BA Complementation Analysis

#=========================================================
# PREAMBLE
#=========================================================

# load the plotting library
suppressMessages(library(ggplot2))
#library(gridExtra)
#library(ggExtra)
#library(tikzDevice)
#library(Hmisc)
#library(pastecs)

theme_set(theme_bw())

options(scipen=999)  # turn-off scientific notation like 1e+48

# size of point for scatterplots
POINT_SIZE = 0.1
#POINT_SIZE = 1

# timeout
TIMEOUT = params$timeout
TIMEOUT_VAL = 1.05 * TIMEOUT

ERR_VAL = 1.3 * TIMEOUT

# saturate
TIME_MIN = 0.01 # seconds

BIG_SIZE=3
SMALL_SIZE=2

# FUNCTIONS
read_file <- function(file) {
  filename = paste0(file)
  df <- read.csv2(filename,
                  header=TRUE,
                  sep=";",
                  dec=",",
                  comment.char="",
                  na.strings=c("TO", "ERR"),
                  quote="\"",
                  strip.white=TRUE,
                  allowEscapes=FALSE,
                  stringsAsFactors=FALSE)

  return(df)
}

plot_scatter_log <- function(df, xlab, ylab, xstring=xlab, ystring=ylab) {
  pscat <- ggplot(df, aes_string(x=xlab, y=ylab)) +
    geom_point(size=POINT_SIZE) +
    geom_abline(size=0.1) +
    geom_vline(size=0.1, xintercept=STATES_TIMEOUT, linetype="dashed") +
    geom_hline(size=0.1, yintercept=STATES_TIMEOUT, linetype="dashed") +
    geom_rug(alpha = 0.2) +
    scale_x_log10() +
    scale_y_log10() +
    theme(axis.text.y = element_text(angle = 90, hjust = 0.5)) +
    coord_fixed(xlim = c(STATES_MIN, STATES_TIMEOUT), ylim = c(STATES_MIN, STATES_TIMEOUT)) +
    labs(
      #title="Title",
      #subtitle="Subtitle",
      x=xstring,
      y=ystring)
  return(pscat)
}

make_tikz <- function(file, picture, width=2.5, height=2.5) {
  font_size <- 1
  tikz(file=file, onefile=T, width=width, height=height)
  plot(picture)
  garbage <- dev.off()
}

make_pdf <- function(file, picture, width=5, height=5) {
  pdf(file=file, onefile=T, width, height)
  plot(picture)
  garbage <- dev.off()
}

df <- read_file(params$file)
orig_size <- nrow(df)

What
Size	11000

# Sanitize
#df[df == 'ERR'] <- NA
#df[df == 'TO'] <- NA

# need to be changed
STATES_MIN = 1
STATES_MAX = max(max(df[,"seminat.States"], na.rm=TRUE), max(df[,"spot.States"], na.rm=TRUE))

STATES_TIMEOUT <- STATES_MAX * 1.3
df[is.na(df)] <- STATES_TIMEOUT

plot_scatter_log(df, "ranker.States", "spot.States")

plot_scatter_log(df, "ranker.States", "seminat.States")

plot_scatter_log(df, "ranker.States", "roll.States")

plot_scatter_log(df, "ranker.States", "schewe.States")

plot_scatter_log(df, "ranker.States", "piterman.States")

plot_scatter_log(df, "ranker.States", "goal.df.States")

plot_scatter_log(df, "ranker.States", "safra.States")

plot_scatter_log(df, "seminat.States", "spot.States")

plot_scatter_log(df, "seminat.States", "roll.States")

plot_scatter_log(df, "seminat.States", "schewe.States")

plot_scatter_log(df, "seminat.States", "piterman.States")

plot_scatter_log(df, "seminat.States", "goal.df.States")

plot_scatter_log(df, "seminat.States", "safra.States")

plot_scatter_log(df, "seminat.States", "spot.States")

plot_scatter_log(df, "roll.States", "spot.States")

plot_scatter_log(df, "roll.States", "seminat.States")