您描述的问题与data.table.
复杂的查询不能轻易地转换为机器可以解析的代码，因此我们无法避免为复杂操作编写查询的复杂性。
您可以尝试想象如何data.table使用dplyr或SQL以编程方式为以下查询构造查询：
DT[, c(f1(v1, v2, opt=TRUE),
f2(v3, v4, v5, opt1=FALSE, opt2=TRUE),
lapply(.SD, f3, opt1=TRUE, opt2=FALSE))
, by=.(id1, id2)]
假设所有列（id1, id2, v1... v5）甚至选项（opt, opt1, opt2）都应该作为变量传递。
由于查询表达的复杂性，我认为您无法轻松完成问题中所述的要求：
比上述或其他需要频繁quote-ing 和eval-ing 的方法更简单、更优雅、更短或更容易设计、实现或理解。
虽然与其他编程语言相比，base R 提供了非常有用的工具来处理这些问题。
您已经找到了使用get, mget, DT[[col_name]], parse, quote, 的建议eval。
- 正如您所提到的，优化
DT[[col_name]]可能无法很好地发挥作用data.table，因此在这里不是很有用。
parse可能是构建复杂查询的最简单方法，因为您可以对字符串进行操作，但它不提供基本的语言语法验证。因此，您最终可能会尝试解析 R 解析器不接受的字符串。此外，还有一个安全问题，如2655#issuecomment-376781159 所示。get/mget是处理此类问题最常用的方法。get并mget在内部被捕获[.data.table并转换为预期的列。因此，您假设您的任意复杂查询将能够被[.data.table正确输入的预期列分解。- 自从您几年前问过这个问题以来，最近推出了新功能 -点点前缀。您使用点-点为变量名称添加前缀以引用当前 data.table 范围之外的变量。与您在文件系统中引用父目录类似。dot-dot 后面的内部结构将与 非常相似，具有前缀的
get变量将在. . 在未来的版本中，点-点前缀可能允许如下调用：[.data.table
col1="a"; col2="b"; col3="g"; col4="x"; col5="y"
DT[..col4==..col5, .(s1=sum(..col1), s2=sum(..col2)), by=..col3]
转到示例。下面我将展示两种解决方法。第一个将使用基本 R 元编程，第二个将使用PR#4304中提出的 data.table 元编程（见上文）。
我会将所有逻辑包装到do_vars函数中。调用do_vars(donot=TRUE)将打印要计算的表达式data.table而不是eval它们。下面的代码应该在 OP 代码之后运行。
expected = copy(new.table)
new.table = the.table[, list(asofdate=seq(from=ymd((year)*10^4+101), length.out=12, by="1 month")), by=year]
do_vars = function(x, y, vars, donot=FALSE) {
name.suffix = function(x, suffix) as.name(paste(x, suffix, sep="."))
do_var = function(var, x, y) {
substitute({
x[, .anntot := y[, rep(.var, each=12)]]
x[, .monthly := y[, rep(.var/12, each=12)]]
x[, .rolling := rollapply(.monthly, mean, width=12, fill=c(head(.monthly,1), tail(.monthly,1)))]
x[, .scaled := .anntot/sum(.rolling)*.rolling, by=year]
}, list(
.var=as.name(var),
.anntot=name.suffix(var, "annual.total"),
.monthly=name.suffix(var, "monthly"),
.rolling=name.suffix(var, "rolling"),
.scaled=name.suffix(var, "scaled")
))
}
ql = lapply(setNames(nm=vars), do_var, x, y)
if (donot) return(ql)
lapply(ql, eval.parent)
invisible(x)
}
do_vars(new.table, the.table, c("var1","var2","var3"))
all.equal(expected, new.table)
#[1] TRUE
我们可以预览查询
do_vars(new.table, the.table, c("var1","var2","var3"), donot=TRUE)
#$var1
#{
# x[, `:=`(var1.annual.total, y[, rep(var1, each = 12)])]
# x[, `:=`(var1.monthly, y[, rep(var1/12, each = 12)])]
# x[, `:=`(var1.rolling, rollapply(var1.monthly, mean, width = 12,
# fill = c(head(var1.monthly, 1), tail(var1.monthly, 1))))]
# x[, `:=`(var1.scaled, var1.annual.total/sum(var1.rolling) *
# var1.rolling), by = year]
#}
#
#$var2
#{
# x[, `:=`(var2.annual.total, y[, rep(var2, each = 12)])]
# x[, `:=`(var2.monthly, y[, rep(var2/12, each = 12)])]
# x[, `:=`(var2.rolling, rollapply(var2.monthly, mean, width = 12,
# fill = c(head(var2.monthly, 1), tail(var2.monthly, 1))))]
# x[, `:=`(var2.scaled, var2.annual.total/sum(var2.rolling) *
# var2.rolling), by = year]
#}
