diff --git a/R/.Rhistory b/R/.Rhistory
index 54e4a59..adb1424 100644
--- a/R/.Rhistory
+++ b/R/.Rhistory
@@ -1,293 +1,3 @@
-contrib_readme_model <- load(file = "final_models/0623_pop_rm_contrib.rda")
-contrib_readme_model <- load(file = "final_models/0623_pop_rm_contrib.rda")
-contrib_readme_model <- load("final_models/0623_pop_rm_contrib.rda")
-contrib_readme_model <- source("final_models/0623_pop_rm_contrib.rda")
-contrib_readme_model <- readRDS("final_models/0623_pop_rm_contrib.rda")
-contrib_readme_model <- readRDS("final_models/0623_pop_contrib_collab.rda")
-collab_readme_model <- readRDS("final_models/0623_pop_rm_collab.rda")
-texreg(list(collab_readme_model, contrib_readme_model), stars=NULL, digits=2,
-custom.model.names=c( 'collab','contrib.'  ),
-custom.coef.names=c('(Intercept)', 'after_introduction'),
-use.packages=FALSE, table=FALSE, ci.force = TRUE)
-library(texreg)
-texreg(list(collab_readme_model, contrib_readme_model), stars=NULL, digits=2,
-custom.model.names=c( 'collab','contrib.'  ),
-custom.coef.names=c('(Intercept)', 'after_introduction'),
-use.packages=FALSE, table=FALSE, ci.force = TRUE)
-texreg(list(collab_readme_model, contrib_readme_model), stars=NULL, digits=2,
-custom.model.names=c( 'collab','contrib.'  ),
-custom.coef.names=c('(Intercept)', 'after_introduction' 'etc'),
-texreg(list(collab_readme_model, contrib_readme_model), stars=NULL, digits=2,
-custom.model.names=c( 'collab','contrib.'  ),
-custom.coef.names=c('(Intercept)', 'after_introduction', 'etc'),
-use.packages=FALSE, table=FALSE, ci.force = TRUE)
-library(tidyverse)
-library(plyr)
-library(stringr)
-try(setwd(dirname(rstudioapi::getActiveDocumentContext()$path)))
-#load in data
-contrib_df <- read_csv("../final_data/deb_contrib_pop_change.csv")
-readme_df <- read_csv("../final_data/deb_readme_pop_change.csv")
-#some expansion needs to happens for each project
-expand_timeseries <- function(project_row) {
-longer <- project_row |>
-pivot_longer(cols = ends_with("new"),
-names_to = "window",
-values_to = "count") |>
-unnest(count) |>
-mutate(after_doc = as.numeric(str_detect(window, "after"))) |>
-mutate(is_collab = as.numeric(str_detect(window, "collab")))
-return(longer)
-}
-expanded_readme_data <- expand_timeseries(readme_df[1,])
-for (i in 2:nrow(readme_df)){
-expanded_readme_data <- rbind(expanded_readme_data, expand_timeseries(readme_df[i,]))
-}
-expanded_contrib_data <- expand_timeseries(contrib_df[1,])
-for (i in 2:nrow(contrib_df)){
-expanded_contrib_data <- rbind(expanded_contrib_data, expand_timeseries(contrib_df[i,]))
-}
-expanded_readme_data$log1pcount <- log1p(expanded_readme_data$count)
-expanded_contrib_data$log1pcount <- log1p(expanded_contrib_data$count)
-expanded_readme_data$logcount <- log(expanded_readme_data$count)
-expanded_contrib_data$logcount <- log(expanded_contrib_data$count)
-#breaking out the types of population counts
-collab_pop_readme <- expanded_readme_data[which(expanded_readme_data$is_collab == 1),]
-contrib_pop_readme <- expanded_readme_data[which(expanded_readme_data$is_collab == 0),]
-collab_pop_contrib <- expanded_contrib_data[which(expanded_contrib_data$is_collab == 1),]
-contrib_pop_contrib <- expanded_contrib_data[which(expanded_contrib_data$is_collab == 0),]
-simple_collab_readme_model <- glm.nb(count ~ as.factor(after_doc), data=collab_pop_readme)
-summary(simple_collab_readme_model)
-anova(simple_collab_readme_model, collab_readme_model)
-summary(collab_readme_model)
-#load in data
-full_df <- read_csv("../final_data/deb_full_data.csv")
