Using app function from {terra} package on raster stacks? (in parallel) - r

I have four high resolution rasters for a country. I have split each raster into tiles and done some other processing to them. I now want to apply a function to each cell, of each 'stack' of the raster tiles, to produce one set of output tiles. The function is a little complex. I have tried to synthesise some data below to reproduce my current approach. It works (ish) but I'm convinced that there's a better way to do this. To use parallel processing on my unix box, I simply swap mapply for mcmapply, but I haven't done that in the example below as I presume many will be working on Windows machines. I'd welcome ideas on my approach and particularly optimisation.
library("terra")
library("glue")
## Make some toy data
dir.create("temp_folder")
dir.create("result_folder")
x <- rast(ncols = 10, nrows = 10)
a <- rast(ncol = 100, nrow = 100)
some_values <- as.integer(runif(10000, min = 1, max = 100))
ind <- which(some_values %in% sample(some_values, 15))
some_values[ind] <- NA
values(a) <- some_values
a_tiles <- makeTiles(a, x, glue("temp_folder/tile_a_{1:100}.tif"), overwrite = TRUE)
b <- rast(ncol = 100, nrow = 100)
some_values <- as.integer(runif(10000, min = 1, max = 100))
ind <- which(some_values %in% sample(some_values, 15))
some_values[ind] <- NA
values(b) <- some_values
b_tiles <- makeTiles(b, x, glue("temp_folder/tile_b_{1:100}.tif"), overwrite = TRUE)
c <-rast(ncol = 100, nrow = 100)
some_values <- as.integer(runif(10000, min = 1, max = 100))
ind <- which(some_values %in% sample(some_values, 15))
some_values[ind] <- NA
values(c) <- some_values
c_tiles <- makeTiles(c, x, glue("temp_folder/tile_c_{1:100}.tif"), overwrite = TRUE)
d <- rast(ncol = 100, nrow = 100)
some_values <- as.integer(runif(10000, min = 1, max = 100))
ind <- which(some_values %in% sample(some_values, 15))
some_values[ind] <- NA
values(d) <- some_values
d_tiles <- makeTiles(d, x, glue("temp_folder/tile_d_{1:100}.tif"), overwrite = TRUE)
## Outer function so that this can be used in parallel ? But maybe this is a silly way to do it?
outer_function <- function(a_tiles, b_tiles, c_tiles, d_tiles, output_files) {
one_a_tile <- rast(unlist(a_tiles))
one_b_tile <- rast(unlist(b_tiles))
one_c_tile <- rast(unlist(c_tiles))
one_d_tile <- rast(unlist(d_tiles))
output_file <- output_files
# I replace any NAs with 0 as an NA will break my 'if' statement of the inner_function.
# I get Error in if (z["a"] <= z["b"]) { : missing value where TRUE/FALSE needed
one_a_tile[is.na(one_a_tile)] <- 0
one_b_tile[is.na(one_b_tile)] <- 0
one_c_tile[is.na(one_c_tile)] <- 0
one_d_tile[is.na(one_d_tile)] <- 0
z <- sds(one_a_tile, one_b_tile, one_c_tile, one_d_tile)
## Inner function that actually does the work I want doing
inner_function <- function(z) {
names(z) <- c('a', 'b', 'c', 'd')
if (z['a'] <= z['b']) {
y <- rowSums(cbind((z['c'] + z['a'] * 10),
(z['c'] + z['a'] * 20)))
}
if (z['a'] >= z['b']) {
y <- rowSums(cbind((z['c'] + z['a'] * 40),
(z['c'] + z['a'] * 10)))
}
if (z['a'] == z['b']) {
y <- rowSums(cbind((z['c'] + z['a'] * 60),
(z['c'] + z['a'] * 10)))
}
y <- ifelse(y == 0, NA, y)
return(y)
}
app(z,
inner_function,
filename = output_file,
overwrite = TRUE,
wopt = list(datatype = "INT4U"))
return(output_file)
}
results <- mapply(outer_function,
a_tiles = a_tiles,
b_tiles = b_tiles,
c_tiles = c_tiles,
d_tiles = d_tiles,
output_files = output_files <- glue("result_folder/result_tile_{1:length(d_tiles)}.tif"))
names(results) <- NULL
unlink("temp_folder", recursive = TRUE)
unlink("result_folder", recursive = TRUE)

