Stratified random sampling in R from a data frame

stratified = function(df, id, group, size, seed="NULL", ...) {
  #  USE: * Specify your data frame, ID variable (as column number), and
  #         grouping variable (as column number) as the first three arguments.
  #       * Decide on your sample size. For a sample proportional to the
  #         population, enter "size" as a decimal. For an equal number of
  #         samples from each group, enter "size" as a whole number.
  #       * Decide on if you want to use a seed or not. If not, leave blank
  #         or type "NULL" (with quotes). 
  #
  #  Example 1: To sample 10% of each group from a data frame named "z", where
  #             the ID variable is the first variable, the grouping variable
  #             is the fourth variable, and the desired seed is "1", use:
  # 
  #                 > stratified(z, 1, 4, .1, 1)
  #
  #  Example 2: To run the same sample as above but without a seed, use:
  # 
  #                 > stratified(z, 1, 4, .1)
  #
  #  Example 3: To sample 5 from each group from a data frame named "z", where
  #             the ID variable is the first variable, the grouping variable
  #             is the third variable, and the desired seed is 2, use:
  #
  #                 > stratified(z, 1, 3, 5, 2)
  #
  #  NOTE: Not tested on datasets with LOTS of groups or with HUGE
  #        differences in group sizes. Probably INCREDIBLY inefficient.
 
  k = unstack(data.frame(as.vector(df[id]), as.vector(df[group])))
  l = length(k)
  results = vector("list", l)
 
  if (seed == "NULL" & size < 1) {
      for (i in 1:length(k)) {
        N = k[[i]]
        n = round(length(N)*size)
        results[[i]] = list(sample(N, n, ...))
      }
    } else if (seed == "NULL" & size >= 1) {
      for (i in 1:length(k)) {
        N = k[[i]]
        results[[i]] = list(sample(N, size, ...))
      }
    } else if (size < 1) {
      for (i in 1:length(k)) {
        set.seed(seed)
        N = k[[i]]
        n = round(length(N)*size)
        results[[i]] = list(sample(N, n, ...))
      }
    } else if (size >= 1) {
      for (i in 1:length(k)) {
        set.seed(seed)
        N = k[[i]]
        results[[i]] = list(sample(N, size, ...))
      }
    }
  z = data.frame(c(unlist(results)))
  names(z) = names(df[id])
  w = merge(df, z)
  w[order(w[group]), ]
}

> source("http://news.mrdwab.com/stratified")
> # Make up some data
> A = 1:100
> B = sample(c("AA", "BB", "CC", "DD", "EE"), 100, replace=T)
> C = rnorm(100)
> D = abs(round(rnorm(100), digits=1))
> E = sample(c("CA", "NY", "TX"), 100, replace=T)
> dat = data.frame(A, B, C, D, E)
> # view the first few rows
> head(dat)
  A  B           C   D  E
1 1 CC -0.07870439 0.6 NY
2 2 CC -0.65048634 0.3 TX
3 3 EE  1.02703616 1.3 NY
4 4 BB -1.08696775 0.4 TX
5 5 CC  0.56741795 0.2 CA
6 6 AA -0.46448941 0.5 TX
> # Sample 10% from each group from variable B, no seed
> stratified(dat, 1, 2, .1)
    A  B           C   D  E
2   6 AA -0.46448941 0.5 TX
7  71 AA  1.98128479 2.1 CA
5  53 BB  1.00539398 0.7 NY
10 97 BB  0.68252675 1.9 NY
1   1 CC -0.07870439 0.6 NY
4  42 CC -2.00256854 0.3 TX
8  76 DD -0.84151459 0.2 NY
9  95 DD -0.47276142 0.3 CA
11 99 DD  1.05173419 2.1 TX
3  10 EE -0.69079473 1.1 TX
6  57 EE -0.38210921 1.5 CA
> # Sample 10% from each group from variable E, seed of 1
> stratified(dat, 1, 5, .1, 1)
    A  B          C   D  E
4  33 AA  1.6105099 0.5 CA
7  48 AA  0.3128274 0.6 CA
9  62 DD  0.4673061 0.0 CA
10 86 EE  0.4047880 1.6 CA
3  28 AA -1.6815553 0.3 NY
5  36 AA  0.3307508 0.3 NY
8  53 BB  1.0053940 0.7 NY
1  21 DD  0.5229282 1.2 TX
2  27 BB  0.8678977 0.7 TX
6  44 DD -0.5790353 0.9 TX
> # You can also be verbose if it helps you remember what you're doing
> stratified(df=dat, id=1, group=5, size=.1, seed=1)
    A  B          C   D  E
4  33 AA  1.6105099 0.5 CA
7  48 AA  0.3128274 0.6 CA
9  62 DD  0.4673061 0.0 CA
10 86 EE  0.4047880 1.6 CA
3  28 AA -1.6815553 0.3 NY
5  36 AA  0.3307508 0.3 NY
8  53 BB  1.0053940 0.7 NY
1  21 DD  0.5229282 1.2 TX
2  27 BB  0.8678977 0.7 TX
6  44 DD -0.5790353 0.9 TX