Download and read shapefile function in R - r

I would like to expand on this function. As of now, the function downloads and unzips the shape file from the web. I would like to implement 'rgdal' to read the file into R.
library(rgdal)
dlshape=function(location) {
temp=tempfile()
download.file(location, temp)
unzip(temp)
}
I found the following code on SO, but I was unsuccessful in adapting it. It appears that the function still looks at the first file unzipped rather than grep for a file ending with the .shp extension.
read.csv.zip <- function(zipfile, ...) {
# Create a name for the dir where we'll unzip
zipdir <- tempfile()
# Create the dir using that name
dir.create(zipdir)
# Unzip the file into the dir
unzip(zipfile, exdir=zipdir)
# Get a list of csv files in the dir
files <- list.files(zipdir)
files <- files[grep("\\.csv$", files)]
# Create a list of the imported csv files
csv.data <- sapply(files, function(f) {
fp <- file.path(zipdir, f)
return(read.csv(fp, ...))
})
return(csv.data)}
dlshape=function(shploc, shpfile) {
temp=tempfile()
download.file(shploc, temp)
unzip(temp, exdir = temp)
files<-list.files(temp)
files <- files[grep("\\.shp$", files)]
shp.data <- sapply(files, function(f) {
fp <- file.path(zipdir, f)
return(ReadOGR(fp, ...))
})
return(shp.data)}
Could someone please help me in figuring this out. I would gladly appreciate it.
EDIT: Included my adaptation for clarification on the "adapting" part.

Try this.
dlshape=function(shploc, shpfile) {
temp=tempfile()
download.file(shploc, temp)
unzip(temp)
shp.data <- sapply(".", function(f) {
fp <- file.path(temp, f)
return(readOGR(".",shpfile))
})
}
x = dlshape(shploc="http://www.location.com/file_name.zip", "file_name")

Related

How to write out multiple files to the environment after apply a function?

I would like to transform 96 .txt files to matrix in R with data.matirx
Here is part of input data in one files
Domain Phylum Class Order
OTU10001 Fungi Ascomycota Dothideomycetes Capnodiales
OTU10004 Fungi Ascomycota Dothideomycetes Pleosporales
And the code for single files:
BC76_OTU <- data.matrix(BC76.frequencytable)
I am trying to process all the files with data.matirx and write out each file to the environment with the following code:
Feature_to_matrix <- function(x) {
x <- as.matrix (files)
return(x)
}
files <- list.files(path="path to directory", pattern="*.txt", full.names=TRUE, recursive=FALSE)
lapply(files, function(Feature_to_matrix) {
t <- read.table(Feature_to_matrix, header=TRUE, row.names=1, sep="")
out <- t
})
But this code doesn't generate output files to the R environment.
Any suggestions?
Thanks!
I also try to write a loop for it
temp = list.files(pattern="*.txt"
for (i in 1:length(temp)) {
sample[i] <- read.csv(temp[i], header = TRUE,row.names=1,sep = "") write.matrix(sample[i]) }
but get an error as follow
Error in sample[i] <- read.csv(temp[i], header = TRUE, row.names = 1, : object of type 'closure' is not subsettable
could anyone give me some suggestion to modify the code?

Dynamic output file name in R

I am so close to getting my code to work, but cannot seem to figure out how to get a dynamic file name. Here is what Ivve got:
require(ncdf)
require(raster)
require(rgdal)
## For multiple files, use a for loop
## Input directory
dir.nc <- 'inputdirectoy'
files.nc <- list.files(dir.nc, full.names = T, recursive = T)
## Output directory
dir.output <- 'outputdirectory'
## For simplicity, I use "i" as the file name, but would like to have a dynamic one
for (i in 1:length(files.nc)) {
r.nc <- raster(files.nc[i], varname = "precipitation")
writeRaster(r.nc, paste(dir.output, i, '.tiff', sep = ''), format = 'GTiff', prj = T, overwrite = T)
}
## END
I appreciate any help. So close!!
You can do this in different ways, but I think it is generally easiest to first create all the output filenames (and check if they are correct) and then use these in the loop.
So something like this:
library(raster)
infiles <- list.files('inputpath', full.names=TRUE)
ff <- extension(basename(infiles), '.tif')
outpath <- 'outputpath'
outfiles <- file.path(outpath, ff)
To assure that you are writing to an existing folder, you can create it first.
dir.create(outpath, showWarnings=FALSE, recursive=TRUE)
And then loop over the files
for (i in 1:length(infiles)) {
r <- raster(infiles[i])
writeRaster(r, paste(outfiles[i], overwrite = TRUE)
}
You might also use something along these lines
outfiles <- gsub('in', 'out', infiles)
Here is the code that finally worked:
# Imports
library(raster)
#Set source file
infiles <- list.files('infilepath', full.names=TRUE)
#create dynamic file names and choose outfiles to view list
ff <- extension(basename(infiles), '.tif')
outpath <- 'outfilepath'
outfiles <- file.path(outpath, ff)
#run da loop
for (i in 1:length(infiles)) {
r <- raster(infiles[i])
writeRaster(r, paste(outfiles[i]), format ='GTiff', overwrite = T)
}
## END