-contrib_df <- read_csv("../final_data/deb_contrib_pop_change.csv")
-contrib_df <- merge(full_df, contrib_df, by="upstream_vcs_link")
-View(contrib_df)
-View(contrib_df)
-readme_df <- read_csv("../final_data/deb_readme_pop_change.csv")
-readme_df <- merge(full_df, readme_df, by="upstream_vcs_link")
-# age is calculated against December 11, 2023
-contrib_df |>
-mutate(start_date = as.Date("2023-12-11") - age_of_project)
-View(contrib_df)
-# age is calculated against December 11, 2023
-contrib_df <- contrib_df |>
-mutate(start_date = as.Date("2023-12-11") - age_of_project)
-View(contrib_df)
-View(contrib_df)
-View(readme_df)
-readme_df <- readme_df |>
-mutate(start_date = as.Date("2023-12-11") - age_of_project)
-View(readme_df)
-collab_readme_model_plus <- glmer.nb(log1pcount ~ as.factor(after_doc) + event_date +  (after_doc| upstream_vcs_link), data=collab_pop_readme)
-#some expansion needs to happens for each project
-expand_timeseries <- function(project_row) {
-longer <- project_row |>
-pivot_longer(cols = ends_with("new"),
-names_to = "window",
-values_to = "count") |>
-unnest(count) |>
-mutate(after_doc = as.numeric(str_detect(window, "after"))) |>
-mutate(is_collab = as.numeric(str_detect(window, "collab")))
-return(longer)
-}
-expanded_readme_data <- expand_timeseries(readme_df[1,])
-for (i in 2:nrow(readme_df)){
-expanded_readme_data <- rbind(expanded_readme_data, expand_timeseries(readme_df[i,]))
-}
-expanded_contrib_data <- expand_timeseries(contrib_df[1,])
-for (i in 2:nrow(contrib_df)){
-expanded_contrib_data <- rbind(expanded_contrib_data, expand_timeseries(contrib_df[i,]))
-}
-expanded_readme_data$log1pcount <- log1p(expanded_readme_data$count)
-expanded_contrib_data$log1pcount <- log1p(expanded_contrib_data$count)
-expanded_readme_data$logcount <- log(expanded_readme_data$count)
-expanded_contrib_data$logcount <- log(expanded_contrib_data$count)
-#breaking out the types of population counts
-collab_pop_readme <- expanded_readme_data[which(expanded_readme_data$is_collab == 1),]
-contrib_pop_readme <- expanded_readme_data[which(expanded_readme_data$is_collab == 0),]
-collab_pop_contrib <- expanded_contrib_data[which(expanded_contrib_data$is_collab == 1),]
-contrib_pop_contrib <- expanded_contrib_data[which(expanded_contrib_data$is_collab == 0),]
-library(tidyverse)
-library(plyr)
-library(stringr)
-try(setwd(dirname(rstudioapi::getActiveDocumentContext()$path)))
-#load in data
-full_df <- read_csv("../final_data/deb_full_data.csv")
-contrib_df <- read_csv("../final_data/deb_contrib_pop_change.csv")
-View(contrib_df)
-readme_df <- read_csv("../final_data/deb_readme_pop_change.csv")
-contrib_df <- merge(full_df, contrib_df, by="upstream_vcs_link")
-readme_df <- merge(full_df, readme_df, by="upstream_vcs_link")
-# age is calculated against December 11, 2023
-contrib_df <- contrib_df |>
-mutate(start_date = as.Date("2023-12-11") - age_of_project) +
-mutate(event_date_days = as.Date("2024-06-24") - event_date) +
-readme_df <- readme_df |>
-mutate(start_date = as.Date("2023-12-11") - age_of_project)
-# age is calculated against December 11, 2023
-contrib_df <- contrib_df |>
-mutate(start_date = as.Date("2023-12-11") - age_of_project) +
-mutate(event_date_days = as.Date("2024-06-24") - event_date)
-# age is calculated against December 11, 2023
-contrib_df <- contrib_df |>
-mutate(start_date = as.Date("2023-12-11") - age_of_project) +
-mutate(event_date_days = diff.Date(as.Date("2023-12-11"),event_date, units = "days"))
-# age is calculated against December 11, 2023
-contrib_df <- contrib_df |>