Related

R bootstrapping for the two dataframe individual column wise

Want to do Bootstrapping while comparing two dataframe column wise with the different number of rows.
I have two dataframe in which row represent values from experiments and column with the dataset names (data1, data2, data3, data4)
emp.data1 <- data.frame(
data1 = c(234,0,34,0,46,0,0,0,2.26,0, 5,8,93,56),
data2 = c(1.40,1.21,0.83,1.379,2.60,9.06,0.88,1.16,0.64,8.28, 5,8,93,56),
data3 =c(0,34,43,0,0,56,0,0,0,45,5,8,93,56),
data4 =c(45,0,545,34,0,35,0,35,0,534, 5,8,93,56),
stringsAsFactors = FALSE
)
emp.data2 <- data.frame(
data1 = c(45, 0, 0, 45, 45, 53),
data2 = c(23, 0, 45, 12, 90, 78),
data3 = c(72, 45, 756, 78, 763, 98),
data4 = c(1, 3, 65, 78, 9, 45),
stringsAsFactors = FALSE
)
I am trying to do bootstrapping(n=1000). Values are selected at random replacement from emp.data1(14 * 4) without change in the emp.data2(6 * 4). For example from emp.data2 first column (data1) select 6 values colSum and from emp.data1(data1) select 6 random non zero values colSum Divide the values and store in temp repeat the same 1000 times and take a median value et the end. like this i want to do it for each column of the dataframe. sample code I am providing which is working fine but i am not able get the non-zero random values for emp.data1
nboot <- 1e3
boot_temp_emp<- c()
n_data1 <- nrow(emp.data1); n_data2 <- nrow(emp.data2)
for (j in seq_len(nboot)) {
boot <- sample(x = seq_len(n_data1), size = n_data2, replace = TRUE)
value <- colSums(emp.data2)/colSums(emp.data1[boot,])
boot_temp_emp <- rbind(boot_temp_emp, value)
}
boot_data<- apply(boot_temp_emp, 2, median)
From the above script i am able get the output but each column emp.data1[boot,] data has zero values and taken sum. I want indivisual ramdomly selected non-zero values column sum so I tried below script not able remove zero values. Not able get desired output please some one help me to correct my script
nboot <- 1e3
boot_temp_emp<- c()
for (i in colnames(emp.data2)){
for (j in seq_len(nboot)){
data1=emp.data1[i]
data2=emp.data2[i]
n_data1 <- nrow(data1); n_data2 <- nrow(data2)
boot <- sample(x = seq_len(n_data1), size = n_data2, replace = TRUE)
value <- colSums(data2[i])/colSums(data1[boot, ,drop = FALSE])
boot_temp_emp <- rbind(boot_temp_emp, value)
}
}
boot_data<- apply(boot_temp_emp, 2, median)
Thank you
Here is a solution.
Write a function to make the code clearer. This function takes the following arguments.
x the input data.frame emp.data1;
s2 the columns sums of emp.data2;
n = 6 the number of vector elements to sample from emp.data1's columns with a default value of 6.
The create a results matrix, pre-compute the column sums of emp.data2 and call the function in a loop.
boot_fun <- function(x, s2, n = 6){
# the loop makes sure ther is no divide by zero
nrx <- nrow(x)
repeat{
i <- sample(nrx, n, replace = TRUE)
s1 <- colSums(x[i, ])
if(all(s1 != 0)) break
}
s2/s1
}
set.seed(2022)
nboot <- 1e3
sums2 <- colSums(emp.data2)
results <- matrix(nrow = nboot, ncol = ncol(emp.data1))
for(i in seq_len(nboot)){
results[i, ] <- boot_fun(emp.data1, sums2)
}
ratios_medians <- apply(results, 2, median)
old_par <- par(mfrow = c(2, 2))
for(j in 1:4) {
main <- paste0("data", j)
hist(results[, j], main = main, xlab = "ratios", freq = FALSE)
abline(v = ratios_medians[j], col = "blue", lty = "dashed")
}
par(old_par)
Created on 2022-02-24 by the reprex package (v2.0.1)
Edit
Following the comments here is a revised version of the bootstrap function. It makes sure there are no zeros in the sampled vectors, before computing their sums.
boot_fun2 <- function(x, s2, n = 6){
nrx <- nrow(x)
ncx <- ncol(x)
s1 <- numeric(ncx)
for(j in seq.int(ncx)) {
repeat{
i <- sample(nrx, n, replace = TRUE)
if(all(x[i, j] != 0)) {
s1[j] <- sum(x[i, j])
break
}
}
}
s2/s1
}
set.seed(2022)
nboot <- 1e3
sums2 <- colSums(emp.data2)
results2 <- matrix(nrow = nboot, ncol = ncol(emp.data1))
for(i in seq_len(nboot)){
results2[i, ] <- boot_fun2(emp.data1, sums2)
}
ratios_medians2 <- apply(results2, 2, median)
old_par <- par(mfrow = c(2, 2))
for(j in 1:4) {
main <- paste0("data", j)
hist(results2[, j], main = main, xlab = "ratios", freq = FALSE)
abline(v = ratios_medians2[j], col = "blue", lty = "dashed")
}
par(old_par)
Created on 2022-02-27 by the reprex package (v2.0.1)

