updating population models

R/.Rhistory

@@ -1,204 +1,3 @@
-ggtitle("Posterior Predictive Density", subtitle="Non-Democracies") +
-theme_bw()
-p
-#plot of reading_ease
-p <- ggplot(readme_df, aes(x=flesch_reading_ease, group=as.factor(subdir))) +
-geom_histogram(aes( color = as.factor(subdir), fill=as.factor(subdir)), alpha=0.2, position="identity") +
-theme_bw()
-p
-p <- ggplot(contributing_df, aes(x=reading_time, group=as.factor(subdir))) +
-geom_histogram(aes( color = as.factor(subdir), fill=as.factor(subdir)), alpha=0.2, position="identity") +
-theme_bw()
-p
-p <- ggplot(contributing_df, aes(x=mcalpine_eflaw, group=as.factor(subdir))) +
-geom_histogram(aes( color = as.factor(subdir), fill=as.factor(subdir)), alpha=0.2, position="identity") +
-theme_bw()
-p
-p <- ggplot(contributing_df, aes(x=linsear_write, group=as.factor(subdir))) +
-geom_histogram(aes( color = as.factor(subdir), fill=as.factor(subdir)), alpha=0.2, position="identity") +
-theme_bw()
-p
-head(readme_df)
-p0
-p0 <- ggplot(contributing_df, aes(x=linsear_write_formula, group=as.factor(subdir))) +
-geom_histogram(aes( color = as.factor(subdir), fill=as.factor(subdir)), alpha=0.2, position="identity") +
-theme_bw()
-p0
-p0 <- ggplot(contributing_df, aes(x=linsear_write_formula, group=as.factor(subdir))) +
-geom_histogram(aes( color = as.factor(subdir), fill=as.factor(subdir)), alpha=0.2, position="identity") +
-xlim(-5, 30) +
-theme_bw()
-p0
-p0 <- ggplot(contributing_df, aes(x=linsear_write_formula, group=as.factor(subdir))) +
-geom_histogram(aes( color = as.factor(subdir), fill=as.factor(subdir)), alpha=0.2, position="identity") +
-xlim(-10, 30) +
-theme_bw()
-p0
-p0 <- ggplot(contributing_df, aes(x=linsear_write_formula, group=as.factor(subdir))) +
-geom_histogram(aes( color = as.factor(subdir), fill=as.factor(subdir)), alpha=0.2, position="identity") +
-xlim(-30, 30) +
-theme_bw()
-p0
-p0 <- ggplot(contributing_df, aes(x=flesch_reading_ease, group=as.factor(subdir))) +
-geom_histogram(aes( color = as.factor(subdir), fill=as.factor(subdir)), alpha=0.2, position="identity") +
-xlim(-30, 30) +
-theme_bw()
-p0
-p0 <- ggplot(contributing_df, aes(x=flesch_reading_ease, group=as.factor(subdir))) +
-geom_histogram(aes( color = as.factor(subdir), fill=as.factor(subdir)), alpha=0.2, position="identity") +
-xlim(-300, 300) +
-theme_bw()
-p0
-p0 <- ggplot(contributing_df, aes(x=linsear_write_formula, group=as.factor(subdir))) +
-geom_histogram(aes( color = as.factor(subdir), fill=as.factor(subdir)), alpha=0.2, position="identity") +
-xlim(-30, 30) +
-theme_bw()
-p0
-readme_linsear_plot <- ggplot(readme_df, aes(x=linsear_write_formula, group=as.factor(subdir))) +
-geom_histogram(aes( color = as.factor(subdir), fill=as.factor(subdir)), alpha=0.2, position="identity") +
-xlim(-30, 30) +
-theme_bw()
-p0
-readme_linsear_plot
-readme_linsear_plot <- ggplot(readme_df, aes(x=linsear_write_formula, group=as.factor(subdir))) +
-geom_histogram(aes( color = as.factor(subdir), fill=as.factor(subdir)), alpha=0.2, position="identity") +
-scale_y_continuous(breaks = seq(0,10,1),labels = paste(seq(0, 10, by = 1), "%", sep = ""))+
-xlim(-30, 30) +
-theme_bw()
-readme_linsear_plot
-readme_linsear_plot <- ggplot(readme_df, aes(x=linsear_write_formula, group=as.factor(subdir))) +
-geom_histogram(aes( color = as.factor(subdir), fill=as.factor(subdir)), alpha=0.2, position="identity") +
-xlim(-30, 30) +
-theme_bw()
-readme_linsear_plot
-readme_linsear_plot <- ggplot(readme_df, aes(x=linsear_write_formula, group=as.factor(subdir))) +
