diff --git a/.gitignore b/.gitignore
new file mode 100644
index 0000000..5b6a065
--- /dev/null
+++ b/.gitignore
@@ -0,0 +1,4 @@
+.Rproj.user
+.Rhistory
+.RData
+.Ruserdata
diff --git a/R/.Rhistory b/R/.Rhistory
index 5426cf6..2e1d1a7 100644
--- a/R/.Rhistory
+++ b/R/.Rhistory
@@ -1,512 +1,512 @@
-summary(lm1)
-lm1 <- glm.nb(after_contrib_new ~ reading_time, data = contrib_total_df)
-qqnorm(residuals(lm1))
-summary(lm1)
-lm1 <- glm.nb(after_contrib_new ~ flesch_reading_ease, data = contrib_total_df)
-qqnorm(residuals(lm1))
-summary(lm1)
-contrib_readability_df <- contrib_readability_df |>
-mutate(project_name = map_chr(filename, ~ {
-parts <- str_split(.x, pattern = "_")[[1]]
-if (length(parts) >= 1) {
-head(parts, -1)
-} else {
-NA_character_
-}
-}))
-parts[1] + parts[2]
-contrib_readability_df <- contrib_readability_df |>
-mutate(project_name = map_chr(filename, ~ {
-parts <- str_split(.x, pattern = "_")[[1]]
-if (length(parts) >= 1) {
-parts[1] + parts[2]
-} else {
-NA_character_
-}
-}))
-contrib_readability_df <- contrib_readability_df |>
-mutate(project_name = map_chr(filename, ~ {
-parts <- str_split(.x, pattern = "_")[[1]]
-if (length(parts) >= 1) {
-paste(head(parts, -1), collapse="")
-} else {
-NA_character_
-}
-}))
-View(contrib_readability_df)
-#libraries
-library(stringr)
-contrib_df <- read_csv("../final_data/deb_contrib_did.csv")
-contrib_pop_df <- read_csv("../final_data/deb_contrib_pop_change.csv")
-contrib_readability_df <- read_csv('../text_analysis/dwo_readability_contributing.csv')
-contrib_pop_df <- contrib_pop_df |>
-mutate(project_name = map_chr(upstream_vcs_link, ~ {
-parts <- str_split(.x, pattern = "/")[[1]]
-if (length(parts) >= 1) {
-parts[length(parts)]
-} else {
-NA_character_
-}
-}))
-contrib_readability_df <- contrib_readability_df |>
-mutate(project_name = map_chr(filename, ~ {
-parts <- str_split(.x, pattern = "_")[[1]]
-if (length(parts) >= 1) {
-paste(head(parts, -1), collapse="_")
-} else {
-NA_character_
-}
-}))
-contrib_total_df <- contrib_pop_df |>
-join(contrib_readability_df, by="project_name")
-View(contrib_total_df)
-# test regressions
-library(MASS)
-lm1 <- glm.nb(after_contrib_new ~ flesch_reading_ease, data = contrib_total_df)
-qqnorm(residuals(lm1))
-summary(lm1)
-lm1 <- glm.nb(after_contrib_new ~ flesch_reading_ease + age_in_days, data = contrib_total_df)
-qqnorm(residuals(lm1))
-summary(lm1)
-View(contrib_df)
-source("~/Desktop/git/24_deb_gov/R/contrib_docChar_outcomes.R")
-View(windowed_data)
-View(windowed_data)
-summed_data <- windowed_data |>
-group_by(upstream_vcs_link) |>
-summarize(total_ct_after_all = sum(ct_after_all))
-summed_data <- windowed_data |>
-filter(window="ct_after_all") |>
-group_by(upstream_vcs_link) |>
-summarize(total_ct_after_all = sum(count))
-summed_data <- windowed_data |>
-filter(window=="ct_after_all") |>
-group_by(upstream_vcs_link) |>
-summarize(total_ct_after_all = sum(count))
-View(summed_data)
-summed_data <- windowed_data |>
-filter(window=="ct_after_all") |>
-group_by(upstream_vcs_link) |>
-mutate(total_ct_after_all = sum(count))
-View(summed_data)
-summed_data <- windowed_data |>
-filter(window=="ct_after_all") |>
-group_by(upstream_vcs_link) |>
-summarize(total_ct_after_all = sum(count)) |> ungroup()
-View(summed_data)
-View(windowed_data)
-summed_data <- windowed_data |>
-filter(window=="ct_after_all") |>
-group_by(upstream_vcs_link) |>
-summarise_at(vars(count), list(name=sum))
-View(summed_data)
-summed_data <- windowed_data |>
-filter(D==1) |>
-group_by(upstream_vcs_link) |>
-summarise_at(vars(count), list(summed_count=sum))
-View(summed_data)
-source("~/Desktop/git/24_deb_gov/R/contrib_docChar_outcomes.R")
-contrib_total_df <- contrib_total_df|>
-join(summed_data, by=upstream_vcs_link)
-contrib_total_df <- contrib_pop_df |>
-join(contrib_readability_df, by="project_name")
-View(contrib_total_df)
-contrib_total_df <- contrib_total_df|>
-join(summed_data, by=upstream_vcs_link)
-View(summed_data)
-contrib_total_df <- contrib_total_df|>
-join(summed_data, by="upstream_vcs_link")
-View(contrib_total_df)
-View(contrib_df)
-source("~/Desktop/git/24_deb_gov/R/contrib_docChar_outcomes.R")
-#outcome variable that is number of commits by number of new contributors
-contrib_total_df$commit_by_contrib = contrib_total_df$summed_count * contrib_total_df$after_contrib_new
-# test regressions
-library(MASS)
-lm1 <- glm.nb(after_contrib_new ~ flesch_reading_ease + age_in_days, data = contrib_total_df)
-qqnorm(residuals(lm1))
-summary(lm1)
-lm1 <- glm.nb(commit_by_contrib ~ flesch_reading_ease + age_in_days, data = contrib_total_df)
-qqnorm(residuals(lm1))
-summary(lm1)
-View(contrib_total_df)
-lm1 <- glm.nb(commit_by_contrib ~ word_count, data = contrib_total_df)
-qqnorm(residuals(lm1))
-summary(lm1)
-contrib_total_df$scaled_outcome = scale(contrib_total_df$commit_by_contrib)
-lm1 <- glm.nb(scaled_outcome ~ word_count + flesch_kincaid, data = contrib_total_df)
-lm1 <- glm.nb(scaled_outcome ~ word_count + flesch_kincaid_grade, data = contrib_total_df)
-contrib_total_df$logged_outcome = log1p(contrib_total_df$commit_by_contrib)
-# test regressions
-library(MASS)
-lm1 <- glm.nb(scaled_outcome ~ word_count + flesch_kincaid_grade, data = contrib_total_df)
-lm1 <- glm.nb(logged_outcome ~ word_count + flesch_kincaid_grade, data = contrib_total_df)
-qqnorm(residuals(lm1))
-summary(lm1)
-lm1 <- glm.nb(logged_outcome ~ word_count + flesch_kincaid_grade + linsear_write_formula, data = contrib_total_df)
-qqnorm(residuals(lm1))
-summary(lm1)
-contrib_total_df$scaled_outcome = scale(contrib_total_df$commit_by_contrib)
-# test regressions
-library(MASS)
-lm1 <- lm(scaled_outcome ~ word_count + flesch_kincaid_grade + linsear_write_formula, data = contrib_total_df)
-qqnorm(residuals(lm1))
-summary(lm1)
-lm1 <- glm.nb(logged_outcome ~ word_count + flesch_kincaid_grade + linsear_write_formula, data = contrib_total_df)
-qqnorm(residuals(lm1))
-summary(lm1)
-lm1 <- glm.nb(logged_outcome ~ word_count + flesch_kincaid_grade + linsear_write_formula + mcalpine_eflaw, data = contrib_total_df)
-qqnorm(residuals(lm1))
-summary(lm1)
-lm1 <- glm.nb(logged_outcome ~ word_count + flesch_kincaid_grade + linsear_write_formula + mcalpine_eflaw + dale_chall_readability_score, data = contrib_total_df)
-qqnorm(residuals(lm1))
-summary(lm1)
-lm1 <- glm.nb(logged_outcome ~ word_count + dale_chall_readability_score, data = contrib_total_df)
-qqnorm(residuals(lm1))
-summary(lm1)
-lm1 <- glm.nb(logged_outcome ~ word_count + reading_time, data = contrib_total_df)
-qqnorm(residuals(lm1))
-summary(lm1)
-lm1 <- glm.nb(commit_by_contrib ~ word_count + reading_time, data = contrib_total_df)
-qqnorm(residuals(lm1))
-summary(lm1)
-lm1 <- glm.nb(commit_by_contrib ~ word_count + flesch_kincaid_grade, data = contrib_total_df)
-qqnorm(residuals(lm1))
-summary(lm1)
-#libraries
-library(stringr)
-readme_df <- read_csv("../final_data/deb_readme_did.csv")
-readme_pop_df <- read_csv("../final_data/deb_readme_pop_change.csv")
-readme_readability_df <- read_csv('../text_analysis/dwo_readability_readmeuting.csv')
-source("~/Desktop/git/24_deb_gov/R/readme_docChar_outcomes.R")
-source("~/Desktop/git/24_deb_gov/R/readme_docChar_outcomes.R")
-lm1 <- glm.nb(commit_by_readme ~ word_count + flesch_kincaid_grade, data = readme_total_df)
-View(readme_readability_df)
-readme_readability_df <- readme_readability_df |>
-mutate(project_name = map_chr(filename, ~ {
-parts <- str_split(.x, pattern = "_")[[1]]
-if (length(parts) >= 1) {
-paste(head(parts, -1), collapse="_")
-} else {
-NA_character_
-}
-}))
-readme_total_df <- readme_pop_df |>
-join(readme_readability_df, by="project_name")
-readme_total_df <- readme_total_df|>
-join(summed_data, by="upstream_vcs_link")
-#outcome variable that is number of commits by number of new readmeutors
-readme_total_df$commit_by_readme = readme_total_df$summed_count * readme_total_df$after_readme_new
-readme_total_df$logged_outcome = log(readme_total_df$commit_by_readme)
-View(readme_total_df)
-View(readme_total_df)
-#outcome variable that is number of commits by number of new readmeutors
-readme_total_df$commit_by_readme = readme_total_df$summed_count * readme_total_df$after_readme_new
-View(readme_total_df)
-View(readme_readability_df)
-readme_pop_df[readme_pop_df['upstream_vcs_link'] == "https://github.com/agateau/yokadi/issues/new", "project_name"] = "yokadi"
-View(readme_pop_df)
-readme_pop_df[readme_pop_df['upstream_vcs_link'] == "https://github.com/SciRuby/rb-gsl/issues/new", "project_name"] = "rb-gsl"
-source("~/Desktop/git/24_deb_gov/R/readme_docChar_outcomes.R")
-readme_readability_df <- readme_readability_df |>
-mutate(project_name = map_chr(filename, ~ {
-parts <- str_split(.x, pattern = "_")[[1]]
-if (length(parts) >= 1) {
-paste(head(parts, -1), collapse="_")
-} else {
-NA_character_
-}
-}))
-readme_readability_df[readme_readability_df['filename'] == "yder_README_8md.html", "project_name"] = "yder"
-readme_readability_df[readme_readability_df['filename'] == "pg_filedump.git_README.pg_filedump", "project_name"] = "pg_filedump.git"
-readme_readability_df[readme_readability_df['filename'] == "openvas_UPGRADE_README", "project_name"] = "openvas"
-readme_readability_df[readme_readability_df['filename'] == "hyphen.git_README_hyph_en_US.txt", "project_name"] = "hyphen.git"
-readme_readability_df[readme_readability_df['filename'] == "cycle.git_README_ru.html", "project_name"] = "cycle.git"
-readme_readability_df[readme_readability_df['filename'] == "diffuse.git_README_ru", "project_name"] = "diffuse.git"
-readme_readability_df[readme_readability_df['filename'] == "CheMPS2_README_8md_source.html", "project_name"] = "CheMPS2"
-readme_readability_df[readme_readability_df['filename'] == "sleuthkit_README_win32.txt", "project_name"] = "sleuthkit"
-readme_readability_df[readme_readability_df['filename'] == "Lmod_README_lua_modulefiles.txt", "project_name"] = "Lmod"
-readme_readability_df[readme_readability_df['filename'] == "engauge_debian_README_for_osx", "project_name"] = "engauge_debian"
-readme_total_df <- readme_pop_df |>
-join(readme_readability_df, by="project_name")
-readme_total_df <- readme_total_df|>
-join(summed_data, by="upstream_vcs_link")
-#outcome variable that is number of commits by number of new readmeutors
-readme_total_df$commit_by_readme = readme_total_df$summed_count * readme_total_df$after_readme_new
-View(readme_total_df)
-readme_total_df$logged_outcome = log(readme_total_df$commit_by_readme)
-#outcome variable that is number of commits by number of new readmeutors
-readme_total_df$commit_by_readme = readme_total_df$summed_count * readme_total_df$after_readme_new
-#outcome variable that is number of commits by number of new readmeutors
-readme_total_df$commit_by_contrib = readme_total_df$summed_count * readme_total_df$after_readme_new
-#outcome variable that is number of commits by number of new readmeutors
-readme_total_df$commit_by_contrib = NA
-readme_total_df$commit_by_contrib = readme_total_df$summed_count * readme_total_df$after_readme_new
-View(readme_total_df)
-View(readme_total_df)
-readme_total_df$commit_by_contrib = readme_total_df$summed_count * readme_total_df$after_contrib_new
-lm1 <- glm.nb(commit_by_contrib ~ word_count + flesch_kincaid_grade, data = readme_total_df)
-qqnorm(residuals(lm1))
-summary(lm1)
-readme_total_df$logged_outcome = log(readme_total_df$commit_by_readme)
-readme_total_df$logged_outcome = log(readme_total_df$commit_by_contrib)
-lm1 <- glm.nb(commit_by_contrib ~ word_count + flesch_kincaid_grade, data = readme_total_df)
-qqnorm(residuals(lm1))
-summary(lm1)
-lm1 <- glm.nb(summed_count ~ word_count + flesch_kincaid_grade, data = readme_total_df)
-qqnorm(residuals(lm1))
-summary(lm1)
-lm1 <- glm.nb(commit_by_contrib ~ word_count + flesch_kincaid_grade, data = readme_total_df)
-qqnorm(residuals(lm1))
-summary(lm1)
-lm1 <- glm.nb(after_contrib_new ~ word_count + flesch_kincaid_grade, data = readme_total_df)
-qqnorm(residuals(lm1))
-summary(lm1)
-lm1 <- glm.nb(after_contrib_new ~ word_count + reading_time, data = readme_total_df)
-qqnorm(residuals(lm1))
-summary(lm1)
-lm1 <- glm.nb(commit_by_contrib ~ word_count + reading_time, data = readme_total_df)
-qqnorm(residuals(lm1))
-summary(lm1)
-lm1 <- glm.nb(reading_time ~ word_count , data = readme_total_df)
-qqnorm(residuals(lm1))
-summary(lm1)
-View(readme_total_df)
-lm1 <- glm.nb(reading_time ~ flesch_reading_ease , data = readme_total_df)
-qqnorm(residuals(lm1))
-summary(lm1)
-lm1 <- glm.nb(flesch_reading_ease ~ reading_time , data = readme_total_df)
-lm1 <- glm.nb(commit_by_contrib ~ reading_time , data = readme_total_df)
-qqnorm(residuals(lm1))
-summary(lm1)
-lm1 <- glm.nb(commit_by_contrib ~ reading_time + linsear_write_formula , data = readme_total_df)
-qqnorm(residuals(lm1))
-summary(lm1)
-readme_total_df$commit_by_contrib = readme_total_df$summed_count * (readme_total_df$after_contrib_new + 1)
-readme_total_df$logged_outcome = log(readme_total_df$commit_by_contrib)
-lm1 <- glm.nb(commit_by_contrib ~ reading_time + linsear_write_formula , data = readme_total_df)
-qqnorm(residuals(lm1))
-summary(lm1)
-readme_total_df$logged_outcome = log1p(readme_total_df$commit_by_contrib)
-lm1 <- glm.nb(logged_outcome ~ reading_time + linsear_write_formula , data = readme_total_df)
-qqnorm(residuals(lm1))
-summary(lm1)
-lm1 <- glm.nb(logged_outcome ~ reading_time + linsear_write_formula + flesch_reading_ease, data = readme_total_df)
-qqnorm(residuals(lm1))
-summary(lm1)
-lm1 <- glm.nb(logged_outcome ~ reading_time + linsear_write_formula + flesch_reading_ease + mcalpine_eflaw, data = readme_total_df)
-qqnorm(residuals(lm1))
-summary(lm1)
-lm1 <- glm.nb(summed_count~ reading_time + linsear_write_formula + flesch_reading_ease + mcalpine_eflaw, data = readme_total_df)
-qqnorm(residuals(lm1))
-summary(lm1)
-lm1 <- glm.nb(summed_count~ reading_time + linsear_write_formula + flesch_reading_ease + mcalpine_eflaw + word_count, data = readme_total_df)
-qqnorm(residuals(lm1))
-summary(lm1)
-lm1 <- glm.nb(logged_outcome~ reading_time + linsear_write_formula + flesch_reading_ease + mcalpine_eflaw + word_count, data = readme_total_df)
-qqnorm(residuals(lm1))
-summary(lm1)
-source("~/Desktop/git/24_deb_gov/R/contrib_docChar_outcomes.R")
-lm1 <- glm.nb(logged_outcome~ reading_time + linsear_write_formula + flesch_reading_ease + mcalpine_eflaw + word_count, data = contrib_total_df)
-contrib_total_df$logged_outcome = log1p(contrib_total_df$commit_by_contrib)
-lm1 <- glm.nb(logged_outcome ~ reading_time + linsear_write_formula + flesch_reading_ease + mcalpine_eflaw + word_count, data = contrib_total_df)
-qqnorm(residuals(lm1))
-summary(lm1)
-lm1 <- glm.nb(summed_count ~ reading_time + linsear_write_formula + flesch_reading_ease + mcalpine_eflaw + word_count, data = contrib_total_df)
-qqnorm(residuals(lm1))
-summary(lm1)
-contrib_topics_df <- read_csv("../text_analysis/contrib_file_topic_distributions.csv")
+, c(0,1,2)  )
+contrib_g <- contrib_groupings |>
+ggplot(aes(x=rank, y=estimate, col = as.factor(ranef_grouping))) +
+geom_linerange(aes(ymin= conf.low, ymax= conf.high)) +
+scale_color_manual(values = subdirColors, labels=c('CI < 0', '0 in CI', '0 < CI')) +
+theme_bw() +
+theme(legend.position = "top")  +
+labs(x="RE Coefficient Rank", y="RE Coefficient Estimate", color="Estimate Grouping")
+contrib_g
+subdirColors <-
+setNames( c('#942e55', '#78c58a', '#9b6e29')
+, c(0,1,2)  )
+contrib_g <- contrib_groupings |>
+ggplot(aes(x=rank, y=estimate, col = as.factor(ranef_grouping))) +
+geom_linerange(aes(ymin= conf.low, ymax= conf.high)) +
+scale_color_manual(values = subdirColors, labels=c('CI < 0', '0 in CI', '0 < CI')) +
+theme_bw() +
+theme(legend.position = "top")  +
+labs(x="RE Coefficient Rank", y="RE Coefficient Estimate", color="Estimate Grouping")
+contrib_g
+subdirColors <-
+setNames( c('#a1a596', '#557784', '#2f6382')
+, c(0,1,2)  )
+contrib_g <- contrib_groupings |>
+ggplot(aes(x=rank, y=estimate, col = as.factor(ranef_grouping))) +
+geom_linerange(aes(ymin= conf.low, ymax= conf.high)) +
+scale_color_manual(values = subdirColors, labels=c('CI < 0', '0 in CI', '0 < CI')) +
+theme_bw() +
+theme(legend.position = "top")  +
+labs(x="RE Coefficient Rank", y="RE Coefficient Estimate", color="Estimate Grouping")
+contrib_g
+subdirColors <-
+setNames( c('#a3b0c9', '#101f31', '#28578d')
+, c(0,1,2)  )
+readme_g <- readme_groupings |>
+ggplot(aes(x=rank, y=estimate, col = as.factor(ranef_grouping))) +
+geom_linerange(aes(ymin= conf.low, ymax= conf.high)) +
+scale_color_manual(values = subdirColors) +
+guides(fill="none", color="none")+
+theme_bw() +
+labs(x="RE Coefficient Rank", y="RE Coefficient Estimate", color="Estimate Grouping")
+readme_g
+contrib_g <- contrib_groupings |>
+ggplot(aes(x=rank, y=estimate, col = as.factor(ranef_grouping))) +
+geom_linerange(aes(ymin= conf.low, ymax= conf.high)) +
+scale_color_manual(values = subdirColors, labels=c('CI < 0', '0 in CI', '0 < CI')) +
+theme_bw() +
+theme(legend.position = "top")  +
+labs(x="RE Coefficient Rank", y="RE Coefficient Estimate", color="Estimate Grouping")
+contrib_g
+subdirColors <-
+setNames( c('#f8f06b', '#ca7780', '#a13795')
+, c(0,1,2)  )
+contrib_g <- contrib_groupings |>
+ggplot(aes(x=rank, y=estimate, col = as.factor(ranef_grouping))) +
+geom_linerange(aes(ymin= conf.low, ymax= conf.high)) +
+scale_color_manual(values = subdirColors, labels=c('CI < 0', '0 in CI', '0 < CI')) +
+theme_bw() +
+theme(legend.position = "top")  +
+labs(x="RE Coefficient Rank", y="RE Coefficient Estimate", color="Estimate Grouping")
+contrib_g
 library(tidyverse)
-contrib_topics_df <- read_csv("../text_analysis/contrib_file_topic_distributions.csv")
-View(contrib_topics_df)
-source("~/Desktop/git/24_deb_gov/R/contrib_topic_outcomes.R")
-source("~/Desktop/git/24_deb_gov/R/contrib_topic_outcomes.R")
-source("~/Desktop/git/24_deb_gov/R/contrib_docChar_outcomes.R")
-source("~/Desktop/git/24_deb_gov/R/contrib_topic_outcomes.R")
-source("~/Desktop/git/24_deb_gov/R/contrib_topic_outcomes.R")
-source("~/Desktop/git/24_deb_gov/R/contrib_topic_outcomes.R")
-lm1 <- glm.nb(summed_count ~ t0 + t1 + t2 + t3, data = contrib_total_df)
-#running regressions
-library(MASS)
-lm1 <- glm.nb(summed_count ~ t0 + t1 + t2 + t3, data = contrib_total_df)
-source("~/Desktop/git/24_deb_gov/R/contrib_topic_outcomes.R")
-library(stringr)
 library(plyr)
-contrib_topics_df <- read_csv("../text_analysis/contrib_file_topic_distributions.csv")
-contrib_df <- read_csv("../final_data/deb_contrib_did.csv")
-contrib_pop_df <- read_csv("../final_data/deb_contrib_pop_change.csv")
-#get the contribution count
-#some preprocessing and expansion
-col_order <- c("upstream_vcs_link", "age_in_days", "first_commit", "first_commit_dt", "event_gap", "event_date",  "event_hash", "before_all_ct", "after_all_ct", "before_mrg_ct", "after_mrg_ct", "before_auth_new", "after_auth_new", "before_commit_new",  "after_commit_new")
-contrib_df <- contrib_df[,col_order]
-contrib_df$ct_before_all <- str_split(gsub("[][]","", contrib_df$before_all_ct), ", ")
-contrib_df$ct_after_all <- str_split(gsub("[][]","", contrib_df$after_all_ct), ", ")
-contrib_df$ct_before_mrg <- str_split(gsub("[][]","", contrib_df$before_mrg_ct), ", ")
-contrib_df$ct_after_mrg <- str_split(gsub("[][]","", contrib_df$after_mrg_ct), ", ")
-drop <- c("before_all_ct", "before_mrg_ct", "after_all_ct", "after_mrg_ct")
-contrib_df = contrib_df[,!(names(contrib_df) %in% drop)]
-# 2 some expansion needs to happens for each project
-expand_timeseries <- function(project_row) {
-longer <- project_row |>
-pivot_longer(cols = starts_with("ct"),
-names_to = "window",
-values_to = "count") |>
-unnest(count)
-longer$observation_type <- gsub("^.*_", "", longer$window)
-longer <- ddply(longer, "observation_type", transform, week=seq(from=0, by=1, length.out=length(observation_type)))
-longer$count <- as.numeric(longer$count)
-#longer <- longer[which(longer$observation_type == "all"),]
-return(longer)
-}
-expanded_data <- expand_timeseries(contrib_df[1,])
-for (i in 2:nrow(contrib_df)){
-expanded_data <- rbind(expanded_data, expand_timeseries(contrib_df[i,]))
-}
-#filter out the windows of time that we're looking at
-window_num <- 8
-windowed_data <- expanded_data |>
-filter(week >= (27 - window_num) & week <= (27 + window_num)) |>
-mutate(D = ifelse(week > 27, 1, 0))
-summed_data <- windowed_data |>
-filter(D==1) |>
-group_by(upstream_vcs_link) |>
-summarise_at(vars(count), list(summed_count=sum))
-#concat dataframes into central data
-contrib_pop_df <- contrib_pop_df |>
-mutate(project_name = map_chr(upstream_vcs_link, ~ {
-parts <- str_split(.x, pattern = "/")[[1]]
-if (length(parts) >= 1) {
-parts[length(parts)]
-} else {
-NA_character_
-}
-}))
-contrib_topic_df <- contrib_topic_df |>
-mutate(project_name = map_chr(filename, ~ {
-parts <- str_split(.x, pattern = "_")[[1]]
-if (length(parts) >= 1) {
-paste(head(parts, -1), collapse="_")
-} else {
-NA_character_
-}
-}))