-mutate(start_date = as.Date("2023-12-11") - age_of_project) |>
-mutate(event_date_days = diff.Date(as.Date("2023-12-11"),event_date, units = "days"))
-# age is calculated against December 11, 2023
-contrib_df <- contrib_df |>
-mutate(start_date = as.Date("2023-12-11") - age_of_project) |>
-mutate(event_date_days = diff.Date(as.Date("2024-06-24"),event_date, units = "days"))
-# age is calculated against December 11, 2023
-contrib_df <- contrib_df |>
-mutate(start_date = as.Date("2023-12-11") - age_of_project) |>
-mutate(event_date_days = diff.Date(as.Date("2024-06-24"),as.Date(event_date), units = "days"))
-View(contrib_df)
-View(contrib_df)
-# age is calculated against December 11, 2023
-contrib_df <- contrib_df |>
-mutate(start_date = as.Date("2023-12-11") - age_of_project) |>
-mutate(event_date_days = diff.Date(as.Date("2024-06-24"),as.POSIXct(event_date, format = "%Y-%m-%d %H:%M:%S"), units = "days"))
-# age is calculated against December 11, 2023
-contrib_df <- contrib_df |>
-mutate(start_date = as.Date("2023-12-11") - age_of_project) |>
-mutate(event_date_days =
-as.numeric(
-difftime(as.POSIXct("2024-06-24 00:00:00", format = "%Y-%m-%d %H:%M:%S")
-as.POSIXct(event_date, format = "%Y-%m-%d %H:%M:%S"),
-# age is calculated against December 11, 2023
-contrib_df <- contrib_df |>
-mutate(start_date = as.Date("2023-12-11") - age_of_project) |>
-mutate(event_date_days =
-as.numeric(
-difftime(as.POSIXct("2024-06-24 00:00:00", format = "%Y-%m-%d %H:%M:%S"),
-as.POSIXct(event_date, format = "%Y-%m-%d %H:%M:%S"),
-units = "days")))
-View(contrib_df)
-readme_df <- readme_df |>
-mutate(start_date = as.Date("2023-12-11") - age_of_project) |>
-mutate(event_date_days =
-as.numeric(
-difftime(as.POSIXct("2024-06-24 00:00:00", format = "%Y-%m-%d %H:%M:%S"),
-as.POSIXct(event_date, format = "%Y-%m-%d %H:%M:%S"),
-units = "days")))
-#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_readme_data <- expand_timeseries(readme_df[1,])
-for (i in 2:nrow(readme_df)){
-expanded_readme_data <- rbind(expanded_readme_data, expand_timeseries(readme_df[i,]))
-}
-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,]))
-}
-expanded_readme_data$log1pcount <- log1p(expanded_readme_data$count)
-expanded_contrib_data$log1pcount <- log1p(expanded_contrib_data$count)
-expanded_readme_data$logcount <- log(expanded_readme_data$count)
-expanded_contrib_data$logcount <- log(expanded_contrib_data$count)
-#breaking out the types of population counts
-collab_pop_readme <- expanded_readme_data[which(expanded_readme_data$is_collab == 1),]
-contrib_pop_readme <- expanded_readme_data[which(expanded_readme_data$is_collab == 0),]
-collab_pop_contrib <- expanded_contrib_data[which(expanded_contrib_data$is_collab == 1),]
-contrib_pop_contrib <- expanded_contrib_data[which(expanded_contrib_data$is_collab == 0),]
-#import models
-library(lme4)
-library(optimx)
-collab_readme_model_plus <- glmer.nb(log1pcount ~ as.factor(after_doc) + event_date_days +  (after_doc| upstream_vcs_link), data=collab_pop_readme)
-anova(collab_readme_model_plus, collab_readme_model)
-collab_readme_model <- readRDS("final_models/0623_pop_rm_collab.rda")
-anova(collab_readme_model_plus, collab_readme_model)
-saveRDS(collab_readme_model, "final_models/0623_pop_rm_collab_better.rda")
-summary(collab_readme_model_plus)
-summary(collab_readme_model)
-library(tidyverse)
-#things to get:
-# - delete old age column
-# - normal age, in date
-# - age from today in days
-# - delta between first commit and document in days
-#README Document updates
-#loading in new ages
-####RDD CSV
