Working with large csv file in R - r

any help will be appreciated.
I used the following code to break down my large csv file (4gb) and now I am trying to save the 2nd, 3rd... part into a csv. However, I can only access the first chunk of my data.
Is there anything wrong with my code?
How do I save the second chunk of my data into csv?
rgfile <- 'filename.csv'
index <- 0
chunkSize <- 100000
con <- file(description = rgfile, open="r")
dataChunk <- read.table(con, nrows= chunkSize, header=T, fill= TRUE, sep= ",")
actualColumnNames <- names(dataChunk)
repeat {
index <- index + 1
print(paste('Processing rows:', index * chunkSize))
if (nrow(dataChunk) != chunkSize){
print('Processed all files!')
break
}
dataChunk <- read.table(
con, nrows = chunkSize, skip=0, header = FALSE,
fill=TRUE, sep = ",", col.names=actualColumnNames
)
break
}

library(tidyverse)
library(nycflights13)
# make the problelm reproducible
rgfile <- 'flights.csv'
write_csv(flights, rgfile)
# now, get to work
lines <- as.numeric(R.utils::countLines(rgfile))
chunk_size <- 100000
hdr <- read_csv(rgfile, n_max=2)
fnum <- 1
for (i in seq(1, lines, chunk_size)) {
suppressMessages(
read_csv(
rgfile, col_names=colnames(hdr), skip=(i-1), n_max=chunk_size
)
) -> x
if (i>1) colnames(x) <- colnames(hdr)
write_csv(x, sprintf("file%03d.csv", fnum))
fnum <- fnum + 1
}

Related

For-loop in R to create a new file (but gives incorrect/unexpected output)