-geom_histogram(aes(y = (..count..)/sum(..count..)), color = as.factor(subdir), fill=as.factor(subdir)), alpha=0.2, position="identity") +
-readme_linsear_plot <- ggplot(readme_df, aes(x=linsear_write_formula, group=as.factor(subdir))) +
-geom_histogram(aes(y = (..count..)/sum(..count..), color = as.factor(subdir), fill=as.factor(subdir)), alpha=0.2, position="identity") +
-xlim(-30, 30) +
-theme_bw()
-readme_linsear_plot
-readme_linsear_plot <- ggplot(readme_df, aes(x=linsear_write_formula, group=as.factor(subdir))) +
-geom_histogram(aes(color = as.factor(subdir), fill=as.factor(subdir)), alpha=0.2, position="identity") +
-xlim(-30, 30) +
-theme_bw()
-readme_linsear_plot
-y = (..count..)/sum(..count..),
-y = (..count..)/sum(..count..),
-readme_linsear_plot <- ggplot(readme_df, aes(x=linsear_write_formula, group=as.factor(subdir))) +
-geom_histogram(aes(y = (..count..)/sum(..count..), color = as.factor(subdir), fill=as.factor(subdir)), alpha=0.2, position="identity") +
-xlim(-30, 30) +
-theme_bw()
-readme_linsear_plot
-readme_linsear_plot <- ggplot(readme_df, aes(x=linsear_write_formula, group=as.factor(subdir))) +
-geom_histogram(aes(color = as.factor(subdir), fill=as.factor(subdir)), alpha=0.2, position="dodge") +
-xlim(-30, 30) +
-theme_bw()
-readme_linsear_plot
-readme_linsear_plot <- ggplot(readme_df, aes(x=linsear_write_formula, group=as.factor(subdir))) +
-geom_histogram(aes(color = as.factor(subdir), fill=as.factor(subdir)), alpha=0.2, position="identity") +
-xlim(-30, 30) +
-theme_bw()
-readme_linsear_plot
-contributing_linsear_plot <- ggplot(contributing_df, aes(x=linsear_write_formula, group=as.factor(subdir))) +
-geom_histogram(aes(color = as.factor(subdir), fill=as.factor(subdir)), alpha=0.2, position="identity") +
-xlim(-30, 30) +
-theme_bw()
-contributing_linsear_plot
-contributing_linsear_plot <- ggplot(contributing_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()
-contributing_linsear_plot
-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()
-readme_linsear_plot
-contributing_linsear_plot
-contributing_reading_time_plot <- ggplot(contributing_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()
-contributing_reading_time_plot
-contributing_reading_time_plot
-contributing_reading_time_plot <- ggplot(contributing_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") +
-xlim(-30, 30) +
-theme_bw()
-contributing_reading_time_plot
-contributing_reading_time_plot <- ggplot(contributing_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") +
-xlim(-10, 50) +
-theme_bw()
-contributing_reading_time_plot
-contributing_reading_time_plot <- ggplot(contributing_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") +
-xlim(-10, 70) +
-theme_bw()
-contributing_reading_time_plot
-contributing_reading_time_plot <- ggplot(contributing_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") +
-xlim(-10, 80) +
-theme_bw()
-contributing_reading_time_plot
-contributing_reading_time_plot <- ggplot(contributing_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") +
-xlim(-10, 90) +
-theme_bw()
-contributing_reading_time_plot
-contributing_mcalpine_eflaw <- ggplot(contributing_df, aes(x=mcalpine_eflaw, group=as.factor(subdir))) +
-geom_density(aes(color = as.factor(subdir), fill=as.factor(subdir)), alpha=0.2, position="identity") +
-xlim(-10, 90) +
-theme_bw()
-contributing_mcalpine_eflaw
-contributing_mcalpine_eflaw <- ggplot(contributing_df, aes(x=mcalpine_eflaw, group=as.factor(subdir))) +
-geom_density(aes(color = as.factor(subdir), fill=as.factor(subdir)), alpha=0.2, position="identity") +