-first_commit_df <- read_csv("../062424_did_first_commit_readme.csv")
-first_commit_df_2 <- read_csv("../062424_did_first_commit_readme_2.csv")
-first_commit_df <- rbind(first_commit_df, first_commit_df_2)
-# need to first do an rbind with this data and the second file
-# check with the head of the file/size of the file
-old_rdd_readme <- read_csv("../final_data/deb_readme_did.csv")
-old_rdd_readme <- merge(old_rdd_readme, first_commit_df, by="upstream_vcs_link")
-new_rm_data <- old_rdd_readme |>
-select(-age_of_project) |>
-mutate(first_commit_dt = as.POSIXct(first_commit,
-format = "%a %b %d %H:%M:%S %Y %z")) |>
-mutate(age_in_days =
-as.numeric(
-difftime(
-as.POSIXct("2024-06-24 00:00:00", format = "%Y-%m-%d %H:%M:%S"),
-first_commit_dt,
-units = "days"))) |>
-mutate (event_gap =
-as.numeric(
-difftime(
-as.POSIXct(event_date, format = "%Y-%m-%d %H:%M:%S"),
-first_commit_dt,
-units = "days")))
-View(old_rdd_readme)
-new_rm_data <- old_rdd_readme |>
-select(-c(age_of_project)) |>
-mutate(first_commit_dt = as.POSIXct(first_commit,
-format = "%a %b %d %H:%M:%S %Y %z")) |>
-mutate(age_in_days =
-as.numeric(
-difftime(
-as.POSIXct("2024-06-24 00:00:00", format = "%Y-%m-%d %H:%M:%S"),
-first_commit_dt,
-units = "days"))) |>
-mutate (event_gap =
-as.numeric(
-difftime(
-as.POSIXct(event_date, format = "%Y-%m-%d %H:%M:%S"),
-first_commit_dt,
-units = "days")))
-new_rm_data <- old_rdd_readme |>
-mutate(first_commit_dt = as.POSIXct(first_commit,
-format = "%a %b %d %H:%M:%S %Y %z")) |>
-mutate(age_in_days =
-as.numeric(
-difftime(
-as.POSIXct("2024-06-24 00:00:00", format = "%Y-%m-%d %H:%M:%S"),
-first_commit_dt,
-units = "days"))) |>
-mutate (event_gap =
-as.numeric(
-difftime(
-as.POSIXct(event_date, format = "%Y-%m-%d %H:%M:%S"),
-first_commit_dt,
-units = "days")))
-View(new_rm_data)
-new_rm_data <- new_rm_data |>
-select(-age_of_project)
-new_rm_data$age_of_project = NULL
-head(new_rm_data)
-write.csv(new_rm_data, file = "../final_data/deb_readme_did_updated.csv", row.names = FALSE)
-old_pop_readme <- merge(old_pop_readme, first_commit_df, by="upstream_vcs_link")
-####PopChange CSV
-old_pop_readme <- read_csv("../final_data/deb_readme_pop_change.csv")
-old_pop_readme <- merge(old_pop_readme, first_commit_df, by="upstream_vcs_link")
 new_pop_data <- old_pop_readme |>
 mutate(first_commit_dt = as.POSIXct(first_commit,
 format = "%a %b %d %H:%M:%S %Y %z")) |>
@@ -510,3 +220,293 @@ summary(contrib_contrib_model)
 #                                           optCtrl=list(maxfun=2e5)), nAGQ=0, data=all_actions_data)
 all_gmodel <- readRDS("0512_contrib_all.rda")
 summary(all_gmodel)
+#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("0512_contrib_all.rda")
+#identifying the quartiles of effect for D
+test_condvals <- broom.mixed::tidy(all_gmodel, effects = "ran_vals", conf.int = TRUE)
+test_glmer_ranef_D <- test_condvals [which(test_condvals $term == "D"),]
+has_zero <- function(estimate, low, high){
+return(ifelse((low < 0),ifelse((high > 0), 1, 0), 2))
+}
+test_glmer_ranef_D <- test_glmer_ranef_D |>
+mutate(ranef_grouping = has_zero(estimate, conf.low, conf.high)) |>
+mutate(rank = rank(estimate))
+g <- test_glmer_ranef_D |>
+ggplot(aes(x=rank, y=estimate, col = as.factor(ranef_grouping))) +
+geom_linerange(aes(ymin= conf.low, ymax= conf.high)) +
+theme_bw()
+library(tidyverse)
+g <- test_glmer_ranef_D |>
+ggplot(aes(x=rank, y=estimate, col = as.factor(ranef_grouping))) +
+geom_linerange(aes(ymin= conf.low, ymax= conf.high)) +
+theme_bw()
+g
+test_glmer_ranef_D <- test_glmer_ranef_D |>
