Year-by-year 1-column comparison of timeseries data with facet_wrap

year-over-year-comp.r

#!/usr/bin/env Rscript
library(ggplot2)
library(stringr)
library(gridExtra)
library(scales)

args <- commandArgs(trailingOnly = TRUE)

format_si <- function(...) {
  # Format a vector of numeric values according
  # to the International System of Units.
  # http://en.wikipedia.org/wiki/SI_prefix
  #
  # Based on code by Ben Tupper
  # https://stat.ethz.ch/pipermail/r-help/2012-January/299804.html
  # Args:
  #   ...: Args passed to format()
  #
  # Returns:
  #   A function to format a vector of strings using
  #   SI prefix notation
  #
  # Usage:
  #   scale_y_continuous(labels=format_si()) +
  #  
  function(x) {
    limits <- c(1e-24, 1e-21, 1e-18, 1e-15, 1e-12,
                1e-9,  1e-6,  1e-3,  1e0,   1e3,
                1e6,   1e9,   1e12,  1e15,  1e18,
                1e21,  1e24)
    prefix <- c("y",   "z",   "a",   "f",   "p",
                "n",   "µ",   "m",   " ",   "k",
                "M",   "G",   "T",   "P",   "E",
                "Z",   "Y")
  
    # Vector with array indices according to position in intervals
    i <- findInterval(abs(x), limits)
  
    # Set prefix to " " for very small values < 1e-24
    i <- ifelse(i==0, which(limits == 1e0), i)

    paste(format(round(x/limits[i], 1),
                 trim=TRUE, scientific=FALSE, ...),
          prefix[i])
  }
}


Y = read.delim(args[1], sep=",", header=TRUE)
Y$date <- as.POSIXct(Y$time)

png(filename = paste(sep="", args[1], ".png"), width = 550, height = 300, units = 'px')
  print(
    ggplot(data=Y) +
	geom_line(aes(date, count), color="#e56d25") + 
    scale_y_continuous(labels=format_si()) + 
    scale_x_datetime(limits=c(as.POSIXct("2007-01-01"), as.POSIXct("2012-09-01"))) +
    xlab("Date") +
    ylab("Tweets per Day") +
    ggtitle(args[2]) + 
    opts(legend.position = 'none',
       panel.background = theme_rect(fill = "#545454"),
       panel.grid.major = theme_line(colour = "#757575"),
       panel.grid.minor = theme_line(colour = "#757575")
        )
    )
dev.off()


##
# year over year comparison with facet wrap
#
# simulate dates in single year (2000 in this case),
# but give them yr factors for facet
# use custom formatting
#

Y$Yr <- as.factor(as.POSIXlt(Y$time)$year + 1900)
Y$Mn <- as.factor(1 + as.POSIXlt(Y$time)$mon)
Y$Dy <- as.factor(as.POSIXlt(Y$time)$mday)
# use dates for easier plotting
Y <- transform(Y, doy = as.Date(paste("2000", Y$Mn, Y$Dy, sep="/")))

png(filename = paste(sep="", args[1], ".year.png"), width = 550, height = 800, units = 'px')
  print(
    ggplot(data=Y) +
	geom_line(aes(doy, count), color="#e56d25") + 
    facet_wrap( ~ Yr, ncol = 1, scales="free_y" ) + 
    scale_y_continuous(labels=format_si()) + 
    scale_x_date(labels=date_format("%b"), breaks = seq(min(Y$doy),max(Y$doy),"month")) +
    xlab("Date") + ylab("Tweets per Day") +
    labs( title = args[2] ) + 
    theme( legend.position = 'none', 
           panel.margin = unit(1.5, 'line'),
           strip.text.x = element_text(size=12, face="bold"),
           panel.background = element_rect(fill = "#545454"),
           panel.grid.major = element_line(colour = "#757575"),
           panel.grid.minor = element_line(colour = "#757575")
    )
  )
dev.off()