Why does function return NULL?

A beginner in R over here, so apologies for the basic question.
Why does ATE return a null vector instead of saving the values of the difference of the means?
fun.cluster <- function(M, N){
set.seed(02139)
J <- 1:M # vector J_i
df <- as.data.frame(matrix(data=1:N, nrow = N, ncol = 1)) #data frame of all original values
df$cluster <- cut(df$V1, M, labels = 1:M) #breaking the dataframe into clusters
df$cluster <- as.numeric(df$cluster)
Y1 <- as.vector(sample(J, 5)) # assigning treatment
df$treatment <- ifelse(df$cluster %in% Y1, df$treatment <- 1, df$treatment <- 0)
#Inducing intracluster correlation:
mu_0j <- runif(n = 50, min = -1, max = 1)
df$V1[df$treatment==0] <- mu_0j
mu_1j <- runif(n=50, min = -0.5, max = 1.5)
df$V1[df$treatment==0] <- mu_1j
# drawing values
y_0i <- rnorm(n = 50, mean = mu_0j, sd = 1)
y_1i <- rnorm(n = 50, mean = mu_1j, sd = 1)
D_i <- as.vector(c(y_0i, y_1i))
# calculating ATE:
ATE[i] <- mean(y_1i - y_0i)
}
ATE <- c()
for(i in 1:10){
fun.cluster(M = 10, N = 100)
}