+mutate(ranef_grouping = has_zero(estimate, conf.low, conf.high)) |>
+mutate(rank = rank(estimate))
+g <- test_glmer_ranef_D |>
+ggplot(aes(x=rank, y=estimate, col = as.factor(ranef_grouping))) +
+geom_linerange(aes(ymin= conf.low, ymax= conf.high)) +
+theme_bw()
+g
+library(tidyverse)
+library(plyr)
+library(gridExtra)
+library(ggpubr)
+# script for the analysis of document readability metrics
+# readability metrics will be studied controlled by their length
+# gaughan@u.northwestern.edu
+# loading in the data
+try(setwd(dirname(rstudioapi::getActiveDocumentContext()$path)))
+source("~/Desktop/git/24_deb_gov/R/documentReadabilityAnalysis.R", echo=TRUE)
+source("~/Desktop/git/24_deb_gov/R/documentReadabilityAnalysis.R", echo=TRUE)
+source("~/Desktop/git/24_deb_gov/R/documentReadabilityAnalysis.R", echo=TRUE)
+aggregate(readme_df[, 3:10], list(readme_df$subdir), median)
+readme_df <- read_csv("../text_analysis/dwo_readability_readme.csv")
+aggregate(readme_df[, 3:10], list(readme_df$subdir), median)
+aggregate(contributing_df[, 3:10], list(contributing_df$subdir), median)
+aggregate(readme_df[, 3:10], list(readme_df$subdir), median)
+readme_df <- read_csv("../text_analysis/dwo_readability_readme.csv")
+contributing_df <- read_csv("../text_analysis/dwo_readability_contributing.csv")
+#getting basic stats for the readme readability
+median(readme_df$flesch_reading_ease)
+median(readme_df$linsear_write_formula)
+readme_rdd <- readRDS("final_models/0624_readme_all_rdd.rda")
+contrib_rdd <- readRDS("final_models/0624_contrib_all_rdd.rda")
+textreg(list(readme_rdd, contrib_rdd), stars=NULL, digits=3, use.packages=FALSE, table=FALSE, ci.force = TRUE))
+textreg(list(readme_rdd, contrib_rdd), stars=NULL, digits=3, use.packages=FALSE, table=FALSE, ci.force = TRUE)
+reg(list(readme_rdd, contrib_rdd), stars=NULL, digits=3, use.packages=FALSE, table=FALSE, ci.force = TRUE)
+texreg(list(readme_rdd, contrib_rdd), stars=NULL, digits=3, use.packages=FALSE, table=FALSE, ci.force = TRUE)
+library(texreg)
+texreg(list(readme_rdd, contrib_rdd), stars=NULL, digits=3, use.packages=FALSE, table=FALSE, ci.force = TRUE)
+summary(readme)
+summary(readme_rdd)
+texreg(list(readme_rdd, contrib_rdd), stars=NULL, digits=3, use.packages=FALSE,
+custom.model.names=c( 'README','CONTRIBUTING'),
+custom.coef.names=c('(Intercept)', 'Indtroduction', 'Week (Time)', 'Project Age', 'Introduction:Week', 'Event Gap'),
+table=FALSE, ci.force = TRUE)
+readme_groupings <- read.csv('../final_data/deb_readme_interaction_groupings.csv')
+contrib_groupings <- read.csv('../final_data/deb_contrib_interaction_groupings.csv')
+View(readme_groupings)
+library(tidyverse)
+readme_g <- readme_groupings |>
+ggplot(aes(x=rank, y=estimate, col = as.factor(ranef_grouping))) +
+geom_linerange(aes(ymin= conf.low, ymax= conf.high)) +
+theme_bw()
+readme_g
+subdirColors <-
+setNames( c('firebrick1', 'forestgreen', 'cornflowerblue')
+, 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) +
+theme_bw()
+readme_g
+contrib_groupings <- read.csv('../final_data/deb_contrib_interaction_groupings.csv')
+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) +
+theme_bw()
+contrib_g
+grid.arrange(readme_g, contrib_g, nrow = 1)
+library(gridExtra)
+grid.arrange(readme_g, contrib_g, nrow = 1)
+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()
+readme_g
+grid.arrange(readme_g, contrib_g, nrow = 1)
+grid.arrange(contrib_g, readme_g, nrow = 1)
+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) +
+theme_bw() +
+theme(legend.position = "top")
+grid.arrange(contrib_g, readme_g, nrow = 1)
