benjamin-chan

packages <- c("devtools",
              "data.table",
              "lubridate",
              "ggplot2",
              "haven",
              "readxl",
              "tidyr",
              "lme4",
              "metafor",
              "DiagrammeR",

benjamin-chan

install.packages("devtools")
library("devtools")
devtools::install_github("klutometis/roxygen")
library(roxygen2)

setwd("C:/Users/chanb/Documents/GitHub Repositories")
create("prepR")

setwd("./prepR")
document()

benjamin-chan

checkPackage <- function (pkg) {
  # Check if pkg is installed; if not then install it; if an update exists then update
  # Usage:
  # > checkPackage("data.table")
  if (is.character(pkg) == TRUE) {
    repos <- "https://cloud.r-project.org"
    if(pkg %in% rownames(installed.packages()) == FALSE) {
      install.packages(pkg, repos=repos, dependencies=TRUE)
      rowid <- which(installed.packages()[, "Package"] == pkg)
      pkgInfo <- installed.packages()[rowid, ]

benjamin-chan

#Install in order to use RCurl & XML
sudo aptitude install libcurl4-openssl-dev
sudo apt-get install libxml2-dev

benjamin-chan

#Create a user, home directory and set password
sudo useradd rstudio
sudo mkdir /home/rstudio
sudo passwd rstudio
sudo chmod -R 0777 /home/rstudio

#Update all files from the default state
sudo apt-get update
sudo apt-get upgrade

benjamin-chan

What

Roll your own iPython Notebook server with Amazon Web Services (EC2) using their Free Tier.

What are we using? What do you need?

• An active AWS account. First time sign-ups are eligible for the free tier for a year
• One Micro Tier EC2 Instance
• With AWS we will use the stock Ubuntu Server AMI and customize it.
• Anaconda for Python.
• Coffee/Beer/Time

benjamin-chan

################################################################################
#
# R.nanorc -- nano syntax-highlighting file for R
#
# Origin: This file is part of the pkgutils package for R.
#
# Usage: This file should be placed in a directory such as /usr/share/nano/ (on
#   Ubuntu 12.04). That nano uses syntax highlighting at all might need to be
#   enabled separately.

benjamin-chan

body, td {
   font-family: 'Lato', sans-serif;
   background-color: white;
   font-size: medium;
   margin: 8px;
}

tt, code, pre {
   font-family: Consolas, Monaco, monospace;
}

benjamin-chan

Parallel GLM tuning

Benjamin Chan
r Sys.time()

Clear the workspace environment and load packages.

rm(list=ls())
gc()

benjamin-chan

library(data.table)
nBins <- 25
breaks <- seq(0, 1, length.out=nBins+1)
midpoints <- breaks[1:nBins] + (breaks[2:(nBins+1)] - breaks[1:nBins]) / 2
D <- data.table(x = runif(1e4))
D <- D[, xBinned := cut(x, breaks=breaks, labels=sprintf("%.2f", midpoints))]
D <- D[,
       .(.N,
         label=as.character(xBinned),
         min = min(x),