这里有一个想法,可能有点不寻常:您可以创建一个“getter”函数,它只接受一个参数:您要实例化的变量的名称,而不是直接使用代码中的底层对象代码中的那一点。你可以把它当作一个字符串,或者更好的是,使用substitute() 来允许使用不带引号的符号(实际上,我最终使用了as.character(substitute(var)),所以两者都可以)。在函数内部,您可以查找“全局条件”来决定如何对变量进行子集化,如果它应该被子集化。为了获得最大的灵活性,查找表还可以将每个变量映射到该变量的特定条件。这是我的设想:
## lookup table and getter
cond.to.vec <- list();
COND.NAME.GLOBAL <- '!global';
var.to.cond <- list();
cond.register <- function(name,vec=NULL) {
prev.vec <- cond.to.vec[[name]];
cond.to.vec[[name]] <<- vec;
invisible(prev.vec);
};
cond.is.registered <- function(name) !is.null(cond.to.vec[[name]]);
cond.map <- function(var.name,cond.name=NULL) {
## remove previous mapping
prev.mapping <- var.to.cond[[var.name]];
var.to.cond[[var.name]] <<- NULL;
## omit cond.name arg to just remove
if (is.null(cond.name)) return(invisible(prev.mapping));
## ensure cond.name has been registered
if (!cond.is.registered(cond.name)) stop(paste0(cond.name,' not registered'));
## now add new cond.name mapping for var.name
var.to.cond[[var.name]] <<- cond.name;
invisible(prev.mapping);
};
cond.set <- function(var,cond.vec=NULL,sym=T) {
var.name <- if (sym) as.character(substitute(var)) else var;
cond.register(var.name,cond.vec);
cond.map(var.name,if (is.null(cond.vec)) NULL else var.name);
};
cond.set.global <- function(vec=NULL) cond.register(COND.NAME.GLOBAL,vec);
cond.look.up <- function(var.name) {
## 1: specific condition
cond.name <- var.to.cond[[var.name]];
if (!is.null(cond.name)) return(cond.to.vec[[cond.name]]);
## 2: global condition
vec <- cond.to.vec[[COND.NAME.GLOBAL]];
if (!is.null(vec)) return(vec);
## 3: no condition
T;
};
ss <- function(var,sym=T) {
## whitelist subsettables
if (!typeof(var)%in%sapply(list(as.raw(0),T,0L,0,0i,'',list(),expression()),typeof))
return(var);
var.name <- if (sym) as.character(substitute(var)) else var;
vec <- cond.look.up(var.name);
if (length(dim(var)) == 2L) var[vec,] else var[vec];
};
## test data
set.seed(1);
N <- 10;
myNucleotideVector <- sample(c('A','C','T','G'),N,replace=T);
myNucleotideVectorNum <- sample(100:200,N,replace=T);
object2 <- seq_len(N);
dataframe1 <- data.frame(base=sample(c('A','C','T','G'),N,replace=T),x=sample(1:100,N));
## global condition
cond.set.global(myNucleotideVector == 'G');
## main code, uses global condition
result <- ss(myNucleotideVectorNum) - ss(object2) + ss(dataframe1)$x;
## register separate condition for object2
cond.set(object2,object2%%3 == 0);
result2 <- ss(myNucleotideVectorNum) - ss(object2) + ss(dataframe1)$x;
## unset/unregister all conditions to work with the entire data set
cond.set.global();
cond.set(object2);
result3 <- ss(myNucleotideVectorNum) - ss(object2) + ss(dataframe1)$x;
result;
## [1] 153 208 240
result2;
## [1] 154 208 238
result3;
## [1] 168 175 266 153 252 208 240 203 196 206
现在我们可以用更多的函数来增强上面的代码,以提供一种侵入性较小的方法来应用子集条件:
ss.all.sub <- function(pt) {
if (typeof(pt) == 'symbol') ## wrap all symbols in ss()
as.call(list(as.symbol('ss'),pt))
else if (typeof(pt) == 'language' && length(pt) >= 2L) ## handle function args
as.call(c(pt[[1]], ## pass function symbol untouched
if (as.character(pt[[1]]) == '$') ## special case for $ operator
list(ss.all.sub(pt[[2]]),pt[[3]]) ## pass RHS untouched
else
lapply(pt[-1],ss.all.sub) ## recurse on all args
))
else pt; ## pass literals and nullary calls untouched
};
ss.all <- function(expr) eval(ss.all.sub(substitute(expr)));
ss.with <- function(cond.arg,expr) {
if (is.list(cond.arg)) {
prevs <- vector('list',length(cond.arg));
for (i in seq_along(cond.arg)) {
name <- names(cond.arg)[i];
prevs[i] <- list(
if (isTRUE(name != '' && name != COND.NAME.GLOBAL))
cond.set(name,cond.arg[[i]],sym=F)
else
cond.set.global(cond.arg[[i]])
);
};
} else prev <- cond.set.global(cond.arg);
res <- eval(ss.all.sub(substitute(expr)));
if (is.list(cond.arg)) {
for (i in seq_along(cond.arg)) {
name <- names(cond.arg)[i];
if (isTRUE(name != '' && name != COND.NAME.GLOBAL))
cond.set(name,prevs[[i]],sym=F)
else
cond.set.global(prevs[[i]]);
};
} else cond.set.global(prev);
res;
};
## demo parse tree substitution
ss.all.sub(substitute(myNucleotideVectorNum - object2 + dataframe1$x));
## ss(myNucleotideVectorNum) - ss(object2) + ss(dataframe1)$x
## demo using ss.with() to apply an inline condition
ss.with(myNucleotideVector == 'G',myNucleotideVectorNum - object2 + dataframe1$x);
## [1] 153 208 240
ss.with(
list(myNucleotideVector == 'G',object2=object2%%3 == 0),
myNucleotideVectorNum - object2 + dataframe1$x
);
## [1] 154 208 238
ss.with(T,myNucleotideVectorNum - object2 + dataframe1$x);
## [1] 168 175 266 153 252 208 240 203 196 206