+library(jtools)
+plot_summs(readme_rdd, contrib_rdd)
+?plot_summs
+plot_summs(readme_rdd, contrib_rdd, plot.distributions = TRUE)
+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 <- read_csv('../final_data/deb_contrib_did.csv')
+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$observation_type == "all"),]
+return(longer)
+}
+expanded_data <- expand_timeseries(contrib_df[1,])
+library(plyr)
+contrib_df <- read_csv('../final_data/deb_contrib_did.csv')
+col_order <- c("upstream_vcs_link", "age_in_days", "first_commit", "first_commit_dt", "event_gap", "event_date",  "event_hash", "before_all_ct", "after_all_ct", "before_mrg_ct", "after_mrg_ct", "before_auth_new", "after_auth_new", "before_commit_new",  "after_commit_new")
+contrib_df <- contrib_df[,col_order]
+contrib_df$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,]))
+}
+View(expand_timeseries)
+View(expanded_data)
+window_num <- 8
+windowed_data <- expanded_data |>
+filter(week >= (27 - window_num) & week <= (27 + window_num)) |>
+mutate(D = ifelse(week > 27, 1, 0))
+windowed_data$week_offset <- windowed_data$week - 27
+View(windowed_data)
+time_plot <- expanded_data |>
+ggplot(aes(x=week_offset, y=count))
+time_plot
+time_plot <- windowed_data |>
+ggplot(aes(x=week_offset, y=count))
+time_plot
+time_plot <- windowed_data |>
+ggplot(aes(x=week_offset, y=count)) +
+geom_point()
+time_plot
+time_plot <- windowed_data |>
+ggplot(aes(x=week_offset, y=median(count))) +
+geom_point()
+time_plot
+time_plot <- windowed_data |>
+ggplot(aes(x=week_offset, y=mean(count))) +
+geom_point()
+time_plot
+time_plot <- windowed_data |>
+ggplot(aes(x=week_offset, y=count)) +
+geom_point()
+time_plot
+all_actions_data <- windowed_data[which(windowed_data$observation_type == "all"),]
+all_actions_data$log1p_count <- log1p(all_actions_data$count)
+time_plot <- all_actions_data |>
+ggplot(aes(x=week_offset, y=log1p_count)) +
+geom_point()
+time_plot
+time_plot <- all_actions_data |>
+ggplot(aes(x=week_offset, y=log1p_count)) +
+geom_smooth()+
+geom_point()
+time_plot
+time_plot <- all_actions_data |>
+ggplot(aes(x=week_offset, y=log1p_count)) +
+geom_smooth()
+time_plot
+time_plot <- all_actions_data |>
+ggplot(aes(x=week_offset, y=log1p_count)) +
+geom_smooth() +
+theme_bw()
+time_plot
+windowed_readme_data$week_offset <- windowed_readme_data$week - 27
+all_actions_readme_data <- windowed_readme_data[which(windowed_readme_data$observation_type == "all"),]
+source("~/Desktop/git/24_deb_gov/R/gam_plot_documents.R")
+time_plot
+time_plot <- all_actions_data |>
+ggplot(aes(x=week_offset, y=log1p_count, color=factor(document_type))) +
+geom_smooth() +
+theme_bw()
+time_plot
+View(expanded_readme_data)
+mean(all_actions_readme_data$event_gap)
+mean(median$event_gap)
+median(all_actions_readme_data$event_gap)
+mean(all_actions_readme_data$event_gap)
+mean(all_actions_contrib_data$event_gap)
+median(all_actions_contrib_data$event_gap)
+time_plot <- all_actions_data |>
+ggplot(aes(x=week_offset, y=log1p_count, color=factor(document_type))) +
+geom_smooth() +
+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))) +
+geom_smooth() +
+geom_vline(x=0)
+theme_bw() +
+theme(legend.position = "top")
+time_plot <- all_actions_data |>
+ggplot(aes(x=week_offset, y=log1p_count, color=factor(document_type))) +
+geom_smooth() +
+geom_vline(x=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))) +
+geom_smooth() +
+geom_vline(x=0)+
+theme_bw() +
+theme(legend.position = "top")
+time_plot <- all_actions_data |>
+ggplot(aes(x=week_offset, y=log1p_count, color=factor(document_type))) +