Convert for loops into foreach loops

I want to make the code below more efficient by using the foreach package. I tried it for a very long time but I don't manage to get the same result as when using the for-loops. I would like to use a nested foreach-loop including parallelization... And as output I would like to have two matrices with dim [R,b1] I would be very grateful for some suggestions!!
n <- c(100, 300, 500)
R <- 100
b0 <- 110
b1 <- seq(0.01, 0.1, length.out = 100)
## all combinations of n and b1
grid <- expand.grid(n, b1)
names(grid) <- c("n", "b1")
calcPower <- function( R, b0, grid) {
cl <- makeCluster(3)
registerDoParallel(cl)
## n and b1 coefficients
n <- grid$n
b1 <- grid$b1
## ensures reproducibility
set.seed(2020)
x <- runif(n, 18, 80)
x.dich <- factor( ifelse( x < median( x), 0, 1))
## enables to store two outputs
solution <- list()
## .options.RNG ensures reproducibility
res <- foreach(i = 1:R, .combine = rbind, .inorder = TRUE, .options.RNG = 666) %dorng% {
p.val <- list()
p.val.d <- list()
for( j in seq_along(b1)) {
y <- b0 + b1[j] * x + rnorm(n, 0, sd = 10)
mod.lm <- lm( y ~ x)
mod.lm.d <- lm( y ~ x.dich)
p.val <- c( p.val, ifelse( summary(mod.lm)$coef[2,4] <= 0.05, 1, 0))
p.val.d <- c( p.val.d, ifelse( summary(mod.lm.d)$coef[2,4] <= 0.05, 1, 0))
}
solution[[1]] <- p.val
solution[[2]] <- p.val.d
return(solution)
}
dp.val <- matrix( unlist(res[,1], use.names = FALSE), R, length(b1), byrow = TRUE)
dp.val.d <- matrix( unlist(res[,2], use.names = FALSE), R, length(b1), byrow = TRUE)
stopCluster(cl)
df <- data.frame(
effectS = b1,
power = apply( dp.val, 2, function(x){ mean(x) * 100}),
power.d = apply( dp.val.d, 2, function(x){ mean(x) * 100}),
n = factor(n))
return(df)
}
## simulation for different n
tmp <- with(grid,
by( grid, n,
calcPower, R = R, b0 = b0))
## combines the 3 results
df.power <- rbind(tmp[[1]], tmp[[2]], tmp[[3]])
I created a foreach loop in following code. There had to be some changes made. It is a lot easier to return a list then a matrix in foreach, since it's combined with rbind. Especially when you want to return multiple ones. My solution here is to save everything in a list and afterwards transform it into a matrix of length 100.
Note: there is one mistake in your code. summary( mod.lm.d)$coef[2,4] does not exist. I changed it to [2]. Adjust to your needing
solution <- list()
df2<-foreach(i = 1:R, .combine = rbind, .inorder=TRUE) %dopar%{
set.seed(i)
p.val <- list()
p.val.d <- list()
counter <- list()
for( j in seq_along(b1)){
x <- sort( runif(n, 18, 80))
x.dich <- factor( ifelse( x < median(x), 0, 1))
y <- b0 + b1[j] * x + rnorm( n, 0, sd = 10)
mod.lm <- lm( y ~ x)
mod.lm.d <- lm( y ~ x.dich)
p.val <- c(p.val, ifelse( summary( mod.lm)$coef[2] <= 0.05, 1, 0))
p.val.d <- c(p.val.d, ifelse( summary( mod.lm.d)$coef[2] <= 0.05, 1, 0))
counter <- c(counter, j)
}
solution[[1]] <- p.val
solution[[2]] <- p.val.d
solution[[3]] <- counter
return(solution)
}
dp.val <- unlist(df2[,1], use.names = FALSE)
dp.val.d <- unlist(df2[,2], use.names = FALSE)
dp.val.matr <- matrix(dp.val, R, length(b1))
dp.val.d.matr <- matrix(dp.val.d, R, length(b1))
stopCluster(cl)
for your comment:
A foreach does work with a normal for loop. Minimal reproducible example:
df<-foreach(i = 1:R, .combine = cbind, .inorder=TRUE) %dopar%{
x <- list()
for(j in 1:3){
x <- c(x,j)
}
return(x)
}

How do I speed up my function, specifically the ggplot commands?