#
#$var3
#{
# x[, `:=`(var3.annual.total, y[, rep(var3, each = 12)])]
# x[, `:=`(var3.monthly, y[, rep(var3/12, each = 12)])]
# x[, `:=`(var3.rolling, rollapply(var3.monthly, mean, width = 12,
# fill = c(head(var3.monthly, 1), tail(var3.monthly, 1))))]
# x[, `:=`(var3.scaled, var3.annual.total/sum(var3.rolling) *
# var3.rolling), by = year]
#}
#
expected = copy(new.table)
new.table = the.table[, list(asofdate=seq(from=ymd((year)*10^4+101), length.out=12, by="1 month")), by=year]
name.suffix = function(x, suffix) as.name(paste(x, suffix, sep="."))
do_var2 = function(var, x, y) {
x[, .anntot := y[, rep(.var, each=12)],
env = list(
.anntot = name.suffix(var, "annual.total"),
.var = var
)]
x[, .monthly := y[, rep(.var/12, each=12)],
env = list(
.monthly = name.suffix(var, "monthly"),
.var = var
)]
x[, .rolling := rollapply(.monthly, mean, width=12, fill=c(head(.monthly,1), tail(.monthly,1))),
env = list(
.rolling = name.suffix(var, "rolling"),
.monthly = name.suffix(var, "monthly")
)]
x[, .scaled := .anntot/sum(.rolling)*.rolling, by=year,
env = list(
.scaled = name.suffix(var, "scaled"),
.anntot = name.suffix(var, "annual.total"),
.rolling = name.suffix(var, "rolling")
)]
TRUE
}
sapply(setNames(nm=var.names), do_var2, new.table, the.table)
#var1 var2 var3
#TRUE TRUE TRUE
all.equal(expected, new.table)
#[1] TRUE
数据和更新的 OP 代码
library(data.table)
library(lubridate)
library(zoo)
the.table <- data.table(year=1991:1996,var1=floor(runif(6,400,1400)))
the.table[,`:=`(var2=var1/floor(runif(6,2,5)),
var3=var1/floor(runif(6,2,5)))]
# Replicate data across months
new.table <- the.table[, list(asofdate=seq(from=ymd((year)*10^4+101),
length.out=12,
by="1 month")),by=year]
# Do a complicated procedure to each variable in some group.
var.names <- c("var1","var2","var3")
for(varname in var.names) {
#As suggested in an answer to Link 3 above
#Convert the column name to a 'quote' object
quote.convert <- function(x) eval(parse(text=paste0('quote(',x,')')))
#Do this for every column name I'll need
varname <- quote.convert(varname)
anntot <- quote.convert(paste0(varname,".annual.total"))
monthly <- quote.convert(paste0(varname,".monthly"))
rolling <- quote.convert(paste0(varname,".rolling"))
scaled <- quote.convert(paste0(varname,".scaled"))
#Perform the relevant tasks, using eval()
#around every variable columnname I may want
new.table[,paste0(varname,".annual.total"):=
the.table[,rep(eval(varname),each=12)]]
new.table[,paste0(varname,".monthly"):=
the.table[,rep(eval(varname)/12,each=12)]]
new.table[,paste0(varname,".rolling"):=
rollapply(eval(monthly),mean,width=12,
fill=c(head(eval(monthly),1),
tail(eval(monthly),1)))]
new.table[,paste0(varname,".scaled"):=
eval(anntot)/sum(eval(rolling))*eval(rolling),
by=year]
}