为分层抽样准备抽样分布的最佳R包函数

我正试图准备一个R中的演示，演示如何对一小部分人群进行重复分层随机抽样，从而得出均值的近似正态抽样分布。作为一个例子，考虑下面的R代码（它工作，但由于循环）非常慢。

#由掷骰子组成的虚拟群体-每行18次
#~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
P1离开这个问题一段时间后，我发现了一个名为“fifer”（fifer）的包，它似乎在包中包含分层函数，但不幸的是，这个包在最新版本的R上不起作用。然而，我从Ananda Mahto（）中找到了一个聪明的分层函数这很好，但代价是脚本中有一个相当长的函数，而不是加载一行程序包。下面是我使用此函数解决上述问题的方法

#Dummy population made up of dice throws - 18 per row
#~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
P1 <- as.data.frame(c(5,6,5,1,6,4,2,2,4,4,6,6,5,2,3,5,1,6))
P1$Zn <- 1
names(P1) <- c('Die','Zn')
Dt <- P1

P2 <- as.data.frame(c(2,5,4,5,5,5,3,3,2,5,6,1,2,5,4,3,6,1))
P2$Zn <- 2
names(P2) <- c('Die','Zn')
Dt <- rbind(Dt,P2)

#~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
# Stratfed function from web
# https://gist.github.com/mrdwab/6424112
#~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~

stratified <- function(df, group, size, select = NULL, 
                       replace = FALSE, bothSets = FALSE) {
  if (is.null(select)) {
    df <- df
  } else {
    if (is.null(names(select))) stop("'select' must be a named list")
    if (!all(names(select) %in% names(df)))
      stop("Please verify your 'select' argument")
    temp <- sapply(names(select),
                   function(x) df[[x]] %in% select[[x]])
    df <- df[rowSums(temp) == length(select), ]
  }
  df.interaction <- interaction(df[group], drop = TRUE)
  df.table <- table(df.interaction)
  df.split <- split(df, df.interaction)
  if (length(size) > 1) {
    if (length(size) != length(df.split))
      stop("Number of groups is ", length(df.split),
           " but number of sizes supplied is ", length(size))
    if (is.null(names(size))) {
      n <- setNames(size, names(df.split))
      message(sQuote("size"), " vector entered as:\n\nsize = structure(c(",
              paste(n, collapse = ", "), "),\n.Names = c(",
              paste(shQuote(names(n)), collapse = ", "), ")) \n\n")
    } else {
      ifelse(all(names(size) %in% names(df.split)),
             n <- size[names(df.split)],
             stop("Named vector supplied with names ",
                  paste(names(size), collapse = ", "),
                  "\n but the names for the group levels are ",
                  paste(names(df.split), collapse = ", ")))
    }
  } else if (size < 1) {
    n <- round(df.table * size, digits = 0)
  } else if (size >= 1) {
    if (all(df.table >= size) || isTRUE(replace)) {
      n <- setNames(rep(size, length.out = length(df.split)),
                    names(df.split))
    } else {
      message(
        "Some groups\n---",
        paste(names(df.table[df.table < size]), collapse = ", "),
        "---\ncontain fewer observations",
        " than desired number of samples.\n",
        "All observations have been returned from those groups.")
      n <- c(sapply(df.table[df.table >= size], function(x) x = size),
             df.table[df.table < size])
    }
  }
  temp <- lapply(
    names(df.split),
    function(x) df.split[[x]][sample(df.table[x],
                                     n[x], replace = replace), ])
  set1 <- do.call("rbind", temp)

  if (isTRUE(bothSets)) {
    set2 <- df[!rownames(df) %in% rownames(set1), ]
    list(SET1 = set1, SET2 = set2)
  } else {
    set1
  }
}


# Empty dataframe to hold random draws
#~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
Smps <- data.frame(Die = numeric(), Zn = numeric())

# Right function for reporting progress
#~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
right = function(text, num_char) {
  substr(text, nchar(text) - (num_char-1), nchar(text))
}

# Draw stratifed samples one from each row
#~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
n <- 10000          # number of draws
for (j in 1:n){
    y <- stratified(Dt,"Zn",1)
    y <- cbind(y,j)
    Smps <- rbind(Smps,y)
  # report progress
  if(right(j,3) == '000'){
    print(paste(j,'at',Sys.time()))
    flush.console()
  }
}

