gistfile1.r

## Continue from the above R code
year.start.pos <- regexpr("year =", bibfile, perl=TRUE)
year.lines <- which( year.start.pos > 0 ) 
year.split <- strsplit(bib[year.lines], "[ =,]", perl=TRUE)	
Pub.year <- as.numeric(sapply(year.split, "[[", 6))
tradPub <- as.data.frame(table(Pub.year))
names(tradPub) <- c("year", "traditional paper")

## Get information about the online published PDF files
library(XML)
webPub <-
readHTMLTable(readLines("http://cran.r-project.org/doc/contrib/"))[[1]]
## look only at the PDF files
pdfs <- regexpr(".pdf", as.character(webPub[,2]))

webPub.modified <- webPub[pdfs > 0, 3]
webPub.modified <- strsplit(na.omit(as.character(webPub.modified)), "[ -]")
webPub.year <- as.numeric(sapply(webPub.modified, "[[", 3))

webPub <- as.data.frame(table(webPub.year))
names(webPub) <- c("year", "online PDF")
## Merge information about the online and traditional books
totalPub <- merge(tradPub, webPub, all=TRUE)
totalPub[is.na(totalPub)] <- 0 
## Calculate the cumulative statistics
cumPub <- data.frame(year=totalPub$year, apply(totalPub[,2:3], 2, cumsum ))
names(cumPub) <- c("year", "traditional paper",
	          "online PDF")
## We use the googleVis package to create area charts
library(googleVis)
cumPlot <- gvisAreaChart(cumPub, "year", 
  			 options=list(title="Number of R related books available", 
			 isStacked=TRUE))

incPlot <- gvisAreaChart(totalPub, "year", 
	   			   options=list(title="Number of R
				   related books published",
				   isStacked=FALSE))

inccumPlot <- gvisMerge(incPlot, cumPlot)

plot(inccumPlot)