Issue with looping the nc open function

I am trying to loop the
ncin_old<-nc_open("filename", write=TRUE, readunlim=TRUE, verbose=FALSE,
auto_GMT=TRUE, suppress_dimvals=FALSE )
function like this
library(ncdf.tools)
library(ncdf4)
library(ncdf4.helpers)
library(RNetCDF)
library(abind)
setwd("D:/Rwork/Project") # set working folder
# This is the directory where the file for analysing are
dir("D:/Rwork/Project/MASTER_FILES")-> xlab
filelist <- paste("MASTER_FILES/", dir("MASTER_FILES"), sep="")
N <- length(filelist) # Loop over the individual files
for(j in 1:N) {
ncin_old <- nc_open("filelist[j]", write=TRUE, readunlim=TRUE, verbose=FALSE,
auto_GMT=TRUE, suppress_dimvals=FALSE )
}
But I get this error
Error in nc_open("filelist[j]", write = TRUE, readunlim = TRUE,
verbose = FALSE, : Error in nc_open trying to open file
filelist[j]
If I drop everything after filelist[j] the lat file in the loop opens
but the nc_open(x, write) does not seem to like being looped.
I have fixed some issues of your code as below. I think now it is correct.
library(ncdf4)
# set the folder with the files
setwd("D:/Rwork/Project/MASTER_FILES")
# you need the files path, not the directory path
# list only the files with the .nc extension
filelist <- list.files(pattern = "\\.nc$")
# Loop over the individual files
# The filelist cannot be between quotation marks as in your code
N <- length(filelist)
for(j in 1:N) {
ncin_old <- nc_open(filelist[j], write=TRUE, readunlim=TRUE, verbose=FALSE,
auto_GMT=TRUE, suppress_dimvals=FALSE)
}
I've used lapply:
library(ncdf4)
# set the folder that contains all the files
setwd("C:/...")
# create a list with the files with the .nc extension
filelist <- list.files(pattern = "*.nc")
filelist # It contains all the files .nc
# To open all files: Loop over the individual files
for (i in 1:length(filelist)) {
all_nc_files <- lapply(filelist, nc_open)
}
Running that, I obtain "all_nc_files", which contains all .nc files opened and now I can work with them.
Hope it works!

How to append multiple files in R

I'm trying to read a list of files and append them into a new file with all the records. I do not intend to change anything in the original files. I've tried couple of methods.
Method 1: This methods creates a new file but at each iteration the previous file gets added again. Because I'm binding the data frame recursively.
files <- list.files(pattern = "\\.csv$")
#temparary data frame to load the contents on the current file
temp_df <- data.frame(ModelName = character(), Object = character(),stringsAsFactors = F)
#reading each file within the range and append them to create one file
for (i in 1:length(files)){
#read the file
currentFile = read.csv(files[i])
#Append the current file
temp_df = rbind(temp_df, currentFile)
}
#writing the appended file
write.csv(temp_df,"Models_appended.csv",row.names = F,quote = F)
Method 2: I got this method from Rbloggers . This methods won't write to a new file but keeps on modifying the original file.
multmerge = function(){
filenames= list.files(pattern = "\\.csv$")
datalist = lapply(filenames, function(x){read.csv(file=x,header=T)})
Reduce(function(x,y) {merge(x,y)}, temp_df)
}
Can someone advice me on how to achieve my goal?
it could look like this:
files <- list.files(pattern = "\\.csv$")
DF <- read.csv(files[1])
#reading each file within the range and append them to create one file
for (f in files[-1]){
df <- read.csv(f) # read the file
DF <- rbind(DF, df) # append the current file
}
#writing the appended file
write.csv(DF, "Models_appended.csv", row.names=FALSE, quote=FALSE)
or short:
files <- list.files(pattern = "\\.csv$")
DF <- read.csv(files[1])
for (f in files[-1]) DF <- rbind(DF, read.csv(f))
write.csv(DF, "Models_appended.csv", row.names=FALSE, quote=FALSE)
You can use this to load everything into one data set.
dataset <- do.call("rbind", lapply(file.list, FUN = function(file) {
read.table(file, header=TRUE, sep="\t")
}))
And then just save with write.csv.
Or you could go ahead and use shell commands in R:
system2("cat", args = "*.csv", stdout = "appendedfiles.csv")
This would be for unix based systems; I'm not sure what you would do for windows.
Try this for your ListOfFileNames:
ListOfFileNames<-list.files(pattern=".txt")
outFile <- file("all.txt", "w")
for (i in ListOfFileNames){
x <- readLines(i)
writeLines(x, outFile) # in the link the 1st and last line are skipped
}
close(outFile)
Source: https://r.789695.n4.nabble.com/R-Read-multiple-text-files-and-combine-into-single-file-td817344.html
There's an easy answer with rbind_list() now!
For instance:
dataFiles = map(Sys.glob("*.csv"), read.csv)
or however you're reading the files into a list
dat = rbind_list(dataFiles)
and dat will be what you're looking for!
If using Windows, it's easy to do this using the command prompt.
Start -> Run -> type "cmd" and hit return key
cd <path to folder>
copy /b *.txt <outputname>.txt
Concrete example:
cd C:\User\danny\docs\folder_with_txt files
copy /b *.txt concatenated.txt
Note that if you're changing drive letters to do this before cd
D:\> c:
C:\> cd C:\User\danny\docs\folder_with_txt files
copy /b *.txt concatenated.txt