-xlim(-10, 70) +
-theme_bw()
-contributing_mcalpine_eflaw
-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") +
-xlim(-10, 70) +
-theme_bw()
-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") +
-xlim(-10, 90) +
-theme_bw()
-contributing_reading_ease
-grid.arrange(contributing_reading_ease, contributing_linsear_plot, contributing_mcalpine_eflaw, contributing_reading_time_plot, nrow = 2)
-library(gridExtra)
-grid.arrange(contributing_reading_ease, contributing_linsear_plot, contributing_mcalpine_eflaw, contributing_reading_time_plot, nrow = 2)
-# plotting contributing linsear writing formula
-contributing_linsear_plot <- ggplot(contributing_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(legend.position="none")
-# plotting contributing reading time
-contributing_reading_time_plot <- ggplot(contributing_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") +
-xlim(-10, 90) +
-theme_bw(legend.position="none")
-# plotting contributing mcalpine eflaw
-contributing_mcalpine_eflaw <- ggplot(contributing_df, aes(x=mcalpine_eflaw, group=as.factor(subdir))) +
-geom_density(aes(color = as.factor(subdir), fill=as.factor(subdir)), alpha=0.2, position="identity") +
-xlim(-10, 70) +
-theme_bw(legend.position="none")
-# 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") +
-theme(legend.position = "top") +
-xlim(-10, 90) +
-theme_bw()
-contributing_reading_ease
-grid.arrange(contributing_reading_ease, contributing_linsear_plot, contributing_mcalpine_eflaw, contributing_reading_time_plot, nrow = 2)
-# plotting contributing mcalpine eflaw
-contributing_mcalpine_eflaw <- ggplot(contributing_df, aes(x=mcalpine_eflaw, group=as.factor(subdir))) +
-geom_density(aes(color = as.factor(subdir), fill=as.factor(subdir)), alpha=0.2, position="identity") +
-xlim(-10, 70) +
-theme(legend.position="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") +
@@ -510,3 +309,204 @@ theme_bw() +
 theme(legend.position = "top")
 contributing_reading_ease
 grid.arrange(contributing_reading_ease, contributing_reading_time_plot,readme_reading_ease, readme_reading_time_plot, nrow = 2)
+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()$path)))
+readme_df <- read_csv("../text_analysis/draft_readability_readme.csv")
+contributing_df <- read_csv("../text_analysis/draft_readability_contributing.csv")
+#getting basic stats for the readme readability
+median(readme_df$flesch_reading_ease)
+median(readme_df$linsear_write_formula)
+median(contributing_df$reading_time)
+median(contributing_df$linsear_write_formula)
+#plotting readme reading ease
+readme_reading_ease <- ggplot(readme_df, aes(x=flesch_reading_ease, group=as.factor(subdir))) +
+geom_density(aes(color = as.factor(subdir), fill=as.factor(subdir)), alpha=0.2, position="identity") +
+scale_color_manual(values = subdirColors) +
+xlim(-10, 90) +
+ylab("readme density") +
+guides(fill="none", color="none")+
+theme_bw()
+readme_reading_ease
+#plotting readme reading time
+readme_reading_time_plot <- ggplot(readme_df, aes(x=reading_time, group=as.factor(subdir))) +
+geom_density(aes(color = as.factor(subdir), fill=as.factor(subdir)), alpha=0.2, position="identity") +
+scale_color_manual(values = subdirColors) +
+xlim(-10, 90) +
+ylab("readme density") +
+guides(fill="none", color="none")+
+theme_bw()
+# establishing the color scheme
+subdirColors <-
+setNames( c('firebrick1', 'forestgreen', 'cornflowerblue')
+, levels(contributing_df$subdir)  )
+#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(-10, 90) +
+ylab("readme density") +
+guides(fill="none", color="none")+