I put together a function to identify outliers. It takes a dataframe and then shows plots of the data with lines to indicate potential outliers. It'll give a table with outliers marked, too.
But, it is SLOOOW. The problem is it takes a really long time for the plots to load.
I was curious if you might have advice on how to speed this up.
Related: Is the default plotting system faster than ggplot?
I'll start with the dependencies
#These next four functions are not mine. They're used in GetOutliers()
ExtractDetails <- function(x, down, up){
outClass <- rep("N", length(x))
indexLo <- which(x < down)
indexHi <- which(x > up)
outClass[indexLo] <- "L"
outClass[indexHi] <- "U"
index <- union(indexLo, indexHi)
values <- x[index]
outClass <- outClass[index]
nOut <- length(index)
maxNom <- max(x[which(x <= up)])
minNom <- min(x[which(x >= down)])
outList <- list(nOut = nOut, lowLim = down,
upLim = up, minNom = minNom,
maxNom = maxNom, index = index,
values = values,
outClass = outClass)
return(outList)
}
Hampel <- function(x, t = 3){
#
mu <- median(x, na.rm = TRUE)
sig <- mad(x, na.rm = TRUE)
if (sig == 0){
message("Hampel identifer implosion: MAD scale estimate is zero")
}
up<-mu+t*sig
down<-mu-t*sig
out <- list(up = up, down = down)
return(out)
}
ThreeSigma <- function(x, t = 3){
#
mu <- mean(x, na.rm = TRUE)
sig <- sd(x, na.rm = TRUE)
if (sig == 0){
message("All non-missing x-values are identical")
}
up<-mu+t* sig
down<-mu-t * sig
out <- list(up = up, down = down)
return(out)
}
BoxplotRule <- function(x, t = 1.5){
#
xL <- quantile(x, na.rm = TRUE, probs = 0.25, names = FALSE)
xU <- quantile(x, na.rm = TRUE, probs = 0.75, names = FALSE)
Q<-xU-xL
if(Q==0){
message("Boxplot rule implosion: interquartile distance is zero")
}
up<-xU+t*Q
down<-xU-t*Q
out <- list(up = up, down = down)
return(out)
}
FindOutliers <- function(x, t3 = 3, tH = 3, tb = 1.5){
threeLims <- ThreeSigma(x, t = t3)
HampLims <- Hampel(x, t = tH)
boxLims <- BoxplotRule(x, t = tb)
n <- length(x)
nMiss <- length(which(is.na(x)))
threeList <- ExtractDetails(x, threeLims$down, threeLims$up)
HampList <- ExtractDetails(x, HampLims$down, HampLims$up)
boxList <- ExtractDetails(x, boxLims$down, boxLims$up)
sumFrame <- data.frame(method = "ThreeSigma", n = n,
nMiss = nMiss, nOut = threeList$nOut,
lowLim = threeList$lowLim,
upLim = threeList$upLim,
minNom = threeList$minNom,
maxNom = threeList$maxNom)
upFrame <- data.frame(method = "Hampel", n = n,
nMiss = nMiss, nOut = HampList$nOut,
lowLim = HampList$lowLim,
upLim = HampList$upLim,
minNom = HampList$minNom,
maxNom = HampList$maxNom)
sumFrame <- rbind.data.frame(sumFrame, upFrame)
upFrame <- data.frame(method = "BoxplotRule", n = n,
nMiss = nMiss, nOut = boxList$nOut,
lowLim = boxList$lowLim,
upLim = boxList$upLim,
minNom = boxList$minNom,
maxNom = boxList$maxNom)
sumFrame <- rbind.data.frame(sumFrame, upFrame)
threeFrame <- data.frame(index = threeList$index,
values = threeList$values,
type = threeList$outClass)
HampFrame <- data.frame(index = HampList$index,
values = HampList$values,
type = HampList$outClass)
boxFrame <- data.frame(index = boxList$index,
values = boxList$values,
type = boxList$outClass)
outList <- list(summary = sumFrame, threeSigma = threeFrame,
Hampel = HampFrame, boxplotRule = boxFrame)
return(outList)
}
#strip non-numeric variables out of a dataframe
num_vars <- function(df){
X <- which(sapply(df, is.numeric))
num_vars <- df[names(X)]
return(num_vars)
}
This is the function
GetOutliers <- function(df){
library('dplyr')
library('ggplot2')
#strip out the non-numeric columns
