ggplot2内部功能具有第二种美感：作用域问题

Question

I have the following test data:

structure(list(r = c(5.44702625911984, 6.3431860464319, 2.89023592667928, 
6.66260769449341, 7.5521021076857, 5.50645078944005, 6.70001850525037, 
7.39615449137166, 5.96032231142622, 7.88929821115731, 9.45119299499902, 
6.13534105776075, 7.79397401855071, 5.24488870603935, 4.53178061905952, 
5.80573244536445, 10.1194252475799, 12.5794215385996, 7.47503723957468, 
7.8682648760597, 15.7540766770233, 14.9800818974568, 14.5672865569748, 
9.5347507057429, 18.6791666362954, 10.4588651710497, 15.2076130678251, 
10.5052588219606, 13.1314628288852, 12.8384811800557, 10.9978569438483, 
10.0197995395016, 10.1479274794689, 12.5864754383382, 10.7985399338233, 
11.1100572430765, 10.756576992292, 9.17309427876051, 10.0441987112265, 
10.0652520950654), f1 = structure(c(2L, 2L, 2L, 2L, 2L, 2L, 2L, 
2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 1L, 1L, 1L, 
1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 
1L), .Label = c("H", "L"), class = "factor"), f2 = structure(c(1L, 
1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 
2L, 2L, 2L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 2L, 2L, 2L, 
2L, 2L, 2L, 2L, 2L, 2L, 2L), class = "factor", .Label = c("Joe", 
"Sally"))), .Names = c("r", "f1", "f2"), row.names = c(NA, -40L
), class = "data.frame")

And the following function which should draw the points (it does) and connect the means of each group (it doesn't):

testFunc <- function(formula = NULL, data = NULL) {
    res <- as.character(formula[[2]])
    fac1 <- as.character(formula[[3]][2])
    fac2 <- as.character(formula[[3]][3])

    # Specify the data & aesthetics     
    p <- ggplot(data, aes_string(x = fac1, y = res, color = fac2,
        group = fac2))

    # Now add points
    p <- p + geom_point() # works fine if we stop here

    # Due to a bug in ggplot2_0.9.3, we must calc some quantities
    # and put them in a separate data frame for a new aesthetic
    avg <- aggregate(data[,res] ~ data[,fac1]*data[, fac2], data, FUN = mean)
    names(avg) <- c("factor1", "factor2", "mean")   
    p <- p + geom_line(aes_string(x = 'factor1', y = 'mean', group = 'factor2'), data = avg)
    }

When I run it:

ex <- testFunc(formula = r ~ f1*f2, data = td)
print(ex)

I get this error:

Error in eval(expr, envir, enclos) : object 'f2' not found

I seem to always have these scoping problems, any advice? I thought I was following the appropriate work-around for the bug. Using aes instead of aes_string , or not quoting the variable names in geom_line doesn't fix it. Thanks.

Answer 1

When I run into trouble with inherited aesthetics, I always go back and remove anything from the main ggplot() call that doesn't need to be there. Try this:

testFunc <- function(formula = NULL, data = NULL) {
    res <- as.character(formula[[2]])
    fac1 <- as.character(formula[[3]][2])
    fac2 <- as.character(formula[[3]][3])

    # Now add points
    p <- ggplot() + geom_point(data = data, aes_string(x = fac1, y = res, color = fac2,
        group = fac2)) # works fine if we stop here

    # Due to a bug in ggplot2_0.9.3, we must calc some quantities
    # and put them in a separate data frame for a new aesthetic
    avg <- aggregate(data[,res] ~ data[,fac1]*data[, fac2], data, FUN = mean)
    names(avg) <- c("factor1", "factor2", "mean")   
    p <- p + geom_line(aes_string(x = 'factor1', y = 'mean', group = 'factor2'), data = avg)
    }

Answer 2

I had to make two changes to get your function to work. First, there's a bug in ggplot2 0.9.3 (and previous) where the evaluation environment of aes() defaults to the global environment. The workaround: to make it evaluate in the calling environment (for example, your function's environment) use ggplot(..., environment = environment() .

The other change was in the last line, where you have p <- p + geom_line(..., data=avg) . The key there is that you must turn off the inheritance of aesthetics from the main ggplot call, because your avg data set doesn't have the fac2 column. To do that, use geom_line(..., inherit.aes=FALSE) .

testFunc <- function(formula = NULL, data = NULL) {
  res <- as.character(formula[[2]])
  fac1 <- as.character(formula[[3]][2])
  fac2 <- as.character(formula[[3]][3])

  # Specify the data & aesthetics     
  p <- ggplot(data, aes_string(x = fac1, y = res, color = fac2, group = fac2),
    environment = environment())

  # Now add points
  p <- p + geom_point()

  # Due to a bug in ggplot2_0.9.3, we must calc some quantities
  # and put them in a separate data frame for a new aesthetic
  avg <- aggregate(data[,res] ~ data[,fac1]*data[, fac2], data, FUN = mean)
  names(avg) <- c("factor1", "factor2", "mean")   
  p + geom_line(aes_string(x = 'factor1', y = 'mean', group = 'factor2'), 
    inherit.aes = FALSE, data = avg)
}

ex <- testFunc(formula = r ~ f1*f2, data = td)
print(ex)