2024-06-25 00:26:55 +00:00
|
|
|
new_pop_data <- old_pop_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")))
|
|
|
|
|
new_pop_data$age_of_project = NULL
|
|
|
|
|
head(new_pop_data)
|
|
|
|
|
write.csv(new_pop_data, file = "../final_data/deb_readme_pop_change_updated.csv", row.names = FALSE)
|
|
|
|
|
#CONTRIBUTING Document updates
|
|
|
|
|
first_commit_contrib <- read_csv("../062424_did_first_commit_contrib.csv")
|
|
|
|
|
####RDD CSV
|
|
|
|
|
old_rdd_contrib <- read_csv("../final_data/deb_contrib_did.csv")
|
|
|
|
|
old_rdd_contrib <- merge(old_rdd_contrib, first_commit_contrib, by="upstream_vcs_link")
|
|
|
|
|
new_rdd_contrib_data <- old_rdd_contrib |>
|
|
|
|
|
mutate(first_commit_dt = as.POSIXct(first_commit,
|
|
|
|
|
format = "%a %b %d %H:%M:%S %Y %z")) |>
|
|
|
|
|
mutate(age_in_days =
|
|
|
|
|
as.numeric(
|
|
|
|
|
difftime(
|
|
|
|
|
as.POSIXct("2024-06-24 00:00:00", format = "%Y-%m-%d %H:%M:%S"),
|
|
|
|
|
first_commit_dt,
|
|
|
|
|
units = "days"))) |>
|
|
|
|
|
mutate (event_gap =
|
|
|
|
|
as.numeric(
|
|
|
|
|
difftime(
|
|
|
|
|
as.POSIXct(event_date, format = "%Y-%m-%d %H:%M:%S"),
|
|
|
|
|
first_commit_dt,
|
|
|
|
|
units = "days")))
|
|
|
|
|
new_rdd_contrib_data$age_of_project = NULL
|
|
|
|
|
View(new_rdd_contrib_data)
|
|
|
|
|
write.csv(new_rdd_contrib_data, file = "../final_data/deb_contrib_did_change_updated.csv", row.names = FALSE)
|
|
|
|
|
####PopChange CSV
|
|
|
|
|
old_pop_contrib <- read_csv("../final_data/deb_contrib_pop_change.csv")
|
|
|
|
|
old_pop_contrib <- merge(old_pop_contrib, first_commit_contrib, by="upstream_vcs_link")
|
|
|
|
|
new_pop_contrib_data <- old_pop_contrib |>
|
|
|
|
|
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_pop_contrib_data$age_of_project = NULL
|
|
|
|
|
write.csv(new_pop_contrib_data, file = "../final_data/deb_contrib_pop_change_updated.csv", row.names = FALSE)
|
|
|
|
|
library(tidyverse)
|
|
|
|
|
library(plyr)
|
|
|
|
|
library(stringr)
|
|
|
|
|
try(setwd(dirname(rstudioapi::getActiveDocumentContext()$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")
|
|
|
|
|
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
|
2024-06-24 03:10:17 +00:00
|
|
|
#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)
|
|
|
|
|
}
|
2024-06-25 00:26:55 +00:00
|
|
|
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,]))
|
|
|
|
|
}
|
2024-06-24 03:10:17 +00:00
|
|
|
expanded_contrib_data <- expand_timeseries(contrib_df[1,])
|
2024-06-25 00:26:55 +00:00
|
|
|
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)
|
|
|
|
|
#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)
|
|
|
|
|
library(MASS)
|
|
|
|
|
simple_collab_readme_model <- glm.nb(count ~ as.factor(after_doc), data=collab_pop_readme)
|
|
|
|
|
summary(simple_collab_readme_model)
|
|
|
|
|
simple_collab_readme_model <- glm.nb(count ~ as.factor(after_doc) + age_in_days, data=collab_pop_readme)
|
|
|
|
|
summary(simple_collab_readme_model)
|
|
|
|
|
simple_collab_readme_model <- glm.nb(count ~ as.factor(after_doc) + scaled(age_in_days), data=collab_pop_readme)
|
|
|
|
|
simple_collab_readme_model <- glm.nb(count ~ as.factor(after_doc) + scale(age_in_days), data=collab_pop_readme)
|
|
|
|
|
summary(simple_collab_readme_model)
|
|
|
|
|
