513 lines
23 KiB
R
513 lines
23 KiB
R
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$age_of_project = NULL
|
|
head(new_rm_data)
|
|
write.csv(new_rm_data, file = "../final_data/deb_readme_did_updated.csv", row.names = FALSE)
|
|
old_pop_readme <- merge(old_pop_readme, first_commit_df, by="upstream_vcs_link")
|
|
####PopChange CSV
|
|
old_pop_readme <- read_csv("../final_data/deb_readme_pop_change.csv")
|
|
old_pop_readme <- merge(old_pop_readme, first_commit_df, by="upstream_vcs_link")
|
|
new_pop_data <- old_pop_readme |>
|
|
mutate(first_commit_dt = as.POSIXct(first_commit,
|
|
format = "%a %b %d %H:%M:%S %Y %z")) |>
|
|
mutate(age_in_days =
|
|
as.numeric(
|
|
difftime(
|
|
as.POSIXct("2024-06-24 00:00:00", format = "%Y-%m-%d %H:%M:%S"),
|
|
first_commit_dt,
|
|
units = "days"))) |>
|
|
mutate (event_gap =
|
|
as.numeric(
|
|
difftime(
|
|
as.POSIXct(event_date, format = "%Y-%m-%d %H:%M:%S"),
|
|
first_commit_dt,
|
|
units = "days")))
|
|
new_pop_data$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()$path)))
|
|
#load in data
|
|
full_df <- read_csv("../final_data/deb_full_data.csv")
|
|
contrib_df <- read_csv("../final_data/deb_contrib_pop_change.csv")
|
|
readme_df <- read_csv("../final_data/deb_readme_pop_change.csv")
|
|
contrib_df <- merge(full_df, contrib_df, by="upstream_vcs_link")
|
|
readme_df <- merge(full_df, readme_df, by="upstream_vcs_link")
|
|
# age is calculated against December 11, 2023
|
|
#some expansion needs to happens for each project
|
|
expand_timeseries <- function(project_row) {
|
|
longer <- project_row |>
|
|
pivot_longer(cols = ends_with("new"),
|
|
names_to = "window",
|
|
values_to = "count") |>
|
|
unnest(count) |>
|
|
mutate(after_doc = as.numeric(str_detect(window, "after"))) |>
|
|
mutate(is_collab = as.numeric(str_detect(window, "collab")))
|
|
return(longer)
|
|
}
|
|
expanded_readme_data <- expand_timeseries(readme_df[1,])
|
|
for (i in 2:nrow(readme_df)){
|
|
expanded_readme_data <- rbind(expanded_readme_data, expand_timeseries(readme_df[i,]))
|
|
}
|
|
expanded_contrib_data <- expand_timeseries(contrib_df[1,])
|
|
for (i in 2:nrow(contrib_df)){
|
|
expanded_contrib_data <- rbind(expanded_contrib_data, expand_timeseries(contrib_df[i,]))
|
|
}
|
|
expanded_readme_data$log1pcount <- log1p(expanded_readme_data$count)
|
|
expanded_contrib_data$log1pcount <- log1p(expanded_contrib_data$count)
|
|
#breaking out the types of population counts
|
|
collab_pop_readme <- expanded_readme_data[which(expanded_readme_data$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)
|