df_out <- num_vars(df)
#initialize the data frame
df_out$Hampel <- NA
df_out$threeSigma <- NA
df_out$boxplotRule <- NA
df_out_id <- df_out
#identify outliers for each column
for (i in 1:length(names(num_vars(df)))){
#find the outliers
Outs <- FindOutliers(df_out[[i]])
OutsSum <- Outs$summary
#re-enter the outlier status
df_out$Hampel <- NA
df_out$threeSigma <- NA
df_out$boxplotRule <- NA
ifelse(is.na(Outs$Hampel), print(), df_out[unlist(Outs$Hampel[1]),]$Hampel <- TRUE)
ifelse(is.na(Outs$threeSigma), print(), df_out[unlist(Outs$threeSigma[1]),]$threeSigma <- TRUE)
ifelse(is.na(Outs$boxplotRule), print(), df_out[unlist(Outs$boxplotRule[1]),]$boxplotRule <- TRUE)
#visualize the outliers and print outlier information
Temp <- df_out
A <- colnames(Temp)[i]
AA <- paste(A,"Index")
colnames(Temp)[i] <- 'curr_column'
#table with outlier status
X <- arrange(subset(Temp,Hampel == TRUE | boxplotRule == TRUE | threeSigma == TRUE), desc(curr_column))
#scatterplot with labels
Y <- ggplot(Temp,aes(seq_along(curr_column),curr_column)) + geom_point() +
geom_hline(yintercept=OutsSum$lowLim[1],linetype = 'dashed') +
geom_hline(yintercept=OutsSum$lowLim[2],linetype = 'dashed') +
geom_hline(yintercept=OutsSum$lowLim[3],linetype = 'dashed') +
geom_hline(yintercept=OutsSum$upLim[1],linetype = 'dashed') +
geom_hline(yintercept=OutsSum$upLim[2],linetype = 'dashed') +
geom_hline(yintercept=OutsSum$upLim[3],linetype = 'dashed') +
geom_text(aes(40,OutsSum$lowLim[1],label="ThreeSigma Lower",vjust=-1)) +
geom_text(aes(40,OutsSum$lowLim[2],label="Hampel Lower",vjust=-1)) +
geom_text(aes(40,OutsSum$lowLim[3],label="Boxplot Lower",vjust=-1)) +
geom_text(aes(40,OutsSum$upLim[1],label="ThreeSigma Upper",vjust=-1)) +
geom_text(aes(40,OutsSum$upLim[2],label="Hampel Upper",vjust=-1)) +
geom_text(aes(40,OutsSum$upLim[3],label="Boxplot Upper",vjust=-1)) +
xlab(AA) + ylab(A)
#scatterplot without labels
Z <- ggplot(Temp,aes(seq_along(curr_column),curr_column)) + geom_point() +
geom_hline(yintercept=OutsSum$lowLim[1],linetype = 'dashed') +
geom_hline(yintercept=OutsSum$lowLim[2],linetype = 'dashed') +
geom_hline(yintercept=OutsSum$lowLim[3],linetype = 'dashed') +
geom_hline(yintercept=OutsSum$upLim[1],linetype = 'dashed') +
geom_hline(yintercept=OutsSum$upLim[2],linetype = 'dashed') +
geom_hline(yintercept=OutsSum$upLim[3],linetype = 'dashed') +
xlab(AA) + ylab(A)
U <- ggplot(Temp,aes(curr_column)) + geom_density() + xlab(A)
print(A)
print(X)
print(OutsSum)
print(Z)
print(Y)
print(U)
#mark the extreme outliers, the rest are reasonable outliers
A <- colnames(df_out_id[i])
Q <- as.numeric(readline(prompt="Enter the index for final Extreme value on the upper limit (if none, enter 0): "))
W <- as.numeric(readline(prompt="Enter the index for first Extreme value on the lower limit (if none, enter 0): "))
col <- df_out_id[i]
df_out_id[i] <- sapply(col[[1]], function(x){
if(Q>1 & x %in% X$curr_column[1:Q]) return('Extreme')
if(W>1 & x %in% X$curr_column[W:length(X$curr_column)]) return('Extreme')
else if (x %in% X$curr_column[Q+1:length(X$curr_column)]) return('Reasonable')
else return('Non-Outlier')
})
}
#return a dataframe with outlier status, excluding the outlier ID columns
summary(df_out_id)
return(df_out_id[1:(length(names(df_out_id))-3)])
}
Example
library('ISLR')
data(Carseats)
GetOutliers(Carseats)
It'll show you the outliers for each numeric variable.
It'll plot the variable density and then a scatterplot with identifier lines
It will also accept input so you can mark some outliers as reasonable and other as extreme