-contrib_topics_df <- contrib_topics_df |>
-mutate(project_name = map_chr(filename, ~ {
-parts <- str_split(.x, pattern = "_")[[1]]
-if (length(parts) >= 1) {
-paste(head(parts, -1), collapse="_")
-} else {
-NA_character_
-}
-}))
-contrib_total_df <- contrib_pop_df |>
-join(contrib_topics_df, by="project_name")
-contrib_total_df <- contrib_total_df|>
-join(summed_data, by="upstream_vcs_link")
-#outcome variable that is number of commits by number of new contributors
-contrib_total_df$commit_by_contrib = contrib_total_df$summed_count * contrib_total_df$after_contrib_new
-contrib_total_df$logged_outcome = log1p(contrib_total_df$commit_by_contrib)
-#running regressions
-library(MASS)
-lm1 <- glm.nb(summed_count ~ t0 + t1 + t2 + t3, data = contrib_total_df)
-qqnorm(residuals(lm1))
-summary(lm1)
-View(contrib_total_df)
-lm1 <- glm.nb(summed_count ~ t3, data = contrib_total_df)
-qqnorm(residuals(lm1))
-summary(lm1)
-lm1 <- glm.nb(summed_count ~ t3 + t2 + t1, data = contrib_total_df)
-qqnorm(residuals(lm1))
-summary(lm1)
-lm1 <- glm.nb(summed_count ~ t3 + t2 + t1 + t0, data = contrib_total_df)
-qqnorm(residuals(lm1))
-summary(lm1)
-lm1 <- glm.nb(summed_count ~ t0 + t1 + t2 + t3, data = contrib_total_df)
-qqnorm(residuals(lm1))
-summary(lm1)
-lm1 <- lm(summed_count ~ t0 + t1 + t2 + t3, data = contrib_total_df)
-qqnorm(residuals(lm1))
-summary(lm1)
-lm1 <- glm.nb(summed_count ~ t0 + t1 + t2 + t3, data = contrib_total_df)
-qqnorm(residuals(lm1))
-summary(lm1)
-lm1 <- glm.nb(summed_count ~ t1 + t2 + t3, data = contrib_total_df)
-qqnorm(residuals(lm1))
-summary(lm1)
-lm1 <- glm.nb(summed_count ~ t3, data = contrib_total_df)
-qqnorm(residuals(lm1))
-summary(lm1)
-lm1 <- glm.nb(commit_by_contrib ~ t3, data = contrib_total_df)
-qqnorm(residuals(lm1))
-summary(lm1)
-lm1 <- glm.nb(commit_by_contrib ~ t1 + t2 +t3, data = contrib_total_df)
-qqnorm(residuals(lm1))
-summary(lm1)
-lm1 <- glm.nb(commit_by_contrib ~ t3, data = contrib_total_df)
-qqnorm(residuals(lm1))
-summary(lm1)
-lm1 <- glm.nb(commit_by_contrib ~ t2, data = contrib_total_df)
-qqnorm(residuals(lm1))
-summary(lm1)
-lm1 <- glm.nb(commit_by_contrib ~ t1, data = contrib_total_df)
-qqnorm(residuals(lm1))
-summary(lm1)
-lm1 <- glm.nb(commit_by_contrib ~ t3, data = contrib_total_df)
-qqnorm(residuals(lm1))
-summary(lm1)
-source("~/Desktop/git/24_deb_gov/R/readme_topic_outcomes.R")
-#outcome variable that is number of commits by number of new readmeutors
-readme_total_df$commit_by_contrib = readme_total_df$summed_count *readme_total_df$after_contrib_new
-readme_total_df$logged_outcome = log1p(readme_total_df$commit_by_readme)
-#running regressions
-library(MASS)
-lm1 <- glm.nb(commit_by_readme ~ t3, data = readme_total_df)
-lm1 <- glm.nb(commit_by_contrib ~ t3, data = readme_total_df)
-qqnorm(residuals(lm1))
-summary(lm1)
-lm1 <- glm.nb(commit_by_contrib ~ t0, data = readme_total_df)
-qqnorm(residuals(lm1))
-summary(lm1)
-lm1 <- glm.nb(commit_by_contrib ~ t1, data = readme_total_df)
-qqnorm(residuals(lm1))
-summary(lm1)
-lm1 <- glm.nb(commit_by_contrib ~ t7, data = readme_total_df)
-qqnorm(residuals(lm1))
-summary(lm1)
-lm1 <- glm.nb(commit_by_contrib ~ t0+t1+t7, data = readme_total_df)
-qqnorm(residuals(lm1))
-summary(lm1)
-lm1 <- glm.nb(commit_by_contrib ~ t0+t1+t2+t7, data = readme_total_df)
-qqnorm(residuals(lm1))
-summary(lm1)
-lm1 <- glm.nb(commit_by_contrib ~ t0+t1+t2+t7+t3, data = readme_total_df)
-qqnorm(residuals(lm1))
-summary(lm1)
-lm1 <- glm.nb(commit_by_contrib ~ t0+t1+t2+t7+t3 + t4, data = readme_total_df)
-qqnorm(residuals(lm1))
-summary(lm1)
-lm1 <- glm.nb(commit_by_contrib ~ t0+t1+t2+t7+t3 +t4 + t5 + t6, data = readme_total_df)
-qqnorm(residuals(lm1))
-summary(lm1)
-lm1 <- glm.nb(commit_by_contrib ~ t0+t1+t2+t7+t3 +t4 + t5, data = readme_total_df)
-qqnorm(residuals(lm1))
-summary(lm1)
-source("~/Desktop/git/24_deb_gov/R/contrib_topic_outcomes.R")
-lm1 <- glm.nb(commit_by_contrib ~ t3, data = contrib_total_df)
-qqnorm(residuals(lm1))
-summary(lm1)
-lm1 <- glm.nb(commit_by_contrib ~ t0+ t1+ t3, data = contrib_total_df)
-qqnorm(residuals(lm1))
-summary(lm1)
-lm1 <- glm.nb(commit_by_contrib ~ t0+ t1+ t2+ t3, data = contrib_total_df)
-qqnorm(residuals(lm1))
-summary(lm1)
-lm1 <- glm.nb(commit_by_contrib ~ t1+ t2+ t3, data = contrib_total_df)
-qqnorm(residuals(lm1))
-summary(lm1)
-lm1 <- glm.nb(commit_by_contrib ~ t1+  t3, data = contrib_total_df)
-qqnorm(residuals(lm1))
-summary(lm1)
-lm1 <- glm.nb(commit_by_contrib ~ t2+  t3, data = contrib_total_df)
-qqnorm(residuals(lm1))
-summary(lm1)
+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")
+# establishing the color scheme
+subdirColors <-
+setNames( c('#f8f06b', '#ca7780', '#a13795')
+, levels(contributing_df$subdir)  )
+readmeSubdirColors <-
+setNames( c('#ca7780', '#a13795')
+, levels(readme_df$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)), alpha=0.35, position="identity") +
+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)), alpha=0.8, 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)
+# 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)), 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 = "horizontal",
+legend.margin = margin(6, 6, 6, 6))
+# 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)), alpha=0.35, position="identity") +
+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_linsear_plot,contributing_mcalpine_eflaw, readme_reading_ease, readme_linsear_plot, readme_mcalpine_eflaw, nrow = 2)
+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=0.4, position="identity")+
+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_ease, contributing_linsear_plot,contributing_mcalpine_eflaw, readme_reading_ease, readme_linsear_plot, readme_mcalpine_eflaw, nrow = 2)
+length_plot_all <- ggplot(all_df, aes(x=word_count, group=as.factor(type))) +
+geom_density(aes(fill = as.factor(type)), color = NA, alpha=0.4, position="identity")+
+xlim(-10, 500) +
+labs(
+x = "Word Count",
+y = "Density Across Documents",
+fill="Document Type"
+) +
+theme_bw() +
+theme(legend.position = "top")
+length_plot_all
+# 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
+grid.arrange(contributing_reading_ease, contributing_reading_time_plot, readme_reading_ease, readme_reading_time_plot, nrow = 2)
+#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()
+#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()
+# 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")
+grid.arrange(contributing_reading_ease, contributing_reading_time_plot, readme_reading_ease, readme_reading_time_plot, nrow = 2)
+# establishing the color scheme
+subdirColors <-
+setNames( c('#68293c', '#ffcf67', '#91d8f0')
+, levels(contributing_df$subdir)  )
+readmeSubdirColors <-
+setNames( c('#ffcf67', '#91d8f0')
+, levels(readme_df$subdir)  )
+#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()
+#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()
+# 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))
+# 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")
+grid.arrange(contributing_reading_ease, contributing_reading_time_plot, readme_reading_ease, readme_reading_time_plot, nrow = 2)
+source("~/Desktop/git/24_deb_gov/R/documentReadabilityAnalysis.R")
+subdirColors <-
+setNames( c('#31449c', '#4a7c85', '#c5db68')
+, c(0,1,2)  )
+contrib_g <- contrib_groupings |>
+ggplot(aes(x=rank, y=estimate, col = as.factor(ranef_grouping))) +
+geom_linerange(aes(ymin= conf.low, ymax= conf.high)) +
+scale_color_manual(values = subdirColors, labels=c('CI < 0', '0 in CI', '0 < CI')) +
+theme_bw() +
+theme(legend.position = "top")  +
+labs(x="RE Coefficient Rank", y="RE Coefficient Estimate", color="Estimate Grouping")
+contrib_g
+contrib_groupings <- read.csv('../final_data/deb_contrib_interaction_groupings.csv')
+subdirColors <-
+setNames( c('#31449c', '#4a7c85', '#c5db68')
+, c(0,1,2)  )
+contrib_g <- contrib_groupings |>
+ggplot(aes(x=rank, y=estimate, col = as.factor(ranef_grouping))) +
+geom_linerange(aes(ymin= conf.low, ymax= conf.high)) +
+scale_color_manual(values = subdirColors, labels=c('CI < 0', '0 in CI', '0 < CI')) +
+theme_bw() +
+theme(legend.position = "top")  +
+labs(x="RE Coefficient Rank", y="RE Coefficient Estimate", color="Estimate Grouping")
+contrib_g
+source("~/Desktop/git/24_deb_gov/R/gam_plot_documents.R")
+doctypeColors <-
+setNames( c('#4a7c85', '#c5db68')
+, factor(all_actions_data$document_type))
+View(all_actions_data)
+doctypeColors <-
+setNames( c('#4a7c85', '#c5db68')
+, c("CONTRIBUTING", "README"))
+time_plot <- all_actions_data |>
+ggplot(aes(x=week_offset, y=log1p_count, color=factor(document_type))) +
+labs(x="Weekly Offset", y="Log Transformed Commit Count", color="Document Type") +
+scale_fill_manual(values = doctypeColors) +
+geom_smooth() +
+geom_vline(xintercept = 0)+
+theme_bw() +
+theme(legend.position = "top")
+time_plot
+time_plot <- all_actions_data |>
+ggplot(aes(x=week_offset, y=log1p_count, color=factor(document_type))) +
+labs(x="Weekly Offset", y="Log Transformed Commit Count", color="Document Type") +
+scale_color_manual(values = doctypeColors) +
+geom_smooth() +
+geom_vline(xintercept = 0)+
+theme_bw() +
+theme(legend.position = "top")
+time_plot
+doctypeColors <-
+setNames( c('#ffcf67', '#91d8f0')
+, c("CONTRIBUTING", "README"))
+time_plot <- all_actions_data |>
+ggplot(aes(x=week_offset, y=log1p_count, color=factor(document_type))) +
+labs(x="Weekly Offset", y="Log Transformed Commit Count", color="Document Type") +
+scale_color_manual(values = doctypeColors) +
+geom_smooth() +
+geom_vline(xintercept = 0)+
+theme_bw() +
+theme(legend.position = "top")
+time_plot
+doctypeColors <-
+setNames( c('#7d1b16', '#263b90')
+, c("CONTRIBUTING", "README"))
+time_plot <- all_actions_data |>
+ggplot(aes(x=week_offset, y=log1p_count, color=factor(document_type))) +
+labs(x="Weekly Offset", y="Log Transformed Commit Count", color="Document Type") +
+scale_color_manual(values = doctypeColors) +
+geom_smooth() +
+geom_vline(xintercept = 0)+
+theme_bw() +
+theme(legend.position = "top")
+time_plot
+doctypeColors <-
+setNames( c('#995223', '#2464ad')
+, c("CONTRIBUTING", "README"))
+time_plot <- all_actions_data |>
+ggplot(aes(x=week_offset, y=log1p_count, color=factor(document_type))) +
+labs(x="Weekly Offset", y="Log Transformed Commit Count", color="Document Type") +
+scale_color_manual(values = doctypeColors) +
+geom_smooth() +
+geom_vline(xintercept = 0)+
+theme_bw() +
+theme(legend.position = "top")
+time_plot
+doctypeColors <-
+setNames( c('#ba6b44', '#5d7fbd')
+, c("CONTRIBUTING", "README"))
+time_plot <- all_actions_data |>
+ggplot(aes(x=week_offset, y=log1p_count, color=factor(document_type))) +
+labs(x="Weekly Offset", y="Log Transformed Commit Count", color="Document Type") +
+scale_color_manual(values = doctypeColors) +
+geom_smooth() +
+geom_vline(xintercept = 0)+
+theme_bw() +
+theme(legend.position = "top")
+time_plot
+doctypeColors <-
+setNames( c('#5da2d8', '#c7756a')
+, c("CONTRIBUTING", "README"))
+time_plot <- all_actions_data |>
+ggplot(aes(x=week_offset, y=log1p_count, color=factor(document_type))) +
+labs(x="Weekly Offset", y="Log Transformed Commit Count", color="Document Type") +
+scale_color_manual(values = doctypeColors) +
+geom_smooth() +
+geom_vline(xintercept = 0)+
+theme_bw() +
+theme(legend.position = "top")
+time_plot
+time_plot <- all_actions_data |>
+ggplot(aes(x=week_offset, y=count, color=factor(document_type))) +
+scale_y_log1p() +
+labs(x="Weekly Offset", y="Log Transformed Commit Count", color="Document Type") +
+scale_color_manual(values = doctypeColors) +
+geom_smooth() +
+geom_vline(xintercept = 0)+
+theme_bw() +
+theme(legend.position = "top")
+time_plot <- all_actions_data |>
+ggplot(aes(x=week_offset, y=count, color=factor(document_type))) +
+labs(x="Weekly Offset", y="Log Transformed Commit Count", color="Document Type") +
+scale_color_manual(values = doctypeColors) +
+geom_smooth() +
+geom_vline(xintercept = 0)+
+theme_bw() +
+theme(legend.position = "top")
+time_plot
+time_plot <- all_actions_data |>
+ggplot(aes(x=week_offset, y=log1p_count, color=factor(document_type))) +
+labs(x="Weekly Offset", y="Log Transformed Commit Count", color="Document Type") +
+scale_color_manual(values = doctypeColors) +
+geom_smooth() +
+geom_vline(xintercept = 0)+
+theme_bw() +
+theme(legend.position = "top")
+time_plot
+time_plot <- all_actions_data |>
+ggplot(aes(x=week_offset, y=log1p_count, color=factor(document_type))) +
+scale_y_continuous(breaks = c(0, 0.5, 1.0, 1.5),
+labels = round(c(expm1(0), expm1(0.5), expm1(1.0), exp,1(1.5)), 1))
+time_plot <- all_actions_data |>
+ggplot(aes(x=week_offset, y=log1p_count, color=factor(document_type))) +
+scale_y_continuous(breaks = c(0, 0.5, 1.0, 1.5),
+labels = round(c(expm1(0), expm1(0.5), expm1(1.0), exp,1(1.5)), 1)) +
+labs(x="Weekly Offset", y="Log Transformed Commit Count", color="Document Type") +
+scale_color_manual(values = doctypeColors) +
+geom_smooth() +
+geom_vline(xintercept = 0)+
+theme_bw() +
+theme(legend.position = "top")
+time_plot <- all_actions_data |>
+ggplot(aes(x=week_offset, y=log1p_count, color=factor(document_type))) +
+scale_y_continuous(breaks = c(0, 0.5, 1.0, 1.5),
+labels = round(c(expm1(0), expm1(0.5), expm1(1.0), expm1(1.5)), 1)) +
+labs(x="Weekly Offset", y="Log Transformed Commit Count", color="Document Type") +
+scale_color_manual(values = doctypeColors) +
+geom_smooth() +
+geom_vline(xintercept = 0)+
+theme_bw() +
+theme(legend.position = "top")
+time_plot
+time_plot <- all_actions_data |>
+ggplot(aes(x=week_offset, y=log1p_count, color=factor(document_type))) +
+scale_y_continuous(breaks = c(0, 0.5, 1.0, 1.5),
+labels = round(c(expm1(0), expm1(0.5), expm1(1.0), expm1(1.5)), 1)) +
+labs(x="Weekly Offset", y="Commit Count", color="Document Type") +
+scale_color_manual(values = doctypeColors) +
+geom_smooth() +
+geom_vline(xintercept = 0)+
+theme_bw() +
+theme(legend.position = "top")
+time_plot
+time_plot <- all_actions_data |>
+ggplot(aes(x=week_offset, y=log1p_count, color=factor(document_type))) +
+labs(x="Weekly Offset", y="Commit Count", color="Document Type") +
+scale_color_manual(values = doctypeColors) +
+geom_smooth() +
+geom_vline(xintercept = 0)+
+theme_bw() +
+theme(legend.position = "top")
+time_plot
+time_plot <- all_actions_data |>
+ggplot(aes(x=week_offset, y=log1p_count, color=factor(document_type))) +
+scale_y_continuous(breaks = c(0, 0.5, 1.0, 1.5),
+labels = round(c(expm1(0), expm1(0.5), expm1(1.0), expm1(1.5)), 1)) +
+labs(x="Weekly Offset", y="Commit Count", color="Document Type") +
+scale_color_manual(values = doctypeColors) +
+geom_smooth() +
+geom_vline(xintercept = 0)+
+theme_bw() +
+theme(legend.position = "top")
+time_plot
+time_plot <- all_actions_data |>
+ggplot(aes(x=week_offset, y=log1p_count, color=factor(document_type))) +
+labs(x="Weekly Offset", y="Commit Count", color="Document Type") +
+scale_color_manual(values = doctypeColors) +
+geom_smooth() +
+geom_vline(xintercept = 0)+
+theme_bw() +
+theme(legend.position = "top")
+time_plot
+source("~/Desktop/git/24_deb_gov/R/documentReadabilityAnalysis.R")
+length_plot_all
+length_plot_all <- ggplot(all_df, aes(x=word_count, group=as.factor(type))) +
+geom_density(aes(fill = as.factor(type)), color = NA, alpha=0.5, 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
+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
diff --git a/R/072524_contirbuting_ranef_plot.png b/R/072524_contirbuting_ranef_plot.png
new file mode 100644
index 0000000..1c9348e
Binary files /dev/null and b/R/072524_contirbuting_ranef_plot.png differ
diff --git a/R/072524_contributing_ranef_plot.png b/R/072524_contributing_ranef_plot.png
new file mode 100644
index 0000000..1c9348e
Binary files /dev/null and b/R/072524_contributing_ranef_plot.png differ
diff --git a/R/072524_gam_document introduction.png b/R/072524_gam_document introduction.png
new file mode 100644
index 0000000..e254a24
Binary files /dev/null and b/R/072524_gam_document introduction.png differ
diff --git a/R/072524_readability_density.png b/R/072524_readability_density.png
new file mode 100644
index 0000000..d38f0a2
Binary files /dev/null and b/R/072524_readability_density.png differ
diff --git a/R/0725_topic_commitoutcome_contrib.rda b/R/0725_topic_commitoutcome_contrib.rda
new file mode 100644
index 0000000..c08890b
Binary files /dev/null and b/R/0725_topic_commitoutcome_contrib.rda differ
diff --git a/R/0725_topic_commitoutcome_readme.rda b/R/0725_topic_commitoutcome_readme.rda
new file mode 100644
index 0000000..1efbd95
Binary files /dev/null and b/R/0725_topic_commitoutcome_readme.rda differ
diff --git a/R/0725_topic_contriboutcome_contrib.rda b/R/0725_topic_contriboutcome_contrib.rda
new file mode 100644
index 0000000..f852940
Binary files /dev/null and b/R/0725_topic_contriboutcome_contrib.rda differ
diff --git a/R/0725_topic_contriboutcome_readme.rda b/R/0725_topic_contriboutcome_readme.rda
new file mode 100644
index 0000000..3d472ad
Binary files /dev/null and b/R/0725_topic_contriboutcome_readme.rda differ
diff --git a/R/073024_fossy_plot.png b/R/073024_fossy_plot.png
new file mode 100644
index 0000000..1933493
Binary files /dev/null and b/R/073024_fossy_plot.png differ
diff --git a/R/0731_topic_commitoutcome_contrib.rda b/R/0731_topic_commitoutcome_contrib.rda
new file mode 100644
index 0000000..97a5ff4
Binary files /dev/null and b/R/0731_topic_commitoutcome_contrib.rda differ
diff --git a/R/0731_topic_contriboutcome_contrib.rda b/R/0731_topic_contriboutcome_contrib.rda
new file mode 100644
index 0000000..1881d7e
Binary files /dev/null and b/R/0731_topic_contriboutcome_contrib.rda differ
diff --git a/R/082424_contributing_ranef_plot.png b/R/082424_contributing_ranef_plot.png
new file mode 100644
index 0000000..e1cfa91
Binary files /dev/null and b/R/082424_contributing_ranef_plot.png differ
diff --git a/R/082424_doctype_wordcount.png b/R/082424_doctype_wordcount.png
new file mode 100644
index 0000000..742e95b
Binary files /dev/null and b/R/082424_doctype_wordcount.png differ
diff --git a/R/082424_gam_document_introduction.png b/R/082424_gam_document_introduction.png
new file mode 100644
index 0000000..37ecf5b
Binary files /dev/null and b/R/082424_gam_document_introduction.png differ
diff --git a/R/082424_readability_density.png b/R/082424_readability_density.png
new file mode 100644
index 0000000..acb9177
Binary files /dev/null and b/R/082424_readability_density.png differ
diff --git a/R/FOSSY_contributing_doc_intro.png b/R/FOSSY_contributing_doc_intro.png
new file mode 100644
index 0000000..7e36bb6
Binary files /dev/null and b/R/FOSSY_contributing_doc_intro.png differ
diff --git a/R/FOSSY_presentation_README_rt.png b/R/FOSSY_presentation_README_rt.png
new file mode 100644
index 0000000..82d2dbd
Binary files /dev/null and b/R/FOSSY_presentation_README_rt.png differ
diff --git a/R/R.Rproj b/R/R.Rproj
new file mode 100644
index 0000000..8e3c2eb
--- /dev/null
+++ b/R/R.Rproj
@@ -0,0 +1,13 @@
+Version: 1.0
+
+RestoreWorkspace: Default
+SaveWorkspace: Default
+AlwaysSaveHistory: Default
+
+EnableCodeIndexing: Yes
+UseSpacesForTab: Yes
+NumSpacesForTab: 2
+Encoding: UTF-8
+
+RnwWeave: Sweave
+LaTeX: pdfLaTeX
diff --git a/R/contribRDDAnalysis.R b/R/contribRDDAnalysis.R
index d934e1c..1d9671e 100644
--- a/R/contribRDDAnalysis.R
+++ b/R/contribRDDAnalysis.R
@@ -45,9 +45,15 @@ mrg_actions_data <- windowed_data[which(windowed_data$observation_type == "mrg")
 all_actions_data$logged_count <- log(all_actions_data$count)
 all_actions_data$log1p_count <- log1p(all_actions_data$count)
 #EDA
+sd(all_actions_data$count)
+grouped_averages <- aggregate(all_actions_data$count, list(all_actions_data$upstream_vcs_link), mean)
+quantile(grouped_averages$x)
+quantile(all_actions_data$before_auth_new)
+quantile(all_actions_data$after_auth_new)
+
 range(all_actions_data$log1p_count) # 0.000000 6.745236
 mean(all_actions_data$log1p_count) # 1.200043
-var(all_actions_data$log1p_count) # 1.753764
+sd(all_actions_data$log1p_count) 
 median(all_actions_data$log1p_count) # 0.6931472
 # now for merge
 mrg_actions_data$logged_count <- log(mrg_actions_data$count)
@@ -58,12 +64,12 @@ library(optimx)
 library(lattice)
 #model
 print("fitting model")
-all_gmodel <- glmer.nb(log1p_count ~ D * week_offset + scaled_project_age + scaled_event_gap + (D * week_offset | upstream_vcs_link),
-              control=glmerControl(optimizer="bobyqa",
-                                           optCtrl=list(maxfun=2e5)), nAGQ=0, data=all_actions_data)
+#all_gmodel <- glmer.nb(log1p_count ~ D * week_offset + scaled_project_age + scaled_event_gap + (D * week_offset | upstream_vcs_link),
+#              control=glmerControl(optimizer="bobyqa",
+#                                           optCtrl=list(maxfun=2e5)), nAGQ=0, data=all_actions_data)
 #all_gmodel <- readRDS("0711_contrib_all.rda")
 summary(all_gmodel)
-saveRDS(all_gmodel, "0711_contrib_all_01.rda")
+#saveRDS(all_gmodel, "0711_contrib_all_01.rda")
 