Automate zip file reading in R

I need to automate R to read a csv datafile that's into a zip file.
For example, I would type:
read.zip(file = "myfile.zip")
And internally, what would be done is:
Unzip myfile.zip to a temporary folder
Read the only file contained on it using read.csv
If there is more than one file into the zip file, an error is thrown.
My problem is to get the name of the file contained into the zip file, in orded to provide it do the read.csv command. Does anyone know how to do it?
UPDATE
Here's the function I wrote based on #Paul answer:
read.zip <- function(zipfile, row.names=NULL, dec=".") {
# Create a name for the dir where we'll unzip
zipdir <- tempfile()
# Create the dir using that name
dir.create(zipdir)
# Unzip the file into the dir
unzip(zipfile, exdir=zipdir)
# Get the files into the dir
files <- list.files(zipdir)
# Throw an error if there's more than one
if(length(files)>1) stop("More than one data file inside zip")
# Get the full name of the file
file <- paste(zipdir, files[1], sep="/")
# Read the file
read.csv(file, row.names, dec)
}
Since I'll be working with more files inside the tempdir(), I created a new dir inside it, so I don't get confused with the files. I hope it may be useful!
Another solution using unz:
read.zip <- function(file, ...) {
zipFileInfo <- unzip(file, list=TRUE)
if(nrow(zipFileInfo) > 1)
stop("More than one data file inside zip")
else
read.csv(unz(file, as.character(zipFileInfo$Name)), ...)
}
You can use unzip to unzip the file. I just mention this as it is not clear from your question whether you knew that. In regard to reading the file. Once your extracted the file to a temporary dir (?tempdir), just use list.files to find the files that where dumped into the temporary directory. In your case this is just one file, the file you need. Reading it using read.csv is then quite straightforward:
l = list.files(temp_path)
read.csv(l[1])
assuming your tempdir location is stored in temp_path.
I found this thread as I was trying to automate reading multiple csv files from a zip. I adapted the solution to the broader case. I haven't tested it for weird filenames or the like, but this is what worked for me so I thought I'd share:
read.csv.zip <- function(zipfile, ...) {
# Create a name for the dir where we'll unzip
zipdir <- tempfile()
# Create the dir using that name
dir.create(zipdir)
# Unzip the file into the dir
unzip(zipfile, exdir=zipdir)
# Get a list of csv files in the dir
files <- list.files(zipdir)
files <- files[grep("\\.csv$", files)]
# Create a list of the imported csv files
csv.data <- sapply(files, function(f) {
fp <- file.path(zipdir, f)
return(read.csv(fp, ...))
})
return(csv.data)}
If you have zcat installed on your system (which is the case for linux, macos, and cygwin) you could also use:
zipfile<-"test.zip"
myData <- read.delim(pipe(paste("zcat", zipfile)))
This solution also has the advantage that no temporary files are created.
Here is an approach I am using that is based heavily on #Corned Beef Hash Map 's answer. Here are some of the changes I made:
My approach makes use of the data.table package's fread(), which
can be fast (generally, if it's zipped, sizes might be large, so you
stand to gain a lot of speed here!).
I also adjusted the output format so that it is a named list, where
each element of the list is named after the file. For me, this was a
very useful addition.
Instead of using regular expressions to sift through the files
grabbed by list.files, I make use of list.file()'s pattern
argument.
Finally, I by relying on fread() and by making pattern an
argument to which you could supply something like "" or NULL or
".", you can use this to read in many types of data files; in fact,
you can read in multiple types of at once (if your .zip contains