IDW parameters in R

I want to perform IDW interpolation using R using the idw command from the gstat package. I have this data:
#settings
library(gstat)
library(dplyr)
library(sp)
library(tidyr)
id_rep <- rep(c(1,2), 20)
f <- rep(c(930,930.2), each=20)
perc <- rep(c(90, 80), each=10)
x <- sample(1:50, 40)
y <- sample(50:100, 40)
E <- runif(40)
df <- data.frame(id_rep, perc, x,y, f, E)
df_split <- split(df, list(df$id_rep, df$perc, df$f), drop = TRUE, sep="_")
#grid
x.range <- range(df$x)
y.range <- range(df$y)
grid <- expand.grid(x = seq(x.range[1], x.range[2], by=1),
y = seq(y.range[1], y.range[2], by=1))
coordinates(grid) <- ~x + y
#interpolation
lst_interp_idw <- lapply(df_split, function(X) {
coordinates(X) <- ~x + y
E_idw <- idw(E~ 1, X, grid, idp=1, nmax=3) %>% as.data.frame()
df_interp <- select(E_idw, x,y,E_pred=var1.pred)
df_interp
})
df_interp_idw <- bind_rows(lst_interp_idw, .id = "interact") %>%
separate(interact, c("id_rep", "perc", "f"), sep = "\\_")
Now I want to perform each run with different idp and nmax parameters within certain values​ (idp from 1 to 3 by 0.5, and nmax 3 to 6 by 1) and get out a data frame with columns for each combination of idp and nmax values. I try with two for loops but it doesn't work.
EDIT
the code that doesn't work is:
idp = seq(from = 1, to = 3, by = 0.5)
nmax = seq(from = 3, to = 6, by = 1)
...
for(i in idp) {
for(j in nmax)
{ E_idw= idw(E ~ 1, X, grid, nmax = i, idp = j)
}
}
...
Here is a way how to store the result of every iteration in a list.
#settings
#install.packages("gstat")
library(gstat)
library(dplyr)
library(sp)
library(tidyr)
id_rep <- rep(c(1,2), 20)
f <- rep(c(930,930.2), each=20)
perc <- rep(c(90, 80), each=10)
x <- sample(1:50, 40)
y <- sample(50:100, 40)
E <- runif(40)
df <- data.frame(id_rep, perc, x,y, f, E)
df_split <- split(df, list(df$id_rep, df$perc, df$f), drop = TRUE, sep="_")
#grid
x.range <- range(df$x)
y.range <- range(df$y)
grid <- expand.grid(x = seq(x.range[1], x.range[2], by=1),
y = seq(y.range[1], y.range[2], by=1))
coordinates(grid) <- ~x + y
# ==============================================
# NEW function
# ==============================================
idp = seq(from = 1, to = 3, by = 0.5)
nmax = seq(from = 3, to = 6, by = 1)
#interpolation
lst_interp_idw <- lapply(df_split, function(X) {
coordinates(X) <- ~x + y
df_interp <- vector(length(idp)*length(nmax), mode = "list" )
k <- 0
for(i in idp) {
for(j in nmax) {
print(paste(i, j))
# Iterator
k <- k + 1
E_idw= idw(E ~ 1, X, grid, nmax = i, idp = j) %>% as.data.frame()
df_interp[[k]] <- select(E_idw, x,y,E_pred=var1.pred)
}
}
return(df_interp)
})
# ==============================================
Some plausibility checks (lapply is applied to 8 list elements and 20 variations are calculated):
length(lst_interp_idw) # 8
length(lst_interp_idw[[1]]) #20
length(lst_interp_idw[[1]]) #20
It should be easy for you to adapt the last line of your code
df_interp_idw <- bind_rows(lst_interp_idw, .id = "interact") %>%
separate(interact, c("id_rep", "perc", "f"), sep = "\\_")
to format the output in the desired format. This highly depends on how you want to present the different interpolation alternatives.

Resources