 all_residuals <- residuals(all_gmodel)
 qqnorm(all_residuals)
diff --git a/R/contrib_docChar_outcomes.R b/R/contrib_docChar_outcomes.R
index d58ff33..1d9630d 100644
--- a/R/contrib_docChar_outcomes.R
+++ b/R/contrib_docChar_outcomes.R
@@ -1,5 +1,7 @@
 #libraries
-library(stringr)
+library(readr)
+library(tidyverse)
+library(plyr)
 contrib_df <- read_csv("../final_data/deb_contrib_did.csv")
 contrib_pop_df <- read_csv("../final_data/deb_contrib_pop_change.csv")
 contrib_readability_df <- read_csv('../text_analysis/dwo_readability_contributing.csv')
@@ -68,10 +70,12 @@ contrib_total_df <- contrib_pop_df |>
 contrib_total_df <- contrib_total_df|>
   join(summed_data, by="upstream_vcs_link")
 #outcome variable that is number of commits by number of new contributors
-contrib_total_df$commit_by_contrib = contrib_total_df$summed_count * contrib_total_df$after_contrib_new
+contrib_total_df$commit_by_contrib = contrib_total_df$summed_count + contrib_total_df$after_contrib_new * 2
 contrib_total_df$logged_outcome = log1p(contrib_total_df$commit_by_contrib)
+contrib_total_df$logged_contribs = log1p(contrib_total_df$after_contrib_new)
+contrib_total_df$logged_commits = log1p(contrib_total_df$summed_count)
 # test regressions
 library(MASS)
-lm1 <- glm.nb(summed_count ~ reading_time + linsear_write_formula + flesch_reading_ease + mcalpine_eflaw + word_count, data = contrib_total_df)
+lm1 <- glm.nb(logged_contribs ~ reading_time + linsear_write_formula + flesch_reading_ease + mcalpine_eflaw + word_count, data = contrib_total_df)
 qqnorm(residuals(lm1))
 summary(lm1)
diff --git a/R/contrib_topic_outcomes.R b/R/contrib_topic_outcomes.R
index fdc0c97..9b78b98 100644
--- a/R/contrib_topic_outcomes.R
+++ b/R/contrib_topic_outcomes.R
@@ -2,9 +2,12 @@
 library(stringr)
 library(plyr)
 contrib_topics_df <- read_csv("../text_analysis/contrib_file_topic_distributions.csv")
+colMeans(subset(contrib_topics_df, select = -filename))
 contrib_df <- read_csv("../final_data/deb_contrib_did.csv")
 contrib_pop_df <- read_csv("../final_data/deb_contrib_pop_change.csv")
 
