tables[pos])’ vs. ‘as.data.frame(tables[pos + 1])’
+++ +++ --- ---
## X1 X8 X10 X2 X4

use name of dataframe on a list of dataframes

I try to solve a problem from a question I have previously posted looping inside list in r
Is there a way to get the name of a dataframe that is on a list of dataframes?
I have listed a serie of dataframes and to each dataframe I want to apply myfunction. But I do not know how to get the name of each dataframe in order to use it on nameofprocesseddf of myfunction.
Here is the way I get the list of my dataframes and the code I got until now. Any suggestion how I can make this work?
library(missForest)
library(dplyr)
myfunction <- function (originaldf, proceseddf, nonproceseddf, nameofprocesseddf=character){
NRMSE <- nrmse(proceseddf, nonproceseddf, originaldf)
comment(nameofprocesseddf) <- nameofprocesseddf
results <- as.data.frame(list(comment(nameofprocesseddf), NRMSE))
names(results) <- c("Dataset", "NRMSE")
return(results)
}
a <- data.frame(value = rnorm(100), cat = c(rep(1,50), rep(2,50)))
da1 <- data.frame(value = rnorm(100,4), cat2 = c(rep(2,50), rep(3,50)))
dataframes <- dir(pattern = ".txt")
list_dataframes <- llply(dataframes, read.table, header = T, dec=".", sep=",")
n <- length(dataframes)
# Here is where I do not know how to get the name of the `i` dataframe
for (i in 1:n){
modified_list <- llply(list_dataframes, myfunction, originaldf = a, nonproceseddf = da1, proceseddf = list_dataframes[i], nameof processeddf= names(list_dataframes[i]))
write.table(file = sprintf("myfile/%s_NRMSE20%02d.txt", dataframes[i]), modified_list[[i]], row.names = F, sep=",")
}
as a matter of fact, the name of a data frame is not an attribute of the data frame. It's just an expression used to call the object. Hence the name of the data frame is indeed 'list_dataframes[i]'.
Since I assume you want to name your data frame as the text file is named without the extension, I propose you use something like (it require the library stringr) :
nameofprocesseddf = substr(dataframes[i],start = 1,stop = str_length(dataframes[i])-4)

Mean values from multiple csv to data frame

After having searched for help in different threads on this topic, I still have not become wiser. Therefore: Here comes another question on looping through multiple data files...
OK. I have multiple CSV files in one folder containing 5 columns of data. The filenames are as follows:
Moist yyyymmdd hh_mm_ss.csv
I would like to create a script that reads processes the CSV-files one by one doing the following steps:
1) load file
2) check number of rows and exclude file if less than 3 registrations
3) calculate mean value of all measurements (=rows) for column 2
4) calculate mean value of all measurements (=rows) for column 4
5) output the filename timestamp, mean column 2 and mean column 4 to a data frame,
I have written the following function
moist.each.mean <- function() {
library("tcltk")
directory <- tk_choose.dir("","Choose folder for Humidity data files")
setwd(directory)
filelist <- list.files(path = directory)
filetitles <- regmatches(filelist, regexpr("[0-9].*[0-9]", filelist))
mdf <- data.frame(timestamp=character(), humidity=numeric(), temp=numeric())
for(i in 1:length(filelist)){
file.in[[i]] <- read.csv(filelist[i], header=F)
if (nrow(file.in[[i]]<3)){
print("discard")
} else {
newrow <- c(filetitles[[i]], round(mean(file.in[[i]]$V2),1), round(mean(file.in[[i]]$V4),1))
mdf <- rbind(mdf, newrow)
}
}
names(mdf) <- c("timestamp", "humidity", "temp")
}
but i keep getting an error:
Error in `[[<-.data.frame`(`*tmp*`, i, value = list(V1 = c(10519949L, :
replacement has 18 rows, data has 17
Any ideas?
Thx, kruemelprinz
I'd also suggest to use (l)apply... Here's my take:
getMeans <- function(fpath,runfct,
target_cols = c(2),
sep=",",
dec=".",
header = T,
min_obs_threshold = 3){
f <- list.files(fpath)
fcsv <- f[grepl("\.csv",f)]
fcsv <- paste0(fpath,fcsv)
csv_list <- lapply(fcsv,read.table,sep = sep,
dec = dec, header = header)
csv_rows <- sapply(csv_list,nrow)
rel_csv_list <- csv_list[!(csv_rows < min_obs_threshold)]
lapply(rel_csv_list,function(x) colMeans(x[,target_cols]))
}
Also with that kind of error message, the debugger might be very helpful.
Just run debug(moist.each.mean) and execute the function stepwise.
Here's a slightly different approach. Use lapply to read each csv file, exclude it if necessary, otherwise create a summary. This gives you a list where each element is a data frame summary. Then use rbind to create the final summary data frame.
Without a sample of your data, I can't be sure the code below exactly matches your problem, but hopefully it will be enough to get you where you want to go.
# Get vector of filenames to read
filelist=list.files(path=directory, pattern="csv")
# Read all the csv files into a list and create summaries
df.list = lapply(filelist, function(f) {
file.in = read.csv(f, header=TRUE, stringsAsFactors=FALSE)
# Set to empty data frame if file has less than 3 rows of data
if (nrow(file.in) < 3) {
print(paste("Discard", f))
# Otherwise, capture file timestamp and summarise data frame
} else {
data.frame(timestamp=substr(f, 7, 22),
humidity=round(mean(file.in$V2),1),
temp=round(mean(file.in$V4),1))
}
})
# Bind list into final summary data frame (excluding the list elements
# that don't contain a data frame because they didn't have enough rows
# to be included in the summary)
result = do.call(rbind, df.list[sapply(df.list, is.data.frame)])
One issue with your original code is that you create a vector of summary results rather than a data frame of results:
c(filetitles[[i]], round(mean(file.in[[i]]$V2),1), round(mean(file.in[[i]]$V4),1)) is a vector with three elements. What you actually want is a data frame with three columns:
data.frame(timestamp=filetitles[[i]],
humidity=round(mean(file.in[[i]]$V2),1),
temp=round(mean(file.in[[i]]$V4),1))
Thanks for the suggestions using lapply. This is definitely of value as it saves a whole lot of code as well! Meanwhile, I managed to fix my original code as well:
library("tcltk")
# directory: path to csv files
directory <-
tk_choose.dir("","Choose folder for Humidity data files")
setwd(directory)
filelist <- list.files(path = directory)
filetitles <-
regmatches(filelist, regexpr("[0-9].*[0-9]", filelist))
mdf <- data.frame()
for (i in 1:length(filelist)) {
file.in <- read.csv(filelist[i], header = F, skipNul = T)
if (nrow(file.in) < 3) {
print("discard")
} else {
newrow <-
matrix(
c(filetitles[[i]], round(mean(file.in$V2, na.rm=T),1), round(mean(file.in$V4, na.rm=T),1)), nrow = 1, ncol =
3, byrow = T
)
mdf <- rbind(mdf, newrow)
}
}
names(mdf) <- c("timestamp", "humidity", "temp")
Only I did not get it to work as a function because then I would only have one row in mdf containing the last file data. Somehow it did not add rows but overwrite row 1 with each iteration. But using it without a function wrapper worked fine...

