CerebralMastication

rm(list = ls())
nchooser <- function(n, r) {
 if (n == r) {
	 #cat("called nchooser(n = r)\n")
	 return(1)
 } else if (r == 0) {
	 #cat("called nchooser(r = 0)\n")
	 return(1)
 } else 
   #cat("called nchooser(", n", " r ") \n")

CerebralMastication

sampleSize <- 1e6
bigDF <- data.frame(letter1=I(sample(letters, sampleSize, rep=T)), 
                    letter2=I(sample(letters, sampleSize, rep=T)),
                    b=rnorm(sampleSize),
                    c=rnorm(sampleSize))
require(sqldf)
system.time(sqldf("select letter1, letter2, avg(b) as b, avg(c) as c from bigDF group by letter1, letter2"))

CerebralMastication

estimatePi <- function(numDraws){
	r <- .5 #radius... in case the unit circle is too boring
	x <- runif(numDraws, min=-r, max=r) 
	y <- runif(numDraws, min=-r, max=r)
	inCircle <- ifelse( (x^2 + y^2)^.5 < r , 1, 0)
	return(sum(inCircle) / length(inCircle) * 4)
}

CerebralMastication

#first let's set up a big table and a little table 

bigTableRows <- 1e6
numbers <- 0:500

dim1 <- sample(numbers, bigTableRows, replace=T)
dim2 <- sample(numbers, bigTableRows, replace=T)
fact1 <- rnorm(bigTableRows)

bigTable <- data.frame(dim1, dim2, fact1, stringsAsFactors = F)

CerebralMastication

#!/bin/bash

#debian R upgrade
echo "deb http://streaming.stat.iastate.edu/CRAN/bin/linux/debian lenny-cran/" | sudo tee -a /etc/apt/sources.list
sudo apt-get update
sudo apt-get -t lenny-cran install --yes --force-yes r-base r-base-dev

CerebralMastication

#! /usr/bin/env Rscript

#start an instance
startup <- system("ec2-run-instances ami-b232d0db -k ec2ApiTools", intern=T)
Sys.sleep(45) #rather random but 45 seconds is typically long enough to boot

#query running instances
instances <- system("ec2-describe-instances", intern=T)
instancesParsed <- sapply(instances, strsplit, "\t")

CerebralMastication

# looking at some data with @neilkod

myData <- read.csv("http://www.neilkodner.com/10kreads.csv")
plot(density(myData$X1))

#holy shit that's a big spike at the low values. Let's look at the tail
plot(density(subset(myData, X1 > 3)$X1))

plot(density(subset(myData, X1 > 5)$X1))

CerebralMastication

# example of how to use a Guassian Copula to create random draws from
# normally distributed data

require("reshape")
require("plyr")
require("QRMlib")
require("Matrix")

#make this reproducable
set.seed(2)

CerebralMastication

# multivariate normal example using the MASS package


require(MASS)

#make this reproducible
set.seed(2)

#how many draws in our starting data set?
n <- 1e4

CerebralMastication

# multivariate normal example using Cholesky decomposition

require(Matrix)

#make this reproducible
set.seed(2)

#how many draws in our starting data set?
n <- 1e4