+median(contrib_df$age_in_days)
+
 #get the contribution count 
 #some preprocessing and expansion 
 col_order <- c("upstream_vcs_link", "age_in_days", "first_commit", "first_commit_dt", "event_gap", "event_date",  "event_hash", "before_all_ct", "after_all_ct", "before_mrg_ct", "after_mrg_ct", "before_auth_new", "after_auth_new", "before_commit_new",  "after_commit_new")
@@ -73,8 +76,19 @@ contrib_total_df <- contrib_total_df|>
 #outcome variable that is number of commits by number of new contributors
 contrib_total_df$commit_by_contrib = contrib_total_df$summed_count * contrib_total_df$after_contrib_new
 contrib_total_df$logged_outcome = log1p(contrib_total_df$commit_by_contrib)
+contrib_total_df$logged_contrib = log1p(contrib_total_df$after_contrib_new)
+contrib_total_df$logged_commits = log1p(contrib_total_df$summed_count)
 #running regressions 
 library(MASS)
-lm1 <- glm.nb(commit_by_contrib ~ t2+  t3, data = contrib_total_df)
+contrib_ <- glm.nb(logged_contrib ~ t0 + t1 + t2 + t3, data = contrib_total_df)
+commits_ <- glm.nb(logged_commits ~ t0 + t1 + t2 + t3, data = contrib_total_df)
 qqnorm(residuals(lm1))
-summary(lm1)
+summary(contrib_)
+summary(commits_)
+texreg(list(contrib_, commits_), stars=NULL, digits=3, use.packages=FALSE, 
+       custom.model.names=c( 'Contributions','Commits'),
+       custom.coef.names=c('(Intercept)', 'Topic 1', 'Topic 2', 'Topic 3'), 
+       table=FALSE, ci.force = TRUE)
+
+saveRDS(commits_, "0731_topic_commitoutcome_contrib.rda")
+saveRDS(contrib_, "0731_topic_contriboutcome_contrib.rda")
diff --git a/R/delta_analysis.R b/R/delta_analysis.R
index 98a09ea..60b3dfa 100644
--- a/R/delta_analysis.R
+++ b/R/delta_analysis.R
@@ -1,10 +1,22 @@
 library(tidyverse)
 contrib_df <- read_csv("../final_data/deb_contrib_did.csv")
 readme_df <- read_csv("../final_data/deb_readme_did.csv")
+median(readme_df$age_in_days)
+sd(readme_df$age_in_days)
+
+median(contrib_df$age_in_days)
+sd(contrib_df$age_in_days)
+
 contrib_df <- contrib_df |>
   filter(event_gap >= 0)
 readme_df <- readme_df |>
   filter(event_gap >= 0)
+
+quantile(readme_df$age_in_days)
+quantile(contrib_df$age_in_days)
+
+quantile(readme_df$event_gap)
+quantile(contrib_df$event_gap)
   