+geom_smooth() +
+geom_vline(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))) +
+geom_smooth() +
+geom_vline(xintercept = 0)+
+theme_bw() +
+theme(legend.position = "top")
+time_plot
+#looking at event gap
+document_event_gap <- ggplot(all_actions_data, aes(x=event_gap, group=as.factor(document_type))) +
+geom_density(aes(color = as.factor(document_type), fill=as.factor(document_type)), alpha=0.2, position="identity") +
+theme_bw()
+document_event_gap
+#looking at event gap
+document_event_gap <- ggplot(all_actions_data, aes(x=scale(event_gap), group=as.factor(document_type))) +
+geom_density(aes(color = as.factor(document_type), fill=as.factor(document_type)), alpha=0.2, position="identity") +
+theme_bw()
+document_event_gap
+#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)
+mode(all_actions_contrib_data$event_gap)
+mean(all_actions_contrib_data$event_gap)
diff --git a/R/d_working_readability_plot.png b/R/d_working_readability_plot.png
new file mode 100644
index 0000000..b5f973d
Binary files /dev/null and b/R/d_working_readability_plot.png differ
diff --git a/R/documentReadabilityAnalysis.R b/R/documentReadabilityAnalysis.R
index bee6c23..47622f9 100644
--- a/R/documentReadabilityAnalysis.R
+++ b/R/documentReadabilityAnalysis.R
@@ -7,10 +7,11 @@ library(ggpubr)
 # gaughan@u.northwestern.edu
 # loading in the data 
 try(setwd(dirname(rstudioapi::getActiveDocumentContext()$path)))
-readme_df <- read_csv("../text_analysis/draft_readability_readme.csv")
-contributing_df <- read_csv("../text_analysis/draft_readability_contributing.csv")
+readme_df <- read_csv("../text_analysis/dwo_readability_readme.csv")
+contributing_df <- read_csv("../text_analysis/dwo_readability_contributing.csv")
 head(readme_df)
 aggregate(readme_df[, 3:10], list(readme_df$subdir), median)
+aggregate(contributing_df[, 3:10], list(contributing_df$subdir), median)
 #getting basic stats for the readme readability 
 median(readme_df$flesch_reading_ease)
 median(readme_df$linsear_write_formula)
diff --git a/R/draft_Rdd_groupings_plot.png b/R/draft_Rdd_groupings_plot.png
new file mode 100644
index 0000000..52ab7ad
Binary files /dev/null and b/R/draft_Rdd_groupings_plot.png differ
diff --git a/R/draft_average_over_time_plot.png b/R/draft_average_over_time_plot.png
new file mode 100644
index 0000000..f4a051a
Binary files /dev/null and b/R/draft_average_over_time_plot.png differ
diff --git a/R/draft_averages_plot.png b/R/draft_averages_plot.png
new file mode 100644
index 0000000..66f94ba
Binary files /dev/null and b/R/draft_averages_plot.png differ
diff --git a/R/draft_rdd_ranef_plot.png b/R/draft_rdd_ranef_plot.png
new file mode 100644
index 0000000..52ab7ad
Binary files /dev/null and b/R/draft_rdd_ranef_plot.png differ
diff --git a/R/dwo_working_readability.png b/R/dwo_working_readability.png
new file mode 100644
index 0000000..41aa09c
Binary files /dev/null and b/R/dwo_working_readability.png differ
diff --git a/R/gam_plot_documents.R b/R/gam_plot_documents.R
new file mode 100644
index 0000000..380b2d5
--- /dev/null
+++ b/R/gam_plot_documents.R
@@ -0,0 +1,70 @@
+#trying to make a time plot showing the over-time shift
+library(plyr) 
+contrib_df <- read_csv('../final_data/deb_contrib_did.csv')
+readme_df <- read_csv("../final_data/deb_readme_did.csv")
+col_order <- c("upstream_vcs_link", "age_in_days", "first_commit", "first_commit_dt", "event_gap", "event_date",  "event_hash", "before_all_ct", "after_all_ct", "before_mrg_ct", "after_mrg_ct", "before_auth_new", "after_auth_new", "before_commit_new",  "after_commit_new")
