ajdamico

#create the remove NA function
no.na <-
    function( x , value = FALSE ){

        x[ is.na( x ) ] <- value

        x

    }

ajdamico

xl <- seq( 0 , 10000 , 100 )
my_title <- 'if we randomly choose X people from some population and determine that none have a disease,\nwe can be 95% confident that the population prevalence rate is below Y% for this particular affliction.'
plot( xl , qbeta(1 - 0.05, 1 , xl ) , ylim=c(0,.01),axes=F,xlab="",ylab="",main="\nhow rare is a rare disease?\n\nsurvey research does a lousy job of estimating prevalence rates for unlikely events")
axis(2, at=seq(0,.01,.001), lab=paste0(seq(0,.01,.001)*100,"%"), las=TRUE)
axis(1, at=seq(0,10000,1000), lab=prettyNum(seq(0,10000,1000),big.mark=","), las=TRUE)
text( 3500 , 0.0075 , label = my_title , cex = 1.5, adj=c(0,0))

z <- data.frame( x = 0:100000 , y = qbeta(1 - 0.05, 1 , 0:100000 ) )

ajdamico

# install mapping packages
install.packages( c( 'sp' , 'rgdal' ) )

# load necessary libraries
require(sp)
require(rgdal)

# create a temporary file and directory
tf <- tempfile() ; td <- tempdir()

ajdamico

# # # # # # # # # # # # # # # # #
# # set the working directory # #
# # # # # # # # # # # # # # # # #

# setwd( "C:/My Directory/SWMAP/" )


# # # # # # # # # # # # # # # #
# # example survey data set # #
# # # # # # # # # # # # # # # #

ajdamico

library(downloader)

# install.packages( c("MonetDB.R", "MonetDBLite" , "survey" , "SAScii" , "descr" , "downloader" , "digest" , "stringr" , "R.utils" , "RCurl" ) , repos=c("http://dev.monetdb.org/Assets/R/", "http://cran.rstudio.com/"))

library(SAScii) 		# load the SAScii package (imports ascii data with a SAS script)
library(RCurl)			# load RCurl package (downloads https files)
library(stringr)		# load stringr package (manipulates character strings easily)
library(downloader)		# downloads and then runs the source() function on scripts from github
library(MonetDB.R)		# load the MonetDB.R package (connects r to a monet database)

ajdamico

# devtools::install_github( "ajdamico/lodown" )

library(tm)
library(tidyverse)
library(rvest)

cranlogs_html <- read_html( "http://cran-logs.rstudio.com/" )

gz_files <- html_attr( html_nodes( cranlogs_html , "a" ) , "href" )

ajdamico

x <-
	structure(list(name = c("George Washington", "John Adams", "Thomas Jefferson", 
	"James Madison", "James Monroe", "John Quincy Adams", "Andrew Jackson", 
	"Martin Van Buren", "William Henry Harrison", "John Tyler", "James K. Polk", 
	"Zachary Taylor", "Millard Fillmore", "Franklin Pierce", "James Buchanan", 
	"Abraham Lincoln", "Andrew Johnson", "Ulysses S. Grant", "Rutherford B. Hayes", 
	"James A. Garfield", "Chester Arthur", "Grover Cleveland", "Benjamin Harrison", 
	"William McKinley", "Theodore Roosevelt", "William Howard Taft", 
	"Woodrow Wilson", "Warren G. Harding", "Calvin Coolidge", "Herbert Hoover", 

ajdamico

library(survey)
library(lodown)

cpsasec_cat <- get_catalog( "cpsasec" , output_dir = tempdir() )

lodown( "cpsasec" , subset( cpsasec_cat , year == 2017 ) )


plot( 
	c( 15 , 75 ) , 

ajdamico

library(rvest)

tf <- tempfile()
tf2 <- tempfile()

# download and unzip
download.file( "https://dumps.wikimedia.org/other/pagecounts-ez/merged/2018/2018-05/pagecounts-2018-05-27.bz2" , tf , mode = 'wb' )
R.utils::bunzip2( tf , tf2 , remove = FALSE )

# import and restrict to english

ajdamico

#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 )