 hist(readme_df$event_gap)
 median(readme_df$event_gap)
diff --git a/R/documentReadabilityAnalysis.R b/R/documentReadabilityAnalysis.R
index 47622f9..47fa3bb 100644
--- a/R/documentReadabilityAnalysis.R
+++ b/R/documentReadabilityAnalysis.R
@@ -10,6 +10,8 @@ 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$subdir), median)
 #getting basic stats for the readme readability 
@@ -19,45 +21,61 @@ median(readme_df$mcalpine_eflaw)
 median(readme_df$reading_time)
 # establishing the color scheme 
 subdirColors <-
-  setNames( c('firebrick1', 'forestgreen', 'cornflowerblue')
+  setNames( c('#31449c', '#4a7c85', '#c5db68')
             , levels(contributing_df$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=0.2, position="identity") +
+  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(color = as.factor(subdir), fill=as.factor(subdir)), alpha=0.2, position="identity") +
-  scale_color_manual(values = subdirColors) + 
+  geom_density(aes(fill=as.factor(subdir)), position="fill") +
+  scale_fill_manual(values = readmeSubdirColors) + 
   xlim(-5, 90) +
-  ylab("readme density") +
+  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(color = as.factor(subdir), fill=as.factor(subdir)), alpha=0.2, position="identity") +
-  scale_color_manual(values = subdirColors) + 
+  geom_density(aes(fill=as.factor(subdir)), position="fill") +
+  scale_fill_manual(values = readmeSubdirColors) + 
   xlim(-5, 90) +
-  ylab("readme density") +
+  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(color = as.factor(subdir), fill=as.factor(subdir)), alpha=0.2, position="identity") +
-  scale_color_manual(values = subdirColors) + 
-  xlim(-5, 30) +
-  ylab("readme density") +
+  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))) + 
-  scale_color_manual(values = subdirColors) + 
-  geom_density(aes(color = as.factor(subdir), fill=as.factor(subdir)), alpha=0.2, position="identity") +
-  xlim(-5, 60) +
+  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_bw() 
 #theme(axis.title.y=element_blank())
 #plot of reading_ease 
 #readme_df <- readme_df |>
@@ -72,33 +90,64 @@ 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") +
+  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() + 
-  theme(legend.position = "top") 
+  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,contributing_linsear_plot, contributing_mcalpine_eflaw, readme_reading_ease, readme_reading_time_plot, readme_linsear_plot, readme_mcalpine_eflaw, nrow = 2)
+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)
diff --git a/R/document_word_count.png b/R/document_word_count.png
new file mode 100644
index 0000000..88d6176
Binary files /dev/null and b/R/document_word_count.png differ
diff --git a/R/fossy24_plot.png b/R/fossy24_plot.png
new file mode 100644
index 0000000..dbbaed8
Binary files /dev/null and b/R/fossy24_plot.png differ
diff --git a/R/gam_plot_documents.R b/R/gam_plot_documents.R
index 380b2d5..e7593eb 100644
--- a/R/gam_plot_documents.R
+++ b/R/gam_plot_documents.R
@@ -50,21 +50,52 @@ windowed_readme_data <- expanded_readme_data |>
 
