icgc_discusage_pie.R

library(ggplot2) 
# ggpie: draws a pie chart.
# give it:
# * `dat`: your dataframe
# * `by` {character}: the name of the fill column (factor)
# * `totals` {character}: the name of the column that tracks
#    the time spent per level of `by` (percentages work too).
# returns: a plot object.

#credit http://mathematicalcoffee.blogspot.co.uk/2014/06/ggpie-pie-graphs-in-ggplot2.html
ggpie <- function (dat, by, totals) {
    ggplot(dat, aes_string(x=factor(1), y=totals, fill=by)) +
        geom_bar(stat='identity', color='black') +
        guides(fill=guide_legend(override.aes=list(colour=NA))) + # removes black borders from legend
        coord_polar(theta='y') +
        theme(axis.ticks=element_blank(),
            axis.text.y=element_blank(),
            axis.text.x=element_text(colour='black'),
            axis.title=element_blank()) +
    scale_y_continuous(breaks=cumsum(dat[[totals]]) - dat[[totals]] / 2, labels=dat[[by]])    
}

clusterdiskusage_icgconly <- read.csv("/tmp/clusterdiskusage_icgconly.csv", header=FALSE)
  View(clusterdiskusage_icgconly)
#V1 is GB size, V2 project name

library(grid) # for `unit`
library(dplyr)
c <- arrange(clusterdiskusage_icgconly, desc(V1))

ggpie(c, by='V2', totals='V1') +
    ggtitle("Clusterstorage use.") +
    theme(axis.ticks.margin=unit(0,"lines"),
          plot.margin=rep(unit(0, "lines"),4))

#Does not work that nice with polar coord labels, consider
#http://www.sthda.com/english/wiki/ggplot2-pie-chart-quick-start-guide-r-software-and-data-visualization