applying same function on multiple files in R

I am new to R program and currently working on a set of financial data. Now I got around 10 csv files under my working directory and I want to analyze one of them and apply the same command to the rest of csv files.
Here are all the names of these files: ("US%10y.csv", "UK%10y.csv", "GER%10y.csv","JAP%10y.csv", "CHI%10y.csv", "SWI%10y.csv","SOA%10y.csv", "BRA%10y.csv", "CAN%10y.csv", "AUS%10y.csv")
For example, because the Date column in CSV files are Factor so I need to change them to Date format:
CAN <- read.csv("CAN%10y.csv", header = T, sep = ",")
CAN$Date <- as.character(CAN$Date)
CAN$Date <- as.Date(CAN$Date, format ="%m/%d/%y")
CAN_merge <- merge(all.dates.frame, CAN, all = T)
CAN_merge$Bid.Yield.To.Maturity <- NULL
all.dates.frame is a data frame of 731 consecutive days. I want to merge them so that each file will have the same number of rows which later enables me to combine 10 files together to get a 731 X 11 master data frame.
Surely I can copy and paste this code and change the file name, but is there any simple approach to use apply or for loop to do that ???
Thank you very much for your help.
This should do the trick. Leave a comment if a certain part doesn't work. Wrote this blind without testing.
Get a list of files in your current directory ending in name .csv
L = list.files(".", ".csv")
Loop through each of the name and reads in each file, perform the actions you want to perform, return the data.frame DF_Merge and store them in a list.
O = lapply(L, function(x) {
DF <- read.csv(x, header = T, sep = ",")
DF$Date <- as.character(CAN$Date)
DF$Date <- as.Date(CAN$Date, format ="%m/%d/%y")
DF_Merge <- merge(all.dates.frame, CAN, all = T)
DF_Merge$Bid.Yield.To.Maturity <- NULL
return(DF_Merge)})
Bind all the DF_Merge data.frames into one big data.frame
do.call(rbind, O)
I'm guessing you need some kind of indicator, so this may be useful. Create a indicator column based on the first 3 characters of your file name rep(substring(L, 1, 3), each = 731)
A dplyr solution (though untested since no reproducible example given):
library(dplyr)
file_list <- c("US%10y.csv", "UK%10y.csv", "GER%10y.csv","JAP%10y.csv", "CHI%10y.csv", "SWI%10y.csv","SOA%10y.csv", "BRA%10y.csv", "CAN%10y.csv", "AUS%10y.csv")
can_l <- lapply(
file_list
, read.csv
)
can_l <- lapply(
can_l
, function(df) {
df %>% mutate(Date = as.Date(as.character(Date), format ="%m/%d/%y"))
}
)
# Rows do need to match when column-binding
can_merge <- left_join(
all.dates.frame
, bind_cols(can_l)
)
can_merge <- can_merge %>%
select(-Bid.Yield.To.Maturity)
One possible solution would be to read all the files into R in the form of a list, and then use lapply to to apply a function to all data files. For example:
# Create vector of file names in working direcotry
files <- list.files()
files <- files[grep("csv", files)]
#create empty list
lst <- vector("list", length(files))
#Read files in to list
for(i in 1:length(files)) {
lst[[i]] <- read.csv(files[i])
}
#Apply a function to the list
l <- lapply(lst, function(x) {
x$Date <- as.Date(as.character(x$Date), format = "%m/%d/%y")
return(x)
})
Hope it's helpful.

Resources