R Notebook

Warning messages:
1: In readChar(file, size, TRUE) : truncating string with embedded nuls
2: In readChar(file, size, TRUE) : truncating string with embedded nuls
3: In readChar(file, size, TRUE) : truncating string with embedded nuls
4: In readChar(file, size, TRUE) : truncating string with embedded nuls
5: In readChar(file, size, TRUE) : truncating string with embedded nuls
6: In readChar(file, size, TRUE) : truncating string with embedded nuls
7: In readChar(file, size, TRUE) : truncating string with embedded nuls
8: In readChar(file, size, TRUE) : truncating string with embedded nuls
9: In readChar(file, size, TRUE) : truncating string with embedded nuls

# size of point for scatterplots
POINT_SIZE = 0.5
#POINT_SIZE = 1

# timeout
TIMEOUT = 600
TIMEOUT_VAL = 1.05 * TIMEOUT

# saturate
#TIME_MIN = 0.01 # seconds
TIME_MIN = 0.01 # seconds

# FUNCTIONS
read_file <- function(file) {
  filename = paste0(file)
  df <- read.csv2(filename,
                  header=TRUE,
                  sep=";",
                  dec=",",
                  comment.char="",
                  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=TIMEOUT_VAL, linetype="dashed") +
    geom_hline(size=0.1, yintercept=TIMEOUT_VAL, linetype="dashed") +
    scale_x_log10() +
    scale_y_log10() +
    theme(axis.text.y = element_text(angle = 90, hjust = 0.5)) +
    #coord_fixed(xlim = c(TIME_MIN, TIMEOUT_VAL), ylim = c(0.1, TIMEOUT_VAL)) +
    #coord_fixed(xlim = c(TIME_MIN, TIMEOUT_VAL), ylim = c(TIME_MIN, TIMEOUT_VAL)) +
        coord_fixed(xlim = c(TIME_MIN, TIMEOUT_VAL), ylim = c(TIME_MIN, TIMEOUT_VAL)) +

    labs(
      #title="Title",
      #subtitle="Subtitle",
      x=xstring,
      y=ystring)
  return(pscat)
}

df_old <- read_file("results-10-05-2020/table-ALL.csv")
df_new <- read_file("results-12-05-2020/table-ALL-ondra-processed.csv")

tools.times <- c("re2g", "cad", "grep", "srm", "dot.net")

# change the type of columns other than the name
for (i in tools.times) {
  df_old[,i] <- sub(",", ".", df_old[,i])
  suppressWarnings(df_old[,i] <- as.numeric(df_old[,i]))
  df_new[,i] <- sub(",", ".", df_new[,i])
  suppressWarnings(df_new[,i] <- as.numeric(df_new[,i]))
}

df_together <- merge(df_old, df_new, by = "file", suffixes=c(".old", ".new"))

plot_scatter_log(df_together, "grep.old", "grep.new")

plot_scatter_log(df_together, "cad.old", "cad.new")

plot_scatter_log(df_together, "re2g.old", "re2g.new")

plot_scatter_log(df_together, "srm.old", "srm.new")

plot_scatter_log(df_together, "dot.net.old", "dot.net.new")

NA
NA