dmarcelinobr

# These column numbers represent fields with name/contact info that I've 
# marked with 1s and 0s depending on whether or not there's anything in 
# the field.

bio_cols = c(5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,23,24,25,26)

# Now we get the row numbers of all the records with duplicate IDs

dupe_id_rows = which(duplicated(big.dataset$ID) == TRUE)

dmarcelinobr

if (!require("pacman")) install.packages("pacman")
pacman::p_load(dplyr, tidyr, wakefield)

set.seed(10)
dat <- r_data_frame(n = 10000,
        race,
        age,
	    sex
    )

dmarcelinobr

pander.CrossTable <- function(x, ...) {
 pandoc.table(x$t, caption = 'Observed Count')
 pandoc.table(x$prop.row, caption = 'Row percentages')
 pandoc.table(x$prop.col, caption = 'Column percentages')
  emphasize.strong.cells (which(x$chisq$residuals >  2,arr.ind=T))
  emphasize.strong.cells (which(x$chisq$residuals <  -2,arr.ind=T))
 pandoc.table(x$chisq$residuals, caption = 'Residuals of the Chi-sqaured test')

dmarcelinobr

coalesce<-function(...) {
    x<-lapply(list(...), function(z) {if (is.factor(z)) as.character(z) else z})
    m<-is.na(x[[1]])
    i<-2
    while(any(m) & i<=length(x)) {
        if ( length(x[[i]])==length(x[[1]])) {
            x[[1]][m]<-x[[i]][m]
        } else if (length(x[[i]])==1) {
            x[[1]][m]<-x[[i]]
        } else {

dmarcelinobr

# version 1.8.11 (commit 1048)
require(data.table)
# Loading required package: data.table
# data.table 1.8.11  For help type: help("data.table")

## create a huge data.table:
## -------------------------
set.seed(1)
N <- 2e7 # size of DT

dmarcelinobr

# http://stackoverflow.com/a/30781090/2725969


sample0110b <- function(size, n) {
  size <- as.integer(size)
  n <- as.integer(n)
  if(size > 25 || size < 3L) stop("Size out of valid range")

  # Generate integer pool and weights

dmarcelinobr

regcapturedmatches<-function(x,m) {
    
  if (length(x) != length(m))
    stop(gettextf("%s and %s must have the same length",
      sQuote("x"), sQuote("m")), domain = NA)

  ili <- is.list(m)
  useBytes <- if (ili) {
    any(unlist(lapply(m, attr, "useBytes")))
  } else {

dmarcelinobr

##############################################################################
# title         : InstallPackages.R;
# purpose       : install R packages commonly used by Adam H.Sparks when upgrading or installing R;
# producer      : prepared by A. H. Sparks;
# last update   : in Los Baños, Laguna, PHL, May 2015;
# inputs        : none;
# outputs       : none;
# remarks 1     : in order to download any packages, you need to be on-line, of course;
# remarks 2     : for country outlines and the like see http://www.gadm.org/ to download Rdata packages;
##############################################################################

dmarcelinobr

fingerprint <- function(x, y) {
  if (!inherits(x, "character") | !inherits(y, "character")) {
    stop("x and y must be character strings")
  }
  
  x1 <- strsplit(x, "")[[1]]
  y1 <- strsplit(y, "")[[1]]
  f <- c(x1, y1)
  final <- paste(f[order(f)], collapse = "")
  return(final)

dmarcelinobr

library(Rserve)
library(data.table)

port = 9411:9414 # we have 4 ports designed to run cluster, so up to 4 nodes
dt = data.table(time_year = 2012:2014) # simulate input data from which we dynamically derive partitions by year
partitioning = quote(time_year)
partitions = dt[,unique(eval(as.name(partitioning)))] # extract all partitions from reference dataset
names(partitions) = partitions
port = port[seq_along(partitions)]
names(port) = as.character(partitions)