Dear Ravi,
I wrote a small replacement for ifelse() which avoids such unnecessary
evaluations (it bothered me a few times as well - so I decided to try a
small replacement).
### Example:
x = 1:10
FUN = list();
FUN[[1]] = function(x, y) x*y;
FUN[[2]] = function(x, y) x^2;
FUN[[3]] = function(x, y) x;
# lets run multiple conditions
# eval.by.formula(conditions, FUN.list, ... (arguments for FUN) );
eval.by.formula((x > 5 & x %% 2) ~ (x <= 5) ~ ., FUN, x, x-1)
# Example 2
eval.by.formula((x > 5 & x %% 2) ~ (x <= 5) ~ ., FUN, 2, x)
### Disclaimer:
- NOT properly tested;
The code for the function is below. Maybe someone can experiment with
the code and improve it further. There are a few issues / open
questions, like:
1.) Best Name: eval.by.formula, ifelse.formula, ...?
2.) Named arguments: not yet;
3.) Fixed values inside FUN.list
4.) Format of expression for conditions:
expression(cond1, cond2, cond3) vs cond1 ~ cond2 ~ cond3 ???
5.) Code efficiency
- some tests on large data sets & optimizations are warranted;
Sincerely,
Leonard
=======
The latest code is on Github:
https://github.com/discoleo/R/blob/master/Stat/Tools.Formulas.R
eval.by.formula = function(e, FUN.list, ..., default=NA) {
tok = split.formula(e);
if(length(tok) == 0) return();
FUN = FUN.list;
# Argument List
clst = substitute(as.list(...))[-1];
len = length(clst);
clst.all = lapply(clst, eval);
eval.f = function(idCond) {
sapply(seq(length(isEval)), function(id) {
if(isEval[[id]] == FALSE) return(default);
args.l = lapply(clst.all, function(a) if(length(a) == 1) a
else a[[id]]);
do.call(FUN[[idCond]], args.l);
});
}
# eval 1st condition:
isEval = eval(tok[[1]]);
rez = eval.f(1);
if(length(tok) == 1) return(rez);
# eval remaining conditions
isEvalAll = isEval;
for(id in seq(2, length(tok))) {
if(tok[[id]] == ".") {
# Remaining conditions: tok == ".";
# makes sens only on the last position
if(id < length(tok)) warning("\".\" is not last!");
isEval = ! isEvalAll;
rez[isEval] = eval.f(id)[isEval];
next;
}
isEval = rep(FALSE, length(isEval));
isEval[ ! isEvalAll] = eval(tok[[id]])[ ! isEvalAll];
isEvalAll[isEval] = isEval[isEval];
rez[isEval] = eval.f(id)[isEval];
}
return(rez);
}
# current code uses the formula format:
# cond1 ~ cond 2 ~ cond3
# tokenizes a formula in its parts delimited by "~"
# Note:
# - tokenization is automatic for ",";
# - but call MUST then use FUN(expression(_conditions_), other_args, ...);
split.formula = function(e) {
tok = list();
while(length(e) > 0) {
if(e[[1]] == "~") {
if(length(e) == 2) { tok = c(NA, e[[2]], tok); break; }
tok = c(e[[3]], tok);
e = e[[2]];
} else {
tok = c(e, tok); break;
}
}
return(tok);
}
______________________________________________
R-help@r-project.org mailing list -- To UNSUBSCRIBE and more, see
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
and provide commented, minimal, self-contained, reproducible code.