qqnorm(residuals(simple_collab_readme_model))
|
|
|
|
|
simple_readme_model <- glm.nb(count ~ as.factor(after_doc) + scale(age_in_days), data=contrib_pop_readme)
|
|
|
|
|
summary(simple_collab_readme_model)
|
|
|
|
|
qqnorm(residuals(simple_collab_readme_model))
|
|
|
|
|
simple_readme_model <- glm.nb(count ~ as.factor(after_doc) + scale(age_in_days), data=expanded_readme_data)
|
|
|
|
|
summary(simple_collab_readme_model)
|
|
|
|
|
qqnorm(residuals(simple_collab_readme_model))
|
|
|
|
|
View(expanded_readme_data)
|
|
|
|
|
library(tidyverse)
|
|
|
|
|
library(plyr)
|
|
|
|
|
library(stringr)
|
|
|
|
|
try(setwd(dirname(rstudioapi::getActiveDocumentContext()$path)))
|
|
|
|
|
#load in data
|
|
|
|
|
full_df <- read_csv("../final_data/deb_full_data.csv")
|
|
|
|
|
contrib_df <- read_csv("../final_data/deb_contrib_pop_change.csv")
|
|
|
|
|
readme_df <- read_csv("../final_data/deb_readme_pop_change.csv")
|
|
|
|
|
contrib_df <- merge(full_df, contrib_df, by="upstream_vcs_link")
|
|
|
|
|
readme_df <- merge(full_df, readme_df, by="upstream_vcs_link")
|
|
|
|
|
# age is calculated against December 11, 2023
|
|
|
|
|
#some expansion needs to happens for each project
|
|
|
|
|
expand_timeseries <- function(project_row) {
|
|
|
|
|
longer <- project_row |>
|
|
|
|
|
pivot_longer(cols = ends_with("new"),
|
|
|
|
|
names_to = "window",
|
|
|
|
|
values_to = "count") |>
|
|
|
|
|
unnest(count) |>
|
|
|
|
|
mutate(after_doc = as.numeric(str_detect(window, "after"))) |>
|
|
|
|
|
mutate(is_collab = as.numeric(str_detect(window, "collab")))
|
|
|
|
|
return(longer)
|
|
|
|
|
}
|
|
|
|
|
expanded_readme_data <- expand_timeseries(readme_df[1,])
|
|
|
|
|
for (i in 2:nrow(readme_df)){
|
|
|
|
|
expanded_readme_data <- rbind(expanded_readme_data, expand_timeseries(readme_df[i,]))
|
|
|
|
|
}
|
|
|
|
|
expanded_contrib_data <- expand_timeseries(contrib_df[1,])
|
|
|
|
|
for (i in 2:nrow(contrib_df)){
|
|
|
|
|
expanded_contrib_data <- rbind(expanded_contrib_data, expand_timeseries(contrib_df[i,]))
|
|
|
|
|
}
|
|
|
|
|
expanded_readme_data$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$count)
|
|
|
|
|
#scale age
|
|
|
|
|
expanded_readme_data$scaled_age <- scale(expanded_readme_data$age_in_days)
|
|
|
|
|
expanded_contrib_data$scaled_age <- scale(expanded_contrib_data$age_in_days)
|
|
|
|
|
#breaking out the types of population counts
|
|
|
|
|
collab_pop_readme <- expanded_readme_data[which(expanded_readme_data$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)
|
|
|
|
|
library(MASS)
|
|
|
|
|
simple_readme_model <- glm.nb(count ~ as.factor(after_doc) + scale(age_in_days), data=expanded_readme_data)
|
|
|
|
|
summary(simple_collab_readme_model)
|
|
|
|
|
simple_collab_readme_model <- glm.nb(count ~ as.factor(after_doc) + scale(age_in_days), data=collab_pop_readme)
|
|
|
|
|
summary(simple_collab_readme_model)
|
|
|
|
|
qqnorm(residuals(simple_collab_readme_model))
|
|
|
|
|
View(contrib_pop_readme)
|
|
|
|
|
simple_contrib_readme_model <- glm.nb(count ~ as.factor(after_doc) + scale(age_in_days), data=collab_pop_readme)
|
|
|
|
|
summary(simple_contrib_readme_model)
|
|
|
|
|
qqnorm(residuals(simple_contrib_readme_model))
|
|
|
|
|
View(collab_pop_readme)
|
|
|
|
|
View(collab_pop_readme)