 windowed_contrib_data$week_offset <- windowed_contrib_data$week - 27
 all_actions_contrib_data <- windowed_contrib_data[which(windowed_contrib_data$observation_type == "all"),]
-all_actions_contrib_data$document_type <- rep("contributing", length(all_actions_contrib_data$count))
+all_actions_contrib_data$document_type <- rep("CONTRIBUTING", length(all_actions_contrib_data$count))
 windowed_readme_data$week_offset <- windowed_readme_data$week - 27
 all_actions_readme_data <- windowed_readme_data[which(windowed_readme_data$observation_type == "all"),]
-all_actions_readme_data$document_type <- rep("readme", length(all_actions_readme_data$count))
+all_actions_readme_data$document_type <- rep("README", length(all_actions_readme_data$count))
 all_actions_data <- rbind(all_actions_contrib_data, all_actions_readme_data)
 all_actions_data$log1p_count <- log1p(all_actions_data$count)
+library(scales)
+expm1_trans <- trans_new(
+  name = 'expm1',
+  transform = function(x) expm1(x),
+  inverse = function(x) log1p(x)
+)
+
+doctypeColors <-
+  setNames( c('#5da2d8', '#c7756a')
+            , c("CONTRIBUTING", "README"))
+
 time_plot <- all_actions_data |>
-  ggplot(aes(x=week_offset, y=log1p_count, color=factor(document_type))) + 
+  ggplot(aes(x=week_offset, y=log1p_count, color=factor(document_type))) +
+  labs(x="Weekly Offset", y="Commit Count", color="Document Type") +
+  scale_color_manual(values = doctypeColors) + 
   geom_smooth() +
   geom_vline(xintercept = 0)+
   theme_bw() +
   theme(legend.position = "top")
 time_plot
+#code to change the axes
+
+#scale_y_continuous(breaks = c(0, 0.5, 1.0, 1.5), 
+#                   labels = round(c(expm1(0), expm1(0.5), expm1(1.0), expm1(1.5)), 1)) +
+
 #looking at event gap 
 mean(all_actions_readme_data$event_gap)
 sd(all_actions_readme_data$event_gap)
 mean(all_actions_contrib_data$event_gap)
 sd(all_actions_contrib_data$event_gap)
+
+#all_actions_contrib_data$log1p_count <- log1p(all_actions_contrib_data$count)
+#contrib_time_plot <- all_actions_contrib_data |>
+#  ggplot(aes(x=week_offset, y=log1p_count)) + 
+#  geom_smooth(color=forestgreen) +
+#  geom_vline(xintercept = 0)+
+#  annotate("text", x=3, y=1, label="CONTRIBUTING.md Publication", angle=0)+
+#  theme_bw() +
+#  ylab("Log Transformed Count of Contributions") +
+#  xlab("Offset Weeks") +
+#  theme(legend.position = "top")
+#contrib_time_plot
+
diff --git a/R/model_presentation.R b/R/model_presentation.R
index 1aaecf7..5da839b 100644
--- a/R/model_presentation.R
+++ b/R/model_presentation.R
@@ -11,10 +11,10 @@ texreg(list(readme_rdd, contrib_rdd), stars=NULL, digits=3, use.packages=FALSE,
        table=FALSE, ci.force = TRUE)
 