+theme_bw()
+#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(-10, 90) +
+ylab("readme density") +
+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))) +
+geom_density(aes(color = as.factor(subdir), fill=as.factor(subdir)), alpha=0.2, position="identity") +
+xlim(-10, 90) +
+ylab("contributing density") +
+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(-10, 90) +
+theme_bw() +
+theme(legend.position = "top")
+contributing_reading_ease
+grid.arrange(contributing_reading_ease, contributing_reading_time_plot,readme_reading_ease, readme_reading_time_plot, nrow = 2)
+# plotting contributing linsear writing formula
+contributing_linsear_plot <- ggplot(contributing_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) +
+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))) +
+geom_density(aes(color = as.factor(subdir), fill=as.factor(subdir)), alpha=0.2, position="identity") +
+xlim(-10, 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))) +
+geom_density(aes(color = as.factor(subdir), fill=as.factor(subdir)), alpha=0.2, position="identity") +
+xlim(-10, 70) +
+guides(fill="none", color="none")+
+theme_bw()
+grid.arrange(contributing_reading_ease, contributing_reading_time_plot,contributing_linsear_plot, contributing_mcalpine_eflaw readme_reading_ease, readme_reading_time_plot, nrow = 2)
+grid.arrange(contributing_reading_ease, contributing_reading_time_plot,contributing_linsear_plot, contributing_mcalpine_eflaw, readme_reading_ease, readme_reading_time_plot, nrow = 2)
+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(-10, 30) +
+ylab("readme density") +
+guides(fill="none", color="none")+
+theme_bw()
+# plotting contributing linsear writing formula
+contributing_linsear_plot <- ggplot(contributing_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(-10, 30) +
+guides(fill="none", color="none")+
+theme_bw()
+readme_mcalpine_eflaw <- ggplot(readme_df, aes(x=mcalpine_eflaw, group=as.factor(subdir))) +
+geom_density(aes(color = as.factor(subdir), fill=as.factor(subdir)), alpha=0.2, position="identity") +
+xlim(-10, 60) +
+guides(fill="none", color="none")+
+theme_bw()
+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)
+# 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(-10, 60) +
+guides(fill="none", color="none")+
+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()
+#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()
+# 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")
+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)
+library(tidyverse)
+library(plyr)
+library(stringr)
+try(setwd(dirname(rstudioapi::getActiveDocumentContext()$path)))
+#load in data
+contrib_df <- read_csv("../final_data/deb_contrib_pop_change.csv")
+View(contrib_df)
+expanded_contrib_data <- expand_timeseries(contrib_df[1,])
+for (i in 2:nrow(contrib_df)){
+expanded_contrib_data <- rbind(expanded_contrib_data, expand_timeseries(contrib_df[i,]))
+}
+#some expansion needs to happens for each project
+expand_timeseries <- function(project_row) {
+longer <- project_row |>
+pivot_longer(cols = ends_with("new"),
+names_to = "window",
+values_to = "count") |>
+unnest(count) |>
+mutate(after_doc = as.numeric(str_detect(window, "after"))) |>
+mutate(is_collab = as.numeric(str_detect(window, "collab")))
+return(longer)
+}
+expanded_contrib_data <- expand_timeseries(contrib_df[1,])
+View(expanded_contrib_data)

R/documentReadabilityAnalysis.R

@@ -30,7 +30,7 @@ readme_linsear_plot <- ggplot(readme_df, aes(x=linsear_write_formula, group=as.f