|
|
|
|
|
View(contrib_pop_readme)
|
|
|
|
|
#contrib_readme_model <- readRDS("final_models/0623_pop_rm_contrib.rda")
|
|
|
|
|
collab_contrib_model <- glmer.nb(log1pcount ~ after_doc + (after_doc| upstream_vcs_link), data=collab_pop_contrib)
|
|
|
|
|
#contrib docs
|
|
|
|
|
simple_collab_contrib_model <- glm.nb(count ~ as.factor(after_doc) + scale(age_in_days), data=collab_pop_contrib)
|
|
|
|
|
summary(simple_collab_contrib_model)
|
|
|
|
|
#readme docs
|
|
|
|
|
simple_collab_readme_model <- glm.nb(log1pcount ~ as.factor(after_doc) + scale(age_in_days), data=collab_pop_readme)
|
|
|
|
|
summary(simple_collab_readme_model)
|
|
|
|
|
simple_contrib_readme_model <- glm.nb(log1pcount ~ as.factor(after_doc) + scale(age_in_days), data=collab_pop_readme)
|
|
|
|
|
summary(simple_contrib_readme_model)
|
|
|
|
|
# I don't think MLM is the right one
|
|
|
|
|
collab_readme_model <- glmer.nb(log1pcount ~ as.factor(after_doc) + scaled_age + (after_doc| upstream_vcs_link), data=collab_pop_readme)
|
|
|
|
|
summary(collab_readme_model)
|
|
|
|
|
saveRDS(collab_readme_model, "final_models/0624_pop_rm_collab_better.rda")
|
|
|
|
|
contrib_readme_model <- glmer.nb(log1pcount ~ as.factor(after_doc) + scaled_age + (after_doc| upstream_vcs_link), data=contrib_pop_readme)
|
|
|
|
|
summary(collab_contrib_model)
|
|
|
|
|
summary(contrib_readme_model)
|
|
|
|
|
summary(collab_readme_model)
|
|
|
|
|
summary(contrib_readme_model)
|
|
|
|
|
saveRDS(contrib_readme_model, "final_models/0624_pop_rm_contrib.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', 'etc'),
|
|
|
|
|
use.packages=FALSE, table=FALSE, ci.force = TRUE)
|
|
|
|
|
#contrib_readme_model <- readRDS("final_models/0623_pop_rm_contrib.rda")
|
|
|
|
|
collab_contrib_model <- glmer.nb(log1pcount ~ after_doc + scaled_age + (after_doc| upstream_vcs_link), data=collab_pop_contrib)
|
|
|
|
|
summary(collab_contrib_model)
|
|
|
|
|
contrib_pop_readme |>
|
|
|
|
|
ggplot(aes(x = after_doc, y = log1pcount, col = as.factor(after_doc))) +
|
|
|
|
|
geom_violin()
|
|
|
|
|
View(contrib_pop_contrib)
|
|
|
|
|
#contrib_readme_model <- readRDS("final_models/0623_pop_rm_contrib.rda")
|
|
|
|
|
#contributing models are not statistically significant
|
|
|
|
|
contrib_contrib_model <- glm.nb(log1pcount ~ as.factor(after_doc) + event_gap , data=contrib_pop_contrib)
|
|
|
|
|
summary(contrib_contrib_model)
|
|
|
|
|
#contrib_readme_model <- readRDS("final_models/0623_pop_rm_contrib.rda")
|
|
|
|
|
#contributing models are not statistically significant
|
|
|
|
|
contrib_contrib_model <- glmer.nb(log1pcount ~ as.factor(after_doc) + event_gap + (after_doc | upstream_vcs_link), data=contrib_pop_contrib)
|
|
|
|
|
#contrib_readme_model <- readRDS("final_models/0623_pop_rm_contrib.rda")
|
|
|
|
|
#contributing models are not statistically significant
|
|
|
|
|
contrib_contrib_model <- glmer.nb(log1pcount ~ as.factor(after_doc) + scale(event_gap) + (after_doc | upstream_vcs_link), data=contrib_pop_contrib)
|
|
|
|
|
summary(contrib_contrib_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 <- readRDS("0512_contrib_all.rda")
|
|
|
|
|
summary(all_gmodel)
|
2024-06-28 04:40:08 +00:00
|
|
|
#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)
|