+#first contrib
+contrib_df <- contrib_df[,col_order]
+contrib_df$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$after_mrg_ct), ", ")
+drop <- c("before_all_ct", "before_mrg_ct", "after_all_ct", "after_mrg_ct")
+contrib_df = contrib_df[,!(names(contrib_df) %in% drop)]
+#then readme
+readme_df <- readme_df[,col_order]
+readme_df$ct_before_all <- str_split(gsub("[][]","", readme_df$before_all_ct), ", ")
+readme_df$ct_after_all <- str_split(gsub("[][]","", readme_df$after_all_ct), ", ")
+readme_df$ct_before_mrg <- str_split(gsub("[][]","", readme_df$before_mrg_ct), ", ")
+readme_df$ct_after_mrg <- str_split(gsub("[][]","", readme_df$after_mrg_ct), ", ")
+drop <- c("before_all_ct", "before_mrg_ct", "after_all_ct", "after_mrg_ct")
+readme_df = readme_df[,!(names(readme_df) %in% drop)]
+# 2 some expansion needs to happens for each project 
+expand_timeseries <- function(project_row) {
+  longer <- project_row |> 
+    pivot_longer(cols = starts_with("ct"),
+                 names_to = "window",
+                 values_to = "count") |>
+    unnest(count) 
+  longer$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_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,]))
+}
+expanded_readme_data <- expand_timeseries(readme_df[1,])
+for (i in 2:nrow(readme_df)){
+  expanded_readme_data <- rbind(expanded_readme_data, expand_timeseries(readme_df[i,]))
+}
+window_num <- 8
+windowed_contrib_data <- expanded_contrib_data |>
+  filter(week >= (27 - window_num) & week <= (27 + window_num)) |>
+  mutate(D = ifelse(week > 27, 1, 0))
+windowed_readme_data <- expanded_readme_data |>
+  filter(week >= (27 - window_num) & week <= (27 + window_num)) |>
+  mutate(D = ifelse(week > 27, 1, 0))
+
+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$count))
+windowed_readme_data$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_data <- rbind(all_actions_contrib_data, all_actions_readme_data)
+all_actions_data$log1p_count <- log1p(all_actions_data$count)
+time_plot <- all_actions_data |>
+  ggplot(aes(x=week_offset, y=log1p_count, color=factor(document_type))) + 
+  geom_smooth() +
+  geom_vline(xintercept = 0)+
+  theme_bw() +
+  theme(legend.position = "top")
+time_plot
+#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)
diff --git a/R/model_presentation.R b/R/model_presentation.R
new file mode 100644
index 0000000..bdb7887
--- /dev/null
+++ b/R/model_presentation.R
@@ -0,0 +1,42 @@
+library(tidyverse)
+library(texreg)
+
+readme_rdd <- readRDS("final_models/0624_readme_all_rdd.rda")
+contrib_rdd <- readRDS("final_models/0624_contrib_all_rdd.rda")
+summary(readme_rdd)
+
+texreg(list(readme_rdd, contrib_rdd), stars=NULL, digits=3, use.packages=FALSE, 
+       custom.model.names=c( 'README','CONTRIBUTING'),
+       custom.coef.names=c('(Intercept)', 'Indtroduction', 'Week (Time)', 'Project Age', 'Introduction:Week', 'Event Gap'), 
+       table=FALSE, ci.force = TRUE)
+
+readme_groupings <- read.csv('../final_data/deb_readme_interaction_groupings.csv')
+contrib_groupings <- read.csv('../final_data/deb_contrib_interaction_groupings.csv')
+
+subdirColors <-
+  setNames( c('firebrick1', 'forestgreen', 'cornflowerblue')
+            , 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()
+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) + 
+  theme_bw() +
+  theme(legend.position = "top") 
+contrib_g
+
+library(gridExtra)
+grid.arrange(contrib_g, readme_g, nrow = 1)
+library(jtools)
+plot_summs(readme_rdd, contrib_rdd, plot.distributions = TRUE)
+?plot_summs
+