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()$path)))
readme_df <- read_csv("../text_analysis/dwo_readability_readme.csv")
contributing_df <- read_csv("../text_analysis/dwo_readability_contributing.csv")
head(readme_df)
quantile(readme_df$reading_time)
quantile(contributing_df$reading_time)
aggregate(readme_df[, 3:10], list(readme_df$subdir), median)
aggregate(contributing_df[, 3:10], list(contributing_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$reading_time)
# establishing the color scheme 
subdirColors <-
  setNames( c('#31449c', '#4a7c85', '#c5db68')
            , levels(contributing_df$subdir)  )
readmeSubdirColors <-
  setNames( c('#4a7c85', '#c5db68')
            , levels(readme_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=0.35, 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(fill=as.factor(subdir)), position="fill") +
  scale_fill_manual(values = readmeSubdirColors) + 
  xlim(-5, 90) +
  labs(x= "Flesch Reading Ease", y= "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(fill=as.factor(subdir)), position="fill") +
  scale_fill_manual(values = readmeSubdirColors) + 
  xlim(-5, 90) +
  labs(x= "Reading Time (s)", y= NULL)+ 
  guides(fill="none", color="none")+
  theme_bw() 
readme_reading_time_plot
readme_reading_time_no_group <- ggplot(readme_df, aes(x=reading_time)) + 
  geom_histogram(fill='forestgreen') +
  xlim(-5, 190) +
  ylab("Count of README Files") +
  xlab("Reading Time (s)") +
  ggtitle("Reading Time for README files from FLOSS Projects (n=2280)")+
  guides(fill="none", color="none")+
  theme_bw() 

readme_reading_time_no_group 

readme_linsear_plot <- ggplot(readme_df, aes(x=linsear_write_formula, group=as.factor(subdir))) + 
  geom_density(aes(fill=as.factor(subdir)), alpha=0.35, position="identity") +
  scale_fill_manual(values = readmeSubdirColors) + 
  xlim(-5, 90) +
  labs(x= "Linsear Write Score", y= NULL)+ 
  guides(fill="none", color="none")+
  theme_bw() 
readme_linsear_plot
readme_mcalpine_eflaw <- ggplot(readme_df, aes(x=mcalpine_eflaw, group=as.factor(subdir))) + 
  geom_density(aes(fill=as.factor(subdir)), alpha=0.35, position="identity") +
  scale_fill_manual(values = readmeSubdirColors) + 
  xlim(-5, 90) +
  labs(x= "McAlpine EFLAW", y= NULL)+ 
  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))) + 
  geom_density(aes(fill=as.factor(subdir)), alpha=0.35, position="identity") +
  scale_fill_manual(values = subdirColors, labels=c('CI < 0', '0 in CI', '0 < CI')) + 
  labs(x= NULL, y= NULL, fill="RE Grouping")+ 
  xlim(-5, 90) +
  theme_bw() + 
  guides(fill="none", color="none")
# plotting contributing reading time 
contributing_reading_time_plot <- ggplot(contributing_df, aes(x=reading_time, group=as.factor(subdir))) + 
  scale_fill_manual(values = subdirColors, labels=c('CI < 0', '0 in CI', '0 < CI')) + 
  geom_density(aes(fill=as.factor(subdir)), position="fill") +
  xlim(-5, 90) +
  labs(x= NULL, y= NULL, fill="RE Grouping")+ 
  theme_bw() +
  theme(legend.position = "inside", 
        legend.position.inside = c(.93, .93),
        legend.justification = c("right", "top"),
        legend.direction = "horizontal",
        legend.margin = margin(6, 6, 6, 6))
contributing_reading_time_plot
# plotting contributing mcalpine eflaw
contributing_mcalpine_eflaw <- ggplot(contributing_df, aes(x=mcalpine_eflaw, group=as.factor(subdir))) + 
  scale_fill_manual(values = subdirColors, labels=c('CI < 0', '0 in CI', '0 < CI')) + 
  geom_density(aes(fill=as.factor(subdir)), alpha=0.35, position="identity") +
  xlim(-5, 90) +
  labs(x= NULL, y= NULL, fill="RE Grouping")+ 
  theme_bw() +
  theme(legend.position = "inside", 
        legend.position.inside = c(.93, .93),
        legend.justification = c("right", "top"),
        legend.direction = "vertical",
        legend.margin = margin(6, 6, 6, 6))
# plotting contributing reading ease
contributing_reading_ease <- ggplot(contributing_df, aes(x=flesch_reading_ease, group=as.factor(subdir))) + 
  geom_density(aes(fill=as.factor(subdir)), position="fill") +
  scale_fill_manual(values = subdirColors, labels=c('CI < 0', '0 in CI', '0 < CI')) + 
  labs(x= NULL, y="CONTRIBUTING Density", fill="RE Grouping")+ 
  xlim(-5, 90) +
  theme_bw() + 
  guides(fill="none", color="none")
contributing_reading_ease 
grid.arrange(contributing_reading_ease, contributing_reading_time_plot, readme_reading_ease, readme_reading_time_plot, nrow = 2)

doctypeColors <-
  setNames( c('#5da2d8', '#c7756a')
            , c("CONTRIBUTING", "README"))
readme_df$type = "README"
contributing_df$type = "CONTRIBUTING"
all_df = rbind(readme_df, contributing_df)
length_plot_all <- ggplot(all_df, aes(x=word_count, group=as.factor(type))) + 
  geom_density(aes(fill = as.factor(type)), color = NA, alpha=0.6, position="identity")+
  scale_fill_manual(values = doctypeColors) + 
  xlim(-10, 500) +
  labs(
    x = "Word Count",
    y = "Density Across Documents",
    fill="Document Type"
  ) +
  theme_bw() + 
  theme(legend.position = "top") 
length_plot_all
#grid.arrange(contributing_reading_time_plot, readme_reading_time_plot, nrow = 1)