Anthony Damico ajdamico

## import SAS ASCII file into R with SAS INPUT text file
##select file containing SAS input procedure
SASinput <- readLines(file.choose())

##find the first INPUT line
firstline<-min(grep("INPUT @1",toupper(SASinput)))

##find the first semicolon ending that input line
a<-grep(";",toupper(SASinput))
lastline<-min(a[a>firstline])

## calculate your ten thousandth day on earth with R
#replace my birthday with yours
birthday <- strptime(c("8.18.1982"), format = "%m.%d.%Y", tz="EST")

#r counts everything in seconds, so this code multiplies by 60 seconds in a minute, 60 minutes in an hour, 24 hours in a day.
days <- function(u) {
x <- u * 60 * 60 * 24
return(x)
}

#change these numbers to whichever days you'd like to see, separated by commas

## download the medical expenditure panel survey.R
library(RCurl)

setwd("R:\\Medical Expenditure Panel Survey\\Data")

#input all available MEPS public use file numbers
year <- c(1996:2008)
consolidated <- c(12,20,28,38,50,60,70,79,89,97,105,113,NA)
conditions <- c("06r",18,27,37,52,61,69,78,87,96,104,112,NA)
jobs <- c("07",19,25,32,40,56,63,74,83,91,100,108,116)
prpf <- c(24,47,47,47,47,57,66,76,88,95,103,111,119)

## concentration of health expenditures.R
#warning: excludes the institutionalized population!

#install survey and foreign packages
#-- only run these lines of code the first time

#install.packages("foreign")
#install.packages("survey")

#designate each of the MEPS consolidated files -
consolidated_files <- c( 12 , 20 , 28 , 38 , 50 , 60 , 70 , 79 , 89 , 97 , 105 , 113 )

## multicore win64.R
library(snowfall)

bigProcess <- function( x ) {
	mean( replicate ( 10^6 , max( rnorm( 100 , x ) ) ) )
	}

#run the function twice in parallel
start <- Sys.time()
sfInit(cpus=2,type='SOCK',parallel=TRUE)
sfSapply( c(1,5) , bigProcess )

## furman intro to r lecture.R
#three reasons to use R-

#it's free

#it's open source- package system

#it's a programming language for statistics.

x <- 1:5

## determine what pecent of fractions are non-repeating.R
# calculate the percent of fractions that are repeating vs. non-repeating

# install stringr if you don't already have it
#install.packages("stringr")

library( stringr )
options( digits=22 )

# this program looks at..
# 1/1, 1/2, 1/3, 1/4.. up to 1/x

## analyzing big survey data with limited computing resources.R
########################################
###read large csv into SQL DB
########################################

#set to the number of GB of RAM on computer
gbram <- 0.5

#set to CSV file directory
setwd("C:\\American Community Survey\\2009\\")

## download all files from an FTP site.R
#install RCurl on your version of R if you don't already have it
#just run this once
#install.packages("RCurl")

#program start
#load the RCurl package
library(RCurl)

#set your output folder - this is where the pdfs will get saved
setwd("R:/National Health Interview Survey/documentation")

## NHIS download matrix.R

#load necessary libraries
library(stringr)
library(foreign)
library(survey)
library(RCurl)

#set the temporary directory to download all files to!
setwd("s:/temp")
	##select file containing SAS input procedure
	SASinput <- readLines(file.choose())

	##find the first INPUT line
	firstline<-min(grep("INPUT @1",toupper(SASinput)))

	##find the first semicolon ending that input line
	a<-grep(";",toupper(SASinput))
	lastline<-min(a[a>firstline])
	#replace my birthday with yours
	birthday <- strptime(c("8.18.1982"), format = "%m.%d.%Y", tz="EST")

	#r counts everything in seconds, so this code multiplies by 60 seconds in a minute, 60 minutes in an hour, 24 hours in a day.
	days <- function(u) {
	x <- u * 60 * 60 * 24
	return(x)
	}

	#change these numbers to whichever days you'd like to see, separated by commas
	library(RCurl)

	setwd("R:\\Medical Expenditure Panel Survey\\Data")

	#input all available MEPS public use file numbers
	year <- c(1996:2008)
	consolidated <- c(12,20,28,38,50,60,70,79,89,97,105,113,NA)
	conditions <- c("06r",18,27,37,52,61,69,78,87,96,104,112,NA)
	jobs <- c("07",19,25,32,40,56,63,74,83,91,100,108,116)
	prpf <- c(24,47,47,47,47,57,66,76,88,95,103,111,119)
	#warning: excludes the institutionalized population!

	#install survey and foreign packages
	#-- only run these lines of code the first time

	#install.packages("foreign")
	#install.packages("survey")

	#designate each of the MEPS consolidated files -
	consolidated_files <- c( 12 , 20 , 28 , 38 , 50 , 60 , 70 , 79 , 89 , 97 , 105 , 113 )
	library(snowfall)

	bigProcess <- function( x ) {
	mean( replicate ( 10^6 , max( rnorm( 100 , x ) ) ) )
	}

	#run the function twice in parallel
	start <- Sys.time()
	sfInit(cpus=2,type='SOCK',parallel=TRUE)
	sfSapply( c(1,5) , bigProcess )
	#three reasons to use R-

	#it's free

	#it's open source- package system

	#it's a programming language for statistics.

	x <- 1:5
	# calculate the percent of fractions that are repeating vs. non-repeating

	# install stringr if you don't already have it
	#install.packages("stringr")

	library( stringr )
	options( digits=22 )

	# this program looks at..
	# 1/1, 1/2, 1/3, 1/4.. up to 1/x
	########################################
	###read large csv into SQL DB
	########################################

	#set to the number of GB of RAM on computer
	gbram <- 0.5

	#set to CSV file directory
	setwd("C:\\American Community Survey\\2009\\")
	#install RCurl on your version of R if you don't already have it
	#just run this once
	#install.packages("RCurl")

	#program start
	#load the RCurl package
	library(RCurl)

	#set your output folder - this is where the pdfs will get saved
	setwd("R:/National Health Interview Survey/documentation")

	#load necessary libraries
	library(stringr)
	library(foreign)
	library(survey)
	library(RCurl)

	#set the temporary directory to download all files to!
	setwd("s:/temp")