I'm currently busy with some data and I need to check their validity.
Therefore, I would like to use a for-loop to go through all my data files.
In this for-loop, I would like to calculate some things (like mean, min,max...).
My code below works but produced an incorrectly written csv file. The problem occurs after the calculations (and their values) are done during csv file creation. CSV:
"c.1..1..1004.89081855716..630.174466667434..461.738905906677.." "c.1..1..950.990843858612..479.98560814955..517.955102920532.."
1 1
1 1
1004.89081855716 950.990843858612
630.174466667434 479.98560814955
461.738905906677 517.955102920532
1535.86795806885 1452.30199813843
-13.3948961645365 3.72026950120926
1259.26423788071 1159.17089223862
Approach/What I'm expecting:
So I start from some data files with eye tracking data in it.
As you can see at the beginning of the code, I try to get some values out of this eye tracking data (validity, new file with only validity == 1 data...). Once I created the filtered_data dataframe, I want to calculate some extra values out of it (mean, sd, min/max).
My plan is to create a new csv file (validity_loop.csv) in which I can find all my calculations (validity_left, validity_right,mean_eye_x, mean_eye_y, min_eye_x,max_eye_x,min_eye_y,max_eye_y). All in a row. One row for each data set (file_list[i]).
Can someone help me in how to tackle and solve this issue?
Here is my code:
set <- setwd("/Users/Sarah/Documents")
file_list <- list.files(set, pattern = ".csv", all.files = TRUE)
validity_list <- data_list <- vector("list", "length" = length(file_list))
for(i in seq_along(file_list)){
filename = file_list[i]
#read files
data_frame = read.csv(filename, sep = ",", dec = ".",
header = TRUE,
stringsAsFactors = FALSE)
#what has to be done
#validity
validity_left <- mean(is.numeric(data_frame$left_gaze_point_validity))
validity_right <-mean(is.numeric(data_frame$right_gaze_point_validity))
#Zuiver dataframe (validity ==1)
to_keep = which(data_frame$left_gaze_point_validity == 1 &
data_frame$right_gaze_point_validity==1)
filtered_data = data_frame[to_keep,]
filtered_data$left_eye_x = as.numeric(filtered_data$left_eye_x)
filtered_data$left_eye_y = as.numeric(filtered_data$left_eye_y)
filtered_data$right_eye_x = as.numeric(filtered_data$right_eye_x)
filtered_data$right_eye_y = as.numeric(filtered_data$right_eye_y)
#1 eye-data
filtered_data$eye_x <- (filtered_data$left_eye_x+filtered_data$right_eye_x)/2
filtered_data$eye_y <- (filtered_data$left_eye_y+filtered_data$right_eye_y)/2
#Pixels
filtered_data$eye_x <- (filtered_data$eye_x)*1920
filtered_data$eye_y <- (filtered_data$eye_y)*1080
#SD and Mean + min-max
mean_eye_x<- mean(filtered_data$eye_x)
mean_eye_y <- mean(filtered_data$eye_y)
sd_eye_x <- sd(filtered_data$eye_x)
sd_eye_y <- sd(filtered_data$eye_y)
min_eye_x <- min(filtered_data$eye_x)
min_eye_y <- min(filtered_data$eye_y)
max_eye_x <- max(filtered_data$eye_x)
max_eye_y <- max(filtered_data$eye_y)
#add everything to new file
validity_list[[i]] <- c(validity_left, validity_right,
mean_eye_x, mean_eye_y,
min_eye_x, min_eye_y,
max_eye_x, max_eye_y)
}
#new document
write.table(validity_list,
file = "Master T&O/Thesis /Loop/Validity/validity_loop.csv",
col.names = TRUE, row.names = FALSE)
I managed to get a new data frame in R, which contains the value of my validity_list as a matrix form.
#FOR LOOP poging 2
set <- setwd("/Users/Sarah/Documents/Master T&O/Thesis /Loop")
file_list <- list.files(set, pattern = ".csv", all.files = TRUE)
validity_list <- vector("list", "length" = length(file_list))
for(i in seq_along(file_list)){
filename = file_list[i]
#read files
data_frame = read.csv(filename, sep = ",", dec = ".", header = TRUE, stringsAsFactors = FALSE)
#what has to be done
#validity
validity_left <- mean(is.numeric(data_frame$left_gaze_point_validity))
validity_right <-mean(is.numeric(data_frame$right_gaze_point_validity))
#Zuiver dataframe (validity ==1)
to_keep = which(data_frame$left_gaze_point_validity == 1 & data_frame$right_gaze_point_validity==1)
filtered_data = data_frame[to_keep,]
filtered_data$left_eye_x = as.numeric(filtered_data$left_eye_x)
filtered_data$left_eye_y = as.numeric(filtered_data$left_eye_y)
filtered_data$right_eye_x = as.numeric(filtered_data$right_eye_x)
filtered_data$right_eye_y = as.numeric(filtered_data$right_eye_y)
#1 eye-data
filtered_data$eye_x <- (filtered_data$left_eye_x+filtered_data$right_eye_x)/2
filtered_data$eye_y <- (filtered_data$left_eye_y+filtered_data$right_eye_y)/2
#Pixels
filtered_data$eye_x <- (filtered_data$eye_x)*1920
filtered_data$eye_y <- (filtered_data$eye_y)*1080
#SD and Mean + min-max
mean_eye_x<- mean(filtered_data$eye_x)
mean_eye_y <- mean(filtered_data$eye_y)
sd_eye_x <- sd(filtered_data$eye_x)
sd_eye_y <- sd(filtered_data$eye_y)
min_eye_x <- min(filtered_data$eye_x)
min_eye_y <- min(filtered_data$eye_y)
max_eye_x <- max(filtered_data$eye_x)
max_eye_y <- max(filtered_data$eye_y)
#add everything to new file
validity_list[[i]] <- c(validity_left, validity_right,mean_eye_x, mean_eye_y, min_eye_x,max_eye_x,min_eye_y,max_eye_y)
validity_matrix <- matrix(unlist(validity_list), ncol = 8, byrow = TRUE)
}
#new document
write.table(validity_matrix, file = "/Users/Sarah/Documents/Master T&O/Thesis /Loop/Validity/validity_loop.csv", dec = ".")
The only problem I have now, is the fact that my values for the validity_list items are wrong, but that's another problem and I'm trying to fix it!
If I get it then the following line grabs all your data together:
validity_list[[i]] <- c (validity_left, validity_right,mean_eye_x,
mean_eye_y, min_eye_x,max_eye_x,min_eye_y,max_eye_y).
if it's like in python then I would have:
validity_list = (validity_left, validity_right,mean_eye_x,
mean_eye_y, min_eye_x,max_eye_x,min_eye_y,max_eye_y)
... whereas the '=' tell the interpreter that everything behind it is a tuple '(', data, ')' ...which makes it one single dataset and if I then write it... it would be end up in one column. If you do a pick using a for-loop I would get "validity_left" writing in a separate column. In your case adding this to your below code an option?
for item in validity_list:
function to process item..etc.