.csv, .txt in you want both, e.g.). If there are only some types of
files you want, you can specify the pattern to only use those, too.
Here is the actual function:
read.csv.zip <- function(zipfile, pattern="\\.csv$", ...){
# Create a name for the dir where we'll unzip
zipdir <- tempfile()
# Create the dir using that name
dir.create(zipdir)
# Unzip the file into the dir
unzip(zipfile, exdir=zipdir)
# Get a list of csv files in the dir
files <- list.files(zipdir, rec=TRUE, pattern=pattern)
# Create a list of the imported csv files
csv.data <- sapply(files,
function(f){
fp <- file.path(zipdir, f)
dat <- fread(fp, ...)
return(dat)
}
)
# Use csv names to name list elements
names(csv.data) <- basename(files)
# Return data
return(csv.data)
}
The following refines the above answers. FUN could be read.csv, cat, or anything you like, providing the first argument will accept a file path. E.g.
head(read.zip.url("http://www.cms.gov/Medicare/Coding/ICD9ProviderDiagnosticCodes/Downloads/ICD-9-CM-v32-master-descriptions.zip", filename = "CMS32_DESC_LONG_DX.txt"))
read.zip.url <- function(url, filename = NULL, FUN = readLines, ...) {
zipfile <- tempfile()
download.file(url = url, destfile = zipfile, quiet = TRUE)
zipdir <- tempfile()
dir.create(zipdir)
unzip(zipfile, exdir = zipdir) # files="" so extract all
files <- list.files(zipdir)
if (is.null(filename)) {
if (length(files) == 1) {
filename <- files
} else {
stop("multiple files in zip, but no filename specified: ", paste(files, collapse = ", "))
}
} else { # filename specified
stopifnot(length(filename) ==1)
stopifnot(filename %in% files)
}
file <- paste(zipdir, files[1], sep="/")
do.call(FUN, args = c(list(file.path(zipdir, filename)), list(...)))
}
Another approach that uses fread from the data.table package
fread.zip <- function(zipfile, ...) {
# Function reads data from a zipped csv file
# Uses fread from the data.table package
## Create the temporary directory or flush CSVs if it exists already
if (!file.exists(tempdir())) {dir.create(tempdir())
} else {file.remove(list.files(tempdir(), full = T, pattern = "*.csv"))
}
## Unzip the file into the dir
unzip(zipfile, exdir=tempdir())
## Get path to file
file <- list.files(tempdir(), pattern = "*.csv", full.names = T)
## Throw an error if there's more than one
if(length(file)>1) stop("More than one data file inside zip")
## Read the file
fread(file,
na.strings = c(""), # read empty strings as NA
...
)
}
Based on the answer/update by #joão-daniel
unzipped file location
outDir<-"~/Documents/unzipFolder"
get all the zip files
zipF <- list.files(path = "~/Documents/", pattern = "*.zip", full.names = TRUE)
unzip all your files
purrr::map(.x = zipF, .f = unzip, exdir = outDir)
I just wrote a function based on top read.zip that may help...
read.zip <- function(zipfile, internalfile=NA, read.function=read.delim, verbose=TRUE, ...) {
# function based on http://stackoverflow.com/questions/8986818/automate-zip-file-reading-in-r
# check the files within zip
unzfiles <- unzip(zipfile, list=TRUE)
if (is.na(internalfile) || is.numeric(internalfile)) {
internalfile <- unzfiles$Name[ifelse(is.na(internalfile),1,internalfile[1])]
}
# Create a name for the dir where we'll unzip
zipdir <- tempfile()
# Create the dir using that name
if (verbose) catf("Directory created:",zipdir,"\n")
dir.create(zipdir)
# Unzip the file into the dir
if (verbose) catf("Unzipping file:",internalfile,"...")
unzip(zipfile, file=internalfile, exdir=zipdir)
if (verbose) catf("Done!\n")
# Get the full name of the file
file <- paste(zipdir, internalfile, sep="/")
if (verbose)
on.exit({
catf("Done!\nRemoving temporal files:",file,".\n")
file.remove(file)
file.remove(zipdir)
})
else
on.exit({file.remove(file); file.remove(zipdir);})
# Read the file
if (verbose) catf("Reading File...")
read.function(file, ...)
}

Resources