 readme_groupings <- read.csv('../final_data/deb_readme_interaction_groupings.csv')
-contrib_groupings <- read.csv('../final_data/0711_contrib_inter_groupings.csv')
+contrib_groupings <- read.csv('../final_data/deb_contrib_interaction_groupings.csv')
 
 subdirColors <-
-  setNames( c('firebrick1', 'forestgreen', 'cornflowerblue')
+  setNames( c('#31449c', '#4a7c85', '#c5db68')
             , c(0,1,2)  )
 
 readme_g <- readme_groupings |> 
@@ -22,16 +22,18 @@ readme_g <- readme_groupings |>
   geom_linerange(aes(ymin= conf.low, ymax= conf.high)) +
   scale_color_manual(values = subdirColors) + 
   guides(fill="none", color="none")+
-  theme_bw()
+  theme_bw() + 
+  labs(x="RE Coefficient Rank", y="RE Coefficient Estimate", color="Estimate Grouping")
 readme_g
 
 
 contrib_g <- contrib_groupings |> 
   ggplot(aes(x=rank, y=estimate, col = as.factor(ranef_grouping))) +
   geom_linerange(aes(ymin= conf.low, ymax= conf.high)) +
-  scale_color_manual(values = subdirColors) + 
+  scale_color_manual(values = subdirColors, labels=c('CI < 0', '0 in CI', '0 < CI')) + 
   theme_bw() +
-  theme(legend.position = "top") 
+  theme(legend.position = "top")  +
+  labs(x="RE Coefficient Rank", y="RE Coefficient Estimate", color="Estimate Grouping")
 contrib_g
 
