r - 如何使用 ddply 以编程方式汇总多列？

Question

是否可以从函数的参数中指定使用 ddply 聚合哪些列，而不使用 eval + parse？这是我到目前为止所拥有的:

x <- c(2,4,3,1,5,7)
y <- c(3,2,6,3,4,6)
group1 <- c("A","A","A","A","B","B")
group2 <- c("X","X","Y","Y","Z","X")

data <- data.frame(group1, group2, x, y)

这就是我想要的输出:

aggFunction <- function(dataframe, toAverage, toGroup) {
  out <- ddply(dataframe, toGroup, summarise, 
               x = mean(x),
               y = mean(y))
  return(out)
}

aggFunction(data, c("x", "y"), c("group1", "group2"))

# group1 group2 x   y
# 1      A      X 3 2.5
# 2      A      Y 2 4.5
# 3      B      X 7 6.0
# 4      B      Z 5 4.0

这是我使用 parse(eval) 的解决方案:

aggFunction <- function(dataframe, toAverage, toGroup) {

  toAverageArgs <- paste(toAverage, " = mean(", toAverage, ")", sep = "", collapse = ", ")
  out <- eval(parse(text = paste("ddply(dataframe, toGroup, here(summarize),", toAverageArgs, ")")))

  return(out)
}

这给了我我想要的输出。

我想知道是否有更好的方法来做到这一点。我知道使用 do.call() 和 get()，但我对这些的尝试都没有成功。

这是一次尝试；get(string) 不起作用，但这里(总结)让我获取字符串值。不幸的是，这意味着 ddply 将它们视为字符串:

aggFunction <- function(dataframe, toAverage, toGroup) {

  string <- paste(toAverage, " = mean(", toAverage, ")", sep = "", collapse = ", ")
  out <- ddply(dataframe, toGroup, here(summarise), string)

  return(out)
}

aggFunction(data, c("x", "y"), c("group1", "group2"))

# group1 group2                      ..2
# 1      A      X x = mean(x), y = mean(y)
# 2      A      Y x = mean(x), y = mean(y)
# 3      B      X x = mean(x), y = mean(y)
# 4      B      Z x = mean(x), y = mean(y)

也尝试过 do.call，但它们仍然被视为字符串:

aggFunction <- function(dataframe, toAverage, toGroup) {

  string <- paste(toAverage, " = mean(", toAverage, ")", sep = "", collapse = ", ")
  print(string)

  args <- list(dataframe, toGroup, here(summarise), string)
  out <- do.call(ddply, args)

  return(out)
}
aggFunction(data, c("x", "y"), c("group1", "group2"))

# group1 group2 "x = mean(x), y = mean(y)"
# 1      A      X   x = mean(x), y = mean(y)
# 2      A      Y   x = mean(x), y = mean(y)
# 3      B      X   x = mean(x), y = mean(y)
# 4      B      Z   x = mean(x), y = mean(y)

最后我尝试在mean()中进行硬编码，但后来我无法设置列名称。如果我使用 get(testVar) = Mean(get(testVar)) 我会得到意外的=。

aggFunction <- function(dataframe, toAverage, toGroup) {

  testVar <- "x"

  out <- ddply(dataframe, toGroup, here(summarise), 
           get(testVar) = mean(get(testVar))
           ## 
  return(out)
}

Answer 1

在基础 R 中使用聚合

aggFunction <- function(dataframe, toAverage, toGroup) {
  aggregate(dataframe[, toAverage], dataframe[, toGroup], mean)
}

aggFunction(data, c("x", "y"), c("group1", "group2"))

   group1 group2 x   y
1      A      X 3 2.5
2      B      X 7 6.0
3      A      Y 2 4.5
4      B      Z 5 4.0