jeffwong

{
 "name": "flare",
 "children": [
  {
   "name": "analytics",
   "children": [
    {
     "name": "cluster",
     "children": [
      {"name": "AgglomerativeCluster", "size": 3938},

jeffwong

mybins = function(x, numbreaks, weights, ordered=T) {
  if (missing(weights)) x.w = x
  else x.w = rep(x, times=weights)
  breaks = quantile(x.w, seq(0,1,length.out=numbreaks+1))
  bins = findInterval(x, breaks, rightmost.closed=T)
  bins.f = factor(bins, levels = 1:numbreaks, ordered=ordered)
  list(breaks = breaks, bins = bins.f, numbreaks = numbreaks, ordered = ordered)
}

mybins.assign = function(bins, newx) {

jeffwong

# Multiple plot function
#
# ggplot objects can be passed in ..., or to plotlist (as a list of ggplot objects)
# - cols:   Number of columns in layout
# - layout: A matrix specifying the layout. If present, 'cols' is ignored.
#
# If the layout is something like matrix(c(1,2,3,3), nrow=2, byrow=TRUE),
# then plot 1 will go in the upper left, 2 will go in the upper right, and
# 3 will go all the way across the bottom.
#

jeffwong

strstrip = function(x) gsub("^\\s+|\\s+$", "", x)

jeffwong

isBinaryVariable = function(x) {
  apply(x, 2, function(j) {
    return (identical(range(unique(j)), c(0,1)))
  })
}

scaleBinary = function(j) {
  p = mean(j)
  j.sd = sqrt(p*(1-p))
  (j - p) / j.sd

jeffwong

myload = function(filename) {
  tryCatch({
    local({
      objects = load(filename)
      if (length(objects) == 1) return (get(objects))
      else return (lapply(sapply, get))
    })
  }, error = function(e) {cat("No such file")})
}

jeffwong

#!/bin/bash

if [ $# -lt 3 ] ;
then
    echo "Usage: $0 inputfile output_prefix lines_per_chunk [header=1]"
    exit
fi

header=1
if [ $# -eq 4 ] ;

jeffwong

require(data.table)

#Note that this permanently modifies test.data
hideNewLevels = function(train.data, test.data, replacement=NA, colnames.factor=NULL) {
  if(is.null(colnames.factor)) colnames.factor = extractFactors(test.data)
  for (col in colnames.factor) {
    levels.test = levels(test.data[,get(col)])
    levels.train = levels(train.data[,get(col)])

    badlevels.indices = which(!levels.test %in% levels.train)

jeffwong

.ls.objects <- function (pos = 1, pattern, head=FALSE, n=5) {
    napply <- function(names, fn) sapply(names, function(x)
                                         fn(get(x, pos = pos)))
    names <- ls(pos = pos, pattern = pattern)
    obj.class <- napply(names, function(x) as.character(class(x))[1])
    obj.mode <- napply(names, mode)
    obj.type <- ifelse(is.na(obj.class), obj.mode, obj.class)
    obj.size <- napply(names, object.size)
    obj.prettysize <- sapply(obj.size, function(r) prettyNum(r, big.mark = ",") )
    obj.dim <- t(napply(names, function(x)

jeffwong

bootstrapForecast = function(..., newxreglist=NULL, inv.transform=NULL, runs=1000, n.ahead=90, CI.level = .95) {
  models = list(...)
  nummodels = length(models)
  sims = vapply(1:runs, function(i) {
    sim = vapply(1:nummodels, function(j) {
      if (is.data.frame(newxreglist)) newxreg = newxreglist
      else newxreg = newxreglist[[j]]
      if (!is.null(inv.transform)) {
        if(is.list(inv.transform)) inv = inv.transform[[j]]
        else inv = inv.transform