 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(-10, 90) +
+  xlim(-5, 90) +
   ylab("readme density") +
   guides(fill="none", color="none")+
   theme_bw() 
@@ -39,10 +39,24 @@ readme_reading_ease
 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(-10, 90) +
+  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 |>
@@ -57,21 +71,24 @@ 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(-30, 30) +
+  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(-10, 90) +
+  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(-10, 70) +
+  xlim(-5, 60) +
   guides(fill="none", color="none")+
   theme_bw()
 # plotting contributing reading ease
@@ -79,8 +96,8 @@ contributing_reading_ease <- ggplot(contributing_df, aes(x=flesch_reading_ease,
   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(-10, 90) +
+  xlim(-5, 90) +
   theme_bw() + 
   theme(legend.position = "top") 
 contributing_reading_ease 
-grid.arrange(contributing_reading_ease, contributing_reading_time_plot,readme_reading_ease, readme_reading_time_plot, nrow = 2)
+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)

R/popRDDAnalyssis.R

@@ -36,28 +36,39 @@ contrib_pop_contrib <- expanded_contrib_data[which(expanded_contrib_data$is_coll
 #import models 
 library(lme4)
 library(optimx)
-collab_readme_model <- glmer.nb(log1pcount ~ after_doc + (after_doc| upstream_vcs_link), data=collab_pop_readme)
+library(MASS)
+simple_collab_readme_model <- glm.nb(count ~ as.factor(after_doc), data=collab_pop_readme)
+summary(simple_collab_readme_model)
+qqnorm(residuals(simple_collab_readme_model))
+#
+cor.test(collab_pop_readme$count, collab_pop_readme$after_doc)
+# I don't think MLM is the right one
+collab_readme_model <- glmer.nb(log1pcount ~ as.factor(after_doc) + (after_doc| upstream_vcs_link), data=collab_pop_readme)
 summary(collab_readme_model)
-saveRDS(collab_readme_model, "0510_pop_rm_collab.rda")
+saveRDS(collab_readme_model, "final_models/0623_pop_rm_collab.rda")
 crm_residuals <- residuals(collab_readme_model)
 qqnorm(crm_residuals)
 contrib_readme_model <- glmer.nb(log1pcount ~ after_doc + (after_doc| upstream_vcs_link), data=contrib_pop_readme)
 summary(contrib_readme_model)
-saveRDS(contrib_readme_model, "0510_pop_rm_contrib.rda")
+saveRDS(contrib_readme_model, "final_models/0623_pop_rm_contrib.rda")
+#contrib_readme_model <- load("final_models/0510_pop_rm_contrib.rda")
 conrm_residuals <- residuals(contrib_readme_model)
 qqnorm(conrm_residuals)
 collab_contrib_model <- glmer.nb(log1pcount ~ after_doc + (after_doc| upstream_vcs_link), data=collab_pop_contrib)
 summary(collab_contrib_model)
-saveRDS(collab_contrib_model, "0510_pop_contrib_collab.rda")
+saveRDS(collab_contrib_model, "final_models/0623_pop_contrib_collab.rda")
 contrib_contrib_model <- glmer.nb(log1pcount ~ after_doc + (after_doc| upstream_vcs_link), data=contrib_pop_contrib)
 summary(contrib_contrib_model)
-saveRDS(contrib_contrib_model, "0510_pop_contrib_contrib.rda")
+saveRDS(contrib_contrib_model, "final_models/0623_pop_contrib_contrib.rda")
 
 library(ggplot2)
+contrib_pop_readme |>
+  ggplot(aes(x = after_doc, y = log1pcount)) +
+
 expanded_readme_data |>
-  ggplot(aes(x = after_doc, y = log1pcount, col = as.factor(is_collab))) +
-  geom_point() + geom_jitter()
+  ggplot(aes(x = after_doc, y = log1pcount, col = as.factor(after_doc))) +
+  geom_violin()
 
 expanded_contrib_data |>
-  ggplot(aes(x = after_doc, y = count, col = as.factor(is_collab))) +
-  geom_point() + geom_jitter()
+  ggplot(aes(x = after_doc, y = count, col = as.factor(after_doc))) +
+  geom_violin()