 library(gridExtra)
diff --git a/R/readmeRDDAnalysis.R b/R/readmeRDDAnalysis.R
index bd9b6a7..c5a3d65 100644
--- a/R/readmeRDDAnalysis.R
+++ b/R/readmeRDDAnalysis.R
@@ -47,6 +47,10 @@ mrg_actions_data <- windowed_data[which(windowed_data$observation_type == "mrg")
 all_actions_data$logged_count <- log(all_actions_data$count)
 all_actions_data$log1p_count <- log1p(all_actions_data$count)
 range(all_actions_data$log1p_count)
+
+grouped_averages <- aggregate(all_actions_data$count, list(all_actions_data$upstream_vcs_link), mean)
+quantile(grouped_averages$x)
+
 # 3 rdd in lmer analysis
 # rdd: https://rpubs.com/phle/r_tutorial_regression_discontinuity_design
 # lmer: https://www.youtube.com/watch?v=LzAwEKrn2Mc
@@ -57,14 +61,16 @@ library(lattice)
 #some more EDA to go between Poisson and neg binomial
 var(all_actions_data$log1p_count) # 1.125429
 mean (all_actions_data$log1p_count) # 0.6426873
+sd(all_actions_data$log1p_count)
 median(all_actions_data$log1p_count) #0
 var(all_actions_data$count) # 268.4449
 mean (all_actions_data$count) # 3.757298
+sd (all_actions_data$count)
 median(all_actions_data$count) # 0
 print("fitting model")
 #all_log1p_gmodel <- glmer.nb(log1p_count ~ D * week_offset+ scaled_project_age + scaled_event_gap + (D * week_offset | upstream_vcs_link), data=all_actions_data, nAGQ=1,  control=glmerControl(optimizer="bobyqa",
 #                         optCtrl=list(maxfun=1e5)))
-all_log1p_gmodel <- readRDS("final_models/0624_readme_all_rdd.rda")
+#all_log1p_gmodel <- readRDS("final_models/0624_readme_all_rdd.rda")
 summary(all_log1p_gmodel)
 print("model fit")
 #I grouped the ranef D effects on 0624
diff --git a/R/readme_docChar_outcomes.R b/R/readme_docChar_outcomes.R
index bf2e4b8..e418f5e 100644
--- a/R/readme_docChar_outcomes.R
+++ b/R/readme_docChar_outcomes.R
@@ -1,5 +1,6 @@
 #libraries
 library(stringr)
+library(tidyverse)
 readme_df <- read_csv("../final_data/deb_readme_did.csv")
 readme_pop_df <- read_csv("../final_data/deb_readme_pop_change.csv")
 readme_readability_df <- read_csv('../text_analysis/dwo_readability_readme.csv')
@@ -94,9 +95,11 @@ readme_total_df <- readme_total_df|>
 readme_total_df$commit_by_contrib = NA
 readme_total_df$commit_by_contrib = readme_total_df$summed_count * (readme_total_df$after_contrib_new + 1)
 readme_total_df$logged_outcome = log1p(readme_total_df$commit_by_contrib)
+readme_total_df$logged_contribs = log1p(readme_total_df$after_contrib_new)
+readme_total_df$logged_commits= log1p(readme_total_df$summed_count)
 # test regressions
 library(MASS)
-lm1 <- glm.nb(logged_outcome~ reading_time + linsear_write_formula + flesch_reading_ease + mcalpine_eflaw + word_count, data = readme_total_df)
+lm1 <- glm.nb(logged_commits~ word_count, data = readme_total_df)
 qqnorm(residuals(lm1))
 summary(lm1)
 
diff --git a/R/readme_topic_outcomes.R b/R/readme_topic_outcomes.R
index 1d1882d..67099df 100644
--- a/R/readme_topic_outcomes.R
+++ b/R/readme_topic_outcomes.R
@@ -1,7 +1,8 @@
 
 library(stringr)
-library(plyr)
+library(tidyverse)
 readme_topics_df <- read_csv("../text_analysis/readme_file_topic_distributions.csv")
+colMeans(subset(readme_topics_df, select = -filename))
 readme_df <- read_csv("../final_data/deb_readme_did.csv")
 readme_pop_df <- read_csv("../final_data/deb_readme_pop_change.csv")
 
@@ -72,9 +73,21 @@ readme_total_df <- readme_total_df|>
 
 #outcome variable that is number of commits by number of new readmeutors
 readme_total_df$commit_by_contrib = readme_total_df$summed_count *readme_total_df$after_contrib_new
-readme_total_df$logged_outcome = log1p(readme_total_df$commit_by_readme)
+readme_total_df$logged_outcome = log1p(readme_total_df$commit_by_contrib)
+readme_total_df$logged_contrib = log1p(readme_total_df$after_contrib_new)
+readme_total_df$logged_commits = log1p(readme_total_df$summed_count)
 #running regressions 
 library(MASS)
-lm1 <- glm.nb(commit_by_contrib ~ t0+t1+t2+t7+t3 +t4 + t5, data = readme_total_df)
+lm1 <- glm.nb(logged_contrib~ t0+t1+t2+t7+t3 +t6 + t5, data = readme_total_df)
 qqnorm(residuals(lm1))
 summary(lm1)
+#saveRDS(lm1, "0725_topic_contriboutcome_readme.rda")
+contrib_ <- glm.nb(logged_contrib~ t0+t1+t2+t3+ t5 +t6 +t7, data = readme_total_df)
+commit_ <- glm.nb(logged_commits~ t0+t1+t2+t3+ t5 +t6 +t7, data = readme_total_df)
+
+library(texreg)
+
+texreg(list(contrib_, commit_), stars=NULL, digits=3, use.packages=FALSE, 
+       custom.model.names=c( 'Contributions','Commits'),
+       custom.coef.names=c('(Intercept)', 'Topic 1', 'Topic 2', 'Topic 3', 'Topic 4', 'Topic 6', 'Topic 7', 'Topic 8'), 
+       table=FALSE, ci.force = TRUE)
diff --git a/R/topic_distributions.R b/R/topic_distributions.R
new file mode 100644
index 0000000..3bb2ce6
--- /dev/null
+++ b/R/topic_distributions.R
@@ -0,0 +1,42 @@
+library(stringr)
+library(tidyverse)
+readme_topics_df <- read_csv("../text_analysis/readme_file_topic_distributions.csv")
+contrib_topics_df <- read_csv("../text_analysis/contrib_file_topic_distributions.csv")
+quantile(contrib_topics_df$t0)
+confint(contrib_topics_df$t0)
+sd(contrib_topics_df$t0)
+quantile(contrib_topics_df$t1)
+mean(contrib_topics_df$t1)
+sd(contrib_topics_df$t1)
+quantile(contrib_topics_df$t2)
+mean(contrib_topics_df$t2)
+sd(contrib_topics_df$t2)
+quantile(contrib_topics_df$t3)
+mean(contrib_topics_df$t3)
+sd(contrib_topics_df$t3)
+quantile(readme_topics_df$t0)
+mean(readme_topics_df$t0)
+sd(readme_topics_df$t0)
+quantile(readme_topics_df$t1)
+mean(readme_topics_df$t1)
+sd(readme_topics_df$t1)
+quantile(readme_topics_df$t2)
+mean(readme_topics_df$t2)
+sd(readme_topics_df$t2)
+quantile(readme_topics_df$t3)
+mean(readme_topics_df$t3)
+sd(readme_topics_df$t3)
+quantile(readme_topics_df$t4)
+mean(readme_topics_df$t4)
+sd(readme_topics_df$t4)
+quantile(readme_topics_df$t5)
+mean(readme_topics_df$t5)
+sd(readme_topics_df$t5)
+quantile(readme_topics_df$t6)
+mean(readme_topics_df$t6)
+sd(readme_topics_df$t6)
+quantile(readme_topics_df$t7)
+mean(readme_topics_df$t7)
+sd(readme_topics_df$t7)
+
+
diff --git a/main.py b/main.py
index e6465f8..3b7b8e5 100644
--- a/main.py
+++ b/main.py
@@ -103,17 +103,3 @@ if __name__ == "__main__":
 
 
 
-'''
-if largest_object[repo_path]["gha_obj"]['milestone_count'] == 0:
-    #del largest_object[repo_path]
-    #return
-    #this is to ensure that projects which don't use milestones are counted
-    largest_object[repo_path]["gha_obj"]['milestone_count'] = 0.1
-largest_object[repo_path]['new_mmt'] = compute_new_mmt(largest_object[repo_path]["perceval_obj"]['contributors'], largest_object[repo_path]["perceval_obj"]['collaborators'])
-#print('New MMT: ' + str(largest_object[repo_path]['new_mmt']))
-largest_object[repo_path]['old_mmt'] = compute_old_mmt(largest_object[repo_path]["perceval_obj"]['contributors'], largest_object[repo_path]["perceval_obj"]['collaborators'])
-#print('Old MMT: ' + str(largest_object[repo_path]['old_mmt']))
-#new mmt formality score
-largest_object[repo_path]['new_formality'] = compute_formality_score(largest_object[repo_path]['new_mmt'], largest_object[repo_path]["gha_obj"]['milestone_count'], largest_object[repo_path]["perceval_obj"]['age_of_project'])
-print(largest_object[repo_path]['new_formality'])
-'''