Stream processing large csv file in R

I need to make a couple of relatively simple changes to a very large csv file (c.8.5GB). I tried initially using various reader functions: read.csv, readr::read.csv, data.table::fread. However: they all run out of memory.
I'm thinking I need to use a stream processing approach instead; read a chunk, update it, write it, repeat. I found this answer which is on the right lines; however I don't how to terminate the loop (I'm relatively new to R).
So I have 2 questions:
What's the right way to make the while loop work?
Is there a better way (for some definition of 'better')? e.g. is there some way to do this using dplyr & pipes?
Current code as follows:
src_fname <- "testdata/model_input.csv"
tgt_fname <- "testdata/model_output.csv"
#Changes needed in file: rebase identifiers, set another col to constant value
rebase_data <- function(data, offset) {
data$'Unique Member ID' <- data$'Unique Member ID' - offset
data$'Client Name' <- "TestClient2"
return(data)
}
CHUNK_SIZE <- 1000
src_conn = file(src_fname, "r")
data <- read.csv(src_conn, nrows = CHUNK_SIZE, check.names=FALSE)
cols <- colnames(data)
offset <- data$'Unique Member ID'[1] - 1
data <- rebase_data(data, offset)
#1st time through, write the headers
tgt_conn = file(tgt_fname, "w")
write.csv(data,tgt_conn, row.names=FALSE)
#loop over remaining data
end = FALSE
while(end == FALSE) {
data <- read.csv(src_conn, nrows = CHUNK_SIZE, check.names=FALSE, col.names = cols)
data <- rebase_data(data, offset)
#write.csv doesn't support col.names=FALSE; so use write.table which does
write.table(data, tgt_conn, row.names=FALSE, col.names=FALSE, sep=",")
# ??? How to test for EOF and set end = TRUE if so ???
# This doesn't work, presumably because nrow() != CHUNK_SIZE on final loop?
if (nrow(data) < CHUNK_SIZE) {
end <- TRUE
}
}
close(src_conn)
close(tgt_conn)
Thanks for any pointers.
Sorry to poke a 2-year-old thread, but now with readr::read_csv_chunked (auto-loaded along with dplyr when loading tidyverse), we could also do like:
require(tidyverse)
## For non-exploratory code, as #antoine-sac suggested, use:
# require(readr) # for function `read_csv_chunked` and `read_csv`
# require(dplyr) # for the pipe `%>%` thus less parentheses
src_fname = "testdata/model_input.csv"
tgt_fname = "testdata/model_output.csv"
CHUNK_SIZE = 1000
offset = read_csv(src_fname, n_max=1)$comm_code %>% as.numeric() - 1
rebase.chunk = function(df, pos) {
df$comm_code = df$comm_code %>% as.numeric() - offset
df$'Client Name' = "TestClient2"
is.append = ifelse(pos > 1, T, F)
df %>% write_csv(
tgt_fname,
append=is.append
)
}
read_csv_chunked(
src_fname,
callback=SideEffectChunkCallback$new(rebase.chunk),
chunk_size = chunck.size,
progress = T # optional, show progress bar
)
Here the tricky part is to set is.append based on parameter pos, which indicates the start row number of the data frame df within original file. Within readr::write_csv, when append=F the header (columns name) will be written to file, otherwise not.
Try this out:
library("chunked")
read_chunkwise(src_fname, chunk_size=CHUNK_SIZE) %>%
rebase_data(offset) %>%
write_chunkwise(tgt_fname)
You may need to fiddle a bit with the colnames to get exactly what you want.
(Disclaimer: haven't tried the code)
Note that there is no vignette with the package but the standard usage is described on github: https://github.com/edwindj/chunked/
OK I found a solution, as follows:
# src_fname <- "testdata/model_input.csv"
# tgt_fname <- "testdata/model_output.csv"
CHUNK_SIZE <- 20000
#Changes needed in file: rebase identifiers, set another col to constant value
rebase_data <- function(data, offset) {
data$'Unique Member ID' <- data$'Unique Member ID' - offset
data$'Client Name' <- "TestClient2"
return(data)
}
#--------------------------------------------------------
# Get the structure first to speed things up
#--------------------------------------------------------
structure <- read.csv(src_fname, nrows = 2, check.names = FALSE)
cols <- colnames(structure)
offset <- structure$'Unique Member ID'[1] - 1
#Open the input & output files for reading & writing
src_conn = file(src_fname, "r")
tgt_conn = file(tgt_fname, "w")
lines_read <- 0
end <- FALSE
read_header <- TRUE
write_header <- TRUE
while(end == FALSE) {
data <- read.csv(src_conn, nrows = CHUNK_SIZE, check.names=FALSE, col.names = cols, header = read_header)
if (nrow(data) > 0) {
lines_read <- lines_read + nrow(data)
print(paste0("lines read this chunk: ", nrow(data), ", lines read so far: ", lines_read))
data <- rebase_data(data, offset)
#write.csv doesn't support col.names=FALSE; so use write.table which does
write.table(data, tgt_conn, row.names=FALSE, col.names=write_header, sep = ",")
}
if (nrow(data) < CHUNK_SIZE) {
end <- TRUE
}
read_header <- FALSE
write_header <- FALSE
}
close(src_conn)
close(tgt_conn)

