jeffwong

sudo aptitude install python3-setuptools
sudo apt-get install python3-dev libzmq3-dev libcurl4-openssl-dev

https://github.com/jupyter/jupyterhub.git
cd jupyterhub

sudo apt-get install npm nodejs-legacy
sudo npm install -g configurable-http-proxy

sudo easy_install3 pip

jeffwong

hashStrings = function(x) {
  sapply(x, function(i) {
    sprintf("hash_%s", paste0(charToRaw(i), collapse=""))
  })
}

unhashStrings = function(x) {
  sapply(x, function(i) {
    i = gsub("hash_", "", i)
    i.split = strsplit(i, "")[[1]]

jeffwong

write.libsvm = function(data, filename= "out.dat", class = 1) { 
  out = file(filename) 
  writeLines(apply(data, 1, function(X) paste(X[class],apply(cbind(which(X!=0)[-class], X[which(X!=0)[-class]]), 1, paste, collapse=":"), collapse=" ") ), out) 
  close(out) 
}

#' x should be a model matrix
#' y is a response vector
write.vw = function(data, outcomeName, weightName = '', classification=F, file = 'vw.txt') {
  

jeffwong

#Getting sigopt to run on Ubuntu

sudo apt-get install gcc-multilib
wget http://ftp.gnu.org/gnu/glpk/glpk-4.39.tar.gz
tar -xzf glpk-4.39.tar.gz 
cd glpk-4.39/
./configure
make
sudo make install
LD_LIBRARY_PATH=/usr/local/lib

jeffwong

wget http://09c8d0b2229f813c1b93-c95ac804525aac4b6dba79b00b39d1d3.r79.cf1.rackcdn.com/Anaconda-2.1.0-Linux-x86_64.sh
bash Anaconda-2.1.0-Linux-x86.sh

#http://thomassileo.com/blog/2012/11/19/setup-a-remote-ipython-notebook-server-with-numpyscipymaltplotlibpandas-in-a-virtualenv-on-ubuntu-server/

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

dbBuildTableDefinition.hive =
  function (databasename, tablename, df, field.types = NULL, s3path)
  {
    if (!is.data.frame(df))
      df <- as.data.frame(df)
    if (is.null(field.types)) {
      field.types <- lapply(df, hiveDataType)
    }
    flds <- paste(names(field.types), field.types)
    base = sprintf("CREATE EXTERNAL TABLE %s.%s

jeffwong

plotCoefs = function(model, nonzero = T, subset.condition, ...) {
  stopifnot(require(ggplot2))
  coefs = coef(model)[,1]
  coef.labels = attr(coefs, "names")
  
  isLogistic = model$name == "Binomial Deviance"
  if (isLogistic) coefs = exp(coefs)
  coefs.df = data.frame(label = coef.labels, value = coefs)
  coefs.df = coefs.df[order(coefs.df$value),]
  coefs.df$label = factor(coefs.df$label, levels = coefs.df$label)

jeffwong

sudo apt-get install libcurl4-openssl-dev

install.packages(c('RCurl', 'jsonlite'))

jeffwong

facetAdjust <- function(x, pos = c("up", "down"))
{
  pos <- match.arg(pos)
  p <- ggplot_build(x)
  gtable <- ggplot_gtable(p); dev.off()
  dims <- apply(p$panel$layout[2:3], 2, max)
  nrow <- dims[1]
  ncol <- dims[2]
  panels <- sum(grepl("panel", names(gtable$grobs)))
  space <- ncol * nrow