mrdwab

stratified = function(df, group, size) {
  #  USE: * Specify your data frame and grouping variable (as column 
  #         number) as the first two 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.
  #
  #  Example 1: Sample 10% of each group from a data frame named "z",
  #             where the grouping variable is the fourth variable, use:
  # 

mrdwab

###############################################################################
#                           Sample Size  and Confidence Interval Calculation  #
#                           v 1.3 by "Ananda Mahto"/mrdwab/[email protected]  #
#  2011 May 17                                                                #
# --------------------------------------------------------------------------- #
#                                                                             #
#  Example usage:                                                             #
#    * sample.size.table(c.lev = c(90, 95, 98, 99), population = 378)         #
#    * sample.size(c.lev = 98, population = 200)                              #
#    * confidence.interval(c.lev = 95, p.ss = 80, population = 100)           #

mrdwab

read.tps = function(data) {
  # Reads the .tps file format produced by TPSDIG 
  # (http://life.bio.sunysb.edu/morph/ into a single data frame
  # USAGE: R> read.tps("filename.tps")
  a = readLines(data) # so we can do some searching and indexing
  LM = grep("LM", a) # find the line numbers for LM
  ID.ind = grep("ID", a) # find the line numbers for ID
  # and the ID values, SCALE values, and image names
  ID = gsub("(ID=)(.*)", "\\2", grep("ID", a, value=T)) 
  SCALE = gsub("(SCALE=)(.*)", "\\2", grep("SCALE", a, value=T)) 

mrdwab

write.Hmisc.SPSS = function(data, datafile, codefile) {
# EXAMPLE DATA (see: http://stackoverflow.com/q/10181730/1270695)
# df <- data.frame(id = c(1:6), 
#                  p.code = c(1, 5, 4, NA, 0, 5),  
#                  p.label = c('Optometrists', 'Nurses', 
#                              'Financial analysts', '<NA>', 
#                              '0', 'Nurses'), 
#                  foo = LETTERS[1:6])
# Add some variable labels using label from the Hmisc package
# require(Hmisc)

mrdwab

df.sorter = function(data, var.order=names(data), col.sort=NULL ) {
  # Sorts a data.frame by columns or rows or both.
  # Can refer to variables either by names or number.
  # If referring to variable by number, and sorting both the order
  # of variables and the sorting within variables, refer to the
  # variable numbers of the final data.frame
  #
  # === EXAMPLES ===
  #
  #    library(foreign)

mrdwab

concat.split = function(data, split.col, mode=NULL, 
                        sep=",", drop.col=FALSE) {
  # Takes a column with multiple values, splits the values into 
  #   separate columns, and returns a new data.frame.
  # 'data' is the source data.frame; 'split.col' is the variable that 
  #   needs to be split; 'mode' can be either 'binary' or 'value' 
  #   (where 'binary' is default and it recodes values to 1 or NA);
  #   'sep' is the character separating each value (defaults to ','); 
  #   and 'drop.col' is logical (whether to remove the original 
  #   variable from the output or not.

mrdwab

LinearizeNestedList <- function(NList, LinearizeDataFrames=FALSE,
                                NameSep="/", ForceNames=FALSE) {
    # LinearizeNestedList:
    #
    # https://sites.google.com/site/akhilsbehl/geekspace/
    #         articles/r/linearize_nested_lists_in_r
    #
    # Akhil S Bhel
    # 
    # Implements a recursive algorithm to linearize nested lists upto any

mrdwab

## @knitr tdasample

TDASample <- function(inString, N, n, toFile = FALSE) {
    if (is.factor(inString)) inString <- as.character(inString)    
    if (nchar(inString) <= 3) stop("inString must be > 3 characters")
    string1 <- "jnt3g127rbfeqixkos 586d90pyal4chzmvwu"
    string2 <- "2dyn0uxq ovalrpksieb3fhjw584cm9t7z16g"
    instring <- chartr(string1, string2, tolower(inString))
    t1 <- sd(c(suppressWarnings(sapply(strsplit(instring, ""),
                                       as.numeric))), na.rm = TRUE)

mrdwab

cut2 <- function (x, breaks, labels = NULL, include.lowest = FALSE, right = TRUE, 
          dig.lab = 3, ordered_result = FALSE, ...) 
{
  if (!is.numeric(x)) 
    stop("'x' must be numeric")
  if (length(breaks) == 1L) {
    if (is.na(breaks) || breaks < 2L) 
      stop("invalid number of intervals")
    nb <- as.integer(breaks + 1)
    dx <- diff(rx <- range(x, na.rm = TRUE))

mrdwab

MERGE <- function (x, y, by = intersect(names(x), names(y)), by.x = by, 
    by.y = by, all = FALSE, all.x = all, all.y = all, sort = TRUE, 
    suffixes = c(".x", ".y"), incomparables = NULL, ...) 
{
    fix.by <- function(by, df) {
        if (is.null(by)) 
            by <- numeric()
        by <- as.vector(by)
        nc <- ncol(df)
        if (is.character(by)) {