# Compute the sample means
#~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
Mns <-aggregate(Smps[, 1], list(Smps$j), mean)

# Density plot of means
#~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
d <- density(Mns$x)
plot(d,xlab = 'Means', las=1, main = '')
polygon(d, col="blue", border="blue")

#由掷骰子组成的虚拟群体-每行18次
#~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
P1
#Dummy population made up of dice throws - 18 per row
#~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
P1 <- as.data.frame(c(5,6,5,1,6,4,2,2,4,4,6,6,5,2,3,5,1,6))
P1$Zn <- 1
names(P1) <- c('Die','Zn')
Dt <- P1

P2 <- as.data.frame(c(2,5,4,5,5,5,3,3,2,5,6,1,2,5,4,3,6,1))
P2$Zn <- 2
names(P2) <- c('Die','Zn')
Dt <- rbind(Dt,P2)

#~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
# Stratfed function from web
# https://gist.github.com/mrdwab/6424112
#~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~

stratified <- function(df, group, size, select = NULL, 
                       replace = FALSE, bothSets = FALSE) {
  if (is.null(select)) {
    df <- df
  } else {
    if (is.null(names(select))) stop("'select' must be a named list")
    if (!all(names(select) %in% names(df)))
      stop("Please verify your 'select' argument")
    temp <- sapply(names(select),
                   function(x) df[[x]] %in% select[[x]])
    df <- df[rowSums(temp) == length(select), ]
  }
  df.interaction <- interaction(df[group], drop = TRUE)
  df.table <- table(df.interaction)
  df.split <- split(df, df.interaction)
  if (length(size) > 1) {
    if (length(size) != length(df.split))
      stop("Number of groups is ", length(df.split),
           " but number of sizes supplied is ", length(size))
    if (is.null(names(size))) {
      n <- setNames(size, names(df.split))
      message(sQuote("size"), " vector entered as:\n\nsize = structure(c(",
              paste(n, collapse = ", "), "),\n.Names = c(",
              paste(shQuote(names(n)), collapse = ", "), ")) \n\n")
    } else {
      ifelse(all(names(size) %in% names(df.split)),
             n <- size[names(df.split)],
             stop("Named vector supplied with names ",
                  paste(names(size), collapse = ", "),
                  "\n but the names for the group levels are ",
                  paste(names(df.split), collapse = ", ")))
    }
  } else if (size < 1) {
    n <- round(df.table * size, digits = 0)
  } else if (size >= 1) {
    if (all(df.table >= size) || isTRUE(replace)) {
      n <- setNames(rep(size, length.out = length(df.split)),
                    names(df.split))
    } else {
      message(
        "Some groups\n---",
        paste(names(df.table[df.table < size]), collapse = ", "),
        "---\ncontain fewer observations",
        " than desired number of samples.\n",
        "All observations have been returned from those groups.")
      n <- c(sapply(df.table[df.table >= size], function(x) x = size),
             df.table[df.table < size])
    }
  }
  temp <- lapply(
    names(df.split),
    function(x) df.split[[x]][sample(df.table[x],
                                     n[x], replace = replace), ])
  set1 <- do.call("rbind", temp)

  if (isTRUE(bothSets)) {
    set2 <- df[!rownames(df) %in% rownames(set1), ]
    list(SET1 = set1, SET2 = set2)
  } else {
    set1
  }
}


# Empty dataframe to hold random draws
#~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
Smps <- data.frame(Die = numeric(), Zn = numeric())

# Right function for reporting progress
#~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
right = function(text, num_char) {
  substr(text, nchar(text) - (num_char-1), nchar(text))
}

# Draw stratifed samples one from each row
#~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
n <- 10000          # number of draws
for (j in 1:n){
    y <- stratified(Dt,"Zn",1)
    y <- cbind(y,j)
    Smps <- rbind(Smps,y)
  # report progress
  if(right(j,3) == '000'){
    print(paste(j,'at',Sys.time()))
    flush.console()
  }
}

# Compute the sample means
#~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
Mns <-aggregate(Smps[, 1], list(Smps$j), mean)

# Density plot of means
#~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
d <- density(Mns$x)
plot(d,xlab = 'Means', las=1, main = '')
polygon(d, col="blue", border="blue")