Read numeric input as string R

So, i have this input csv of the form,
id,No.,V,S,D
1,0100000109,623,233,331
2,0200000109,515,413,314
3,0600000109,611,266,662
I need to read the No. Column as it is(i.e., as a character). I know i can use something like this for that:
data <- read.csv("input.csv", colClasses = c("MSISDN" = "character"))
I have a code that i'm using to read the csv file in chunks:
chunk_size <- 2
con <- file("input.csv", open = "r")
data_frame <- read.csv(con,nrows = chunk_size,colClasses = c("MSISDN" = "character"),quote="",header = TRUE,)
header <- names(data_frame)
print(header)
print(data_frame)
if(nrow(data_frame) == chunk_size) {
repeat {
data_frame <- read.csv(con,nrows = chunk_size, header = FALSE, quote="")
names(data_frame)<-c(header)
print(header)
print(data_frame)
if(nrow(data_frame) < chunk_size) {
break
}
}
}
close(con)
But, here what the issue i'm facing is that, the first chunk will only read the No. Column as a character, the rest of the chunks will not.
How can i resolve this?
PS: the original input file has about 150+ columns and about 20 Million rows.
You can read the data as string with readLines and split it:
fileName <- "input.csv"
df <- do.call(rbind.data.frame, strsplit(readLines(fileName), ",")[-1]) # skipping headlines
colnames(df) <- c("id","No.","V","S","D") #adding headlines
or the direct approach with read.csv:
fileName <- "input.csv"
col <- c("integer","character","integer","integer","integer")
df <- read.csv(file = fileName,
sep = ",",
colClasses=col,
header = TRUE,
stringsAsFactors = FALSE)
You need to give the column type colClasses in the read.csv() inside the repeat procedure.
You no longer have the header so you need to define an unnamed vector to specify the colClasses.
Let's say the size of colClasses is 150.
myColClasses=rep("numeric",150)
myColClasses[2] <- "character"
repeat {
data_frame <- read.csv(con,nrows = chunk_size, colClasses=myColClasses, header = FALSE, quote="")
...

