Add family size histogram

src/family_size_hist.R

@@ -0,0 +1,24 @@
+#!/usr/bin/env Rscript
+library(dplyr)
+library(ggplot2)
+
+args <- commandArgs(trailingOnly=TRUE)
+input_file <- args[1]
+output_file <- args[2]
+title <- args[3]
+
+family_df <- read.table(input_file, header=FALSE)
+colnames(family_df) <- c("geneid", "familyid")
+
+count_df <- family_df %>% count(familyid)
+distribution_df <- count_df %>% count(n)
+
+theme_set(theme_grey(base_size=20))
+
+ggplot(distribution_df, aes(x=n, y=nn)) +
+  geom_bar(stat='identity') +
+  labs(title="Duplicate Gene Family Sizes",
+       subtitle=title) +
+  xlab("family size") +
+  ylab("count")
+ggsave(output_file)