24_deb_pkg_gov/R/documentReadabilityAnalysis.R

library(tidyverse)
library(plyr) 
library(gridExtra)
library(ggpubr)
# script for the analysis of document readability metrics 
# readability metrics will be studied controlled by their length
# gaughan@u.northwestern.edu
# loading in the data 
try(setwd(dirname(rstudioapi::getActiveDocumentContext()$path)))
readme_df <- read_csv("../text_analysis/draft_readability_readme.csv")
contributing_df <- read_csv("../text_analysis/draft_readability_contributing.csv")
head(readme_df)
aggregate(readme_df[, 3:10], list(readme_df$subdir), median)
#getting basic stats for the readme readability 
median(readme_df$flesch_reading_ease)
median(readme_df$linsear_write_formula)
median(readme_df$mcalpine_eflaw)
median(readme_df$reading_time)
# establishing the color scheme 
subdirColors <-
  setNames( c('firebrick1', 'forestgreen', 'cornflowerblue')
            , levels(contributing_df$subdir)  )

#plotting linsear scoring
readme_linsear_plot <- ggplot(readme_df, aes(x=linsear_write_formula, group=as.factor(subdir))) + 
  geom_density(aes(color = as.factor(subdir), fill=as.factor(subdir)), alpha=0.2, position="identity") +
  xlim(-30, 30) +
  theme_bw()
#plotting readme reading ease
readme_reading_ease <- ggplot(readme_df, aes(x=flesch_reading_ease, group=as.factor(subdir))) + 
  geom_density(aes(color = as.factor(subdir), fill=as.factor(subdir)), alpha=0.2, position="identity") +
  scale_color_manual(values = subdirColors) + 
  xlim(-5, 90) +
  ylab("readme density") +
  guides(fill="none", color="none")+
  theme_bw() 
readme_reading_ease 
#plotting readme reading time 
readme_reading_time_plot <- ggplot(readme_df, aes(x=reading_time, group=as.factor(subdir))) + 
  geom_density(aes(color = as.factor(subdir), fill=as.factor(subdir)), alpha=0.2, position="identity") +
  scale_color_manual(values = subdirColors) + 
  xlim(-5, 90) +
  ylab("readme density") +
  guides(fill="none", color="none")+
  theme_bw() 

readme_linsear_plot <- ggplot(readme_df, aes(x=linsear_write_formula, group=as.factor(subdir))) + 
  geom_density(aes(color = as.factor(subdir), fill=as.factor(subdir)), alpha=0.2, position="identity") +
  scale_color_manual(values = subdirColors) + 
  xlim(-5, 30) +
  ylab("readme density") +
  guides(fill="none", color="none")+
  theme_bw() 
readme_mcalpine_eflaw <- ggplot(readme_df, aes(x=mcalpine_eflaw, group=as.factor(subdir))) + 
  scale_color_manual(values = subdirColors) + 
  geom_density(aes(color = as.factor(subdir), fill=as.factor(subdir)), alpha=0.2, position="identity") +
  xlim(-5, 60) +
  guides(fill="none", color="none")+
  theme_bw()
#theme(axis.title.y=element_blank())
#plot of reading_ease 
#readme_df <- readme_df |>
#  mutate(coef_grouping <- as.factor(subdir))
#test_lm <- lm(mcalpine_eflaw ~ word_count + as.factor(subdir),data=readme_df)
#summary(test_lm)
aggregate(contributing_df[, 3:10], list(contributing_df$subdir), median)
#basic stats for the contributing readability
median(contributing_df$flesch_reading_ease)
median(contributing_df$mcalpine_eflaw)
median(contributing_df$reading_time)
median(contributing_df$linsear_write_formula)
# plotting contributing linsear writing formula
contributing_linsear_plot <- ggplot(contributing_df, aes(x=linsear_write_formula, group=as.factor(subdir))) + 
  scale_color_manual(values = subdirColors) + 
  geom_density(aes(color = as.factor(subdir), fill=as.factor(subdir)), alpha=0.2, position="identity") +
  xlim(-5, 30) +
  guides(fill="none", color="none")+
  theme_bw()
# plotting contributing reading time 
contributing_reading_time_plot <- ggplot(contributing_df, aes(x=reading_time, group=as.factor(subdir))) + 
  scale_color_manual(values = subdirColors) + 
  geom_density(aes(color = as.factor(subdir), fill=as.factor(subdir)), alpha=0.2, position="identity") +
  xlim(-5, 90) +
  ylab("contributing density") +
  guides(fill="none", color="none")+
  theme_bw()
# plotting contributing mcalpine eflaw
contributing_mcalpine_eflaw <- ggplot(contributing_df, aes(x=mcalpine_eflaw, group=as.factor(subdir))) + 
  scale_color_manual(values = subdirColors) + 
  geom_density(aes(color = as.factor(subdir), fill=as.factor(subdir)), alpha=0.2, position="identity") +
  xlim(-5, 60) +
  guides(fill="none", color="none")+
  theme_bw()
# plotting contributing reading ease
contributing_reading_ease <- ggplot(contributing_df, aes(x=flesch_reading_ease, group=as.factor(subdir))) + 
  geom_density(aes(color = as.factor(subdir), fill=as.factor(subdir)), alpha=0.2, position="identity") +
  scale_color_manual(values = subdirColors) + 
  ylab("contributing density") +
  xlim(-5, 90) +
  theme_bw() + 
  theme(legend.position = "top") 
contributing_reading_ease 
grid.arrange(contributing_reading_ease, contributing_reading_time_plot,contributing_linsear_plot, contributing_mcalpine_eflaw, readme_reading_ease, readme_reading_time_plot, readme_linsear_plot, readme_mcalpine_eflaw, nrow = 2)