Index elements of large CSV file when reading line by line

I'm reading a large CSV file (>15 GB) line by line in R. I'm using
con <- file("datafile.csv", open = "r")
while (length(oneLine <- readLines(con, n = 1, warn = FALSE)) > 0) {
# code to be written
}
In the "code to be written" section, I need to be able to refer to individual elements in each row and save them to an array. The file has no headers if that's important.
Thanks!
You could use read.table with argument text to parse oneLine string as if it were a csv file:
# set your arguments: separator, decimal separator etc...
x <- read.table(text=oneLine, sep=",", dec=".", header=F)
The returned x is a data.frame with one row only that you can easily turn into an array.
You could do something like this:
CHUNK_SIZE <- 5000
con <- file('datafile.csv', 'rt')
res <- NULL
while (nrow(chunk <- read.csv(con, nrow = CHUNK_SIZE, header = FALSE, stringsAsFactors = FALSE)) > 0) {
res <- rbind(res, chunk)
if (nrow(chunk) < CHUNK_SIZE) break
}

Why is my loop in r is just running once?

I asked a very similar question before but the answers i got dont seem to apply in this case. The aim of my code is primarily to take a file, manipulate it and the save the manipulated file over the old file. Unfortunately there are a lot of file so I have incorporated a for loop but it is stopping after just one run through the loop. I think my return function is in the right place and my for statement worked in a previous slightly different version of the script.
Here is my code:
AddLatLon<- function(num, condition){
#Set working directiory
# num is the number of files needing extraction e.g (3:5) , c(2,7)
connect <- file("./EOBS DATA/sources.txt", "r")
locdata <- readLines(connect)
close(connect)
info <- locdata[24:length(locdata)] # removes non data before the data begins
Infodata <- read.table(text = info, sep=',',fill=TRUE,colClasses='character',header ==TRUE )
InfoTable <- read.csv("./EOBS DATA/sources.csv")
InfoTable$STAID <- as.numeric(InfoTable$STAID)
for(i in c(num)){
filename <-paste("./EOBS DATA/",condition, "_csv_data/", condition,i, ".csv", sep = "")
#if(i <10){
#filename <- paste("./EOBS DATA/ECA_blend_", condition, "/" ,CONDITION, "_STAID00000", i, ".txt", sep = "")
#}
#if(i >=10 & i < 100){
#filename <- paste("./EOBS DATA/ECA_blend_", condition, "/" ,CONDITION, "_STAID0000", i, ".txt", sep = "")
#}
#if(i>= 100 & i <1000){
#filename <- paste("./EOBS DATA/ECA_blend_", condition, "/" ,CONDITION, "_STAID000", i, ".txt", sep = "")
#}
#if(i>= 1000){
#filename <- paste("./EOBS DATA/ECA_blend_", condition, "/" ,CONDITION, "_STAID00", i, ".txt", sep = "")
#}
if(file.exists(filename) == FALSE) {
next
}
#con <- file(filename, "r")
#data <- readLines(con)
#close(con)
#q <- data[21:length(data)] # removes non data before the data begins
#Impactdata <- read.table(text = q, sep=',',fill=TRUE,colClasses='character',header = TRUE )
x <- read.csv(filename)
point <- match(i, InfoTable$STAID)
Lat <- InfoTable[point,5]
Lon <- InfoTable[point,6]
Lat <- as.character(Lat)
Lon <- as.character(Lon)
x$Lat <- Lat
x$Lon <- Lon
x$X <- NULL
x$DATE<- as.Date(as.character(x$DATE), format='%Y%m%d')
Savename <- paste("./EOBS DATA/",condition, "_csv_data/", condition,i, ".csv", sep = "")
if(condition == "rr"){
condition <- "Precipitation"
}
if(condition == "tn"){
condition <- "Minimum Temperature"
}
if(condition == "tx"){
condition <- "Maximum Temperature"
}
names(x)<- c("Station_ID", "Source_ID", "Date(yyyy-mm-dd)", condition, "Quality_code(0='valid'; 1='suspect')", "Latitude", "Longitude")
write.csv(x, Savename)
}
return(head(x))
}
num is not defined, but from the name I'm pretty sure you want to be looping over 1:num, not c(num). So just replace:
for(i in c(num)){
with
for(i in 1:num)){
or
for(i in seq_len(num)){
Why seq_len? It will do the right thing if num is zero (no looping) or negative (throw an error).

Resources