Apply functions instead of for loop in R - r

Question

I am novice in R. I want to know how we can write the below for loop in an efficient way. I am getting correct answer by the below code for small dataset.
data <- data.frame(x1=c(rep('a',12)),
x2=c(rep('b',12)),
x3=c(rep(as.Date('2017-03-09'),4),rep(as.Date('2017-03-10'),4),rep(as.Date('2017-03-11'),4)),
value1= seq(201,212),
x4=c(as.Date('2017-03-09'),as.Date('2017-03-10'),as.Date('2017-03-11'),as.Date('2017-03-12')
,as.Date('2017-03-10'),as.Date('2017-03-11'),as.Date('2017-03-12'),as.Date('2017-03-13')
,as.Date('2017-03-11'),as.Date('2017-03-12'),as.Date('2017-03-13'),as.Date('2017-03-14')),
value2= seq(101,112), stringsAsFactors = FALSE)
Below for loop script:
for (i in 1:length(data$x3)){
print(i)
if (!is.na(data$x4[i])){
if(data$x4[i] == data$x3[i] && data$x2[i]==data$x2[i] && data$x1[i]==data$x1[i]){
data$diff[i] <- data$value1[i] - data$value2[i]
}
else{
print("I am in else")
for (j in 1:length(data$x3)){
print(c(i,j))
# print(a$y[i])
if(data$x4[i]==data$x3[j] && data$x1[i]==data$x1[j] && data$x2[i]==data$x2[j]){
# print(a$x[j])
data$diff[i] <- data$value1[j] - data$value2[i]
break
}
}
}
}
}

Answer 1

If you want performance, the answer is often Rcpp.
Translating your R code in Rcpp:
#include <Rcpp.h>
using namespace Rcpp;
// [[Rcpp::export]]
NumericVector f_Rcpp(List data) {
StringVector x1 = data["x1"];
StringVector x2 = data["x2"];
NumericVector x3 = data["x3"];
NumericVector x4 = data["x4"];
NumericVector value1 = data["value1"];
NumericVector value2 = data["value2"];
int n = value1.size();
NumericVector diff(n, NA_REAL);
int i, j;
for (i = 0; i < n; i++) {
Rprintf("%d\n", i);
if (x4[i] != NA_REAL) {
if (x4[i] == x3[i]) {
diff[i] = value1[i] - value2[i];
} else {
Rprintf("I am in else\n");
for (j = 0; j < n; j++) {
Rprintf("%d %d\n", i, j);
if (x4[i] == x3[j] && x1[i] == x1[j] && x2[i] == x2[j]) {
diff[i] = value1[j] - value2[i];
break;
}
}
}
}
}
return diff;
}
/*** R
f_Rcpp(data)
*/
Put that in a .cpp file and source it.

Answer 2

You can do this:
data$diff <- sapply(seq_along(data$x3), function(i) {
if (!is.na(data$x4[i])){
ind <- which(data$x4[i] == data$x3 & data$x1[i] == data$x1 & data$x2[i] == data$x2)
j <- `if`(i %in% ind, i, min(ind))
data$value1[j] - data$value2[i]
} else {
NA
}
})
Beware in your code, if column $diff doesn't exist yet, doing data$diff[1] <- 100 will put all the values of the column at 100.