2024-07-12 03:22:07 +00:00
|
|
|
hist(contrib_df$event_gap)
|
|
|
|
|
median(contrib_df$event_gap)
|
|
|
|
|
1786.431 / 265
|
|
|
|
|
1786.431 / 365
|
|
|
|
|
sd(contrib_df$event_gap)
|
|
|
|
|
sd(contrib_df$event_gap)
|
|
|
|
|
max(readme_df$event_gap)
|
|
|
|
|
#all_gmodel <- glmer.nb(log1p_count ~ D * week_offset + scaled_project_age + scaled_event_gap + (D * week_offset | upstream_vcs_link),
|
|
|
|
|
# control=glmerControl(optimizer="bobyqa",
|
|
|
|
|
# optCtrl=list(maxfun=2e5)), nAGQ=0, data=all_actions_data)
|
|
|
|
|
all_gmodel <- readRDS("0710_contrib_all.rda")
|
|
|
|
|
summary(all_gmodel)
|
|
|
|
|
library(tidyverse)
|
|
|
|
|
library(texreg)
|
|
|
|
|
readme_rdd <- readRDS("final_models/0624_readme_all_rdd.rda")
|
|
|
|
|
contrib_rdd <- readRDS("final_models/0710_contrib_all.rda")
|
|
|
|
|
contrib_rdd <- readRDS("final_models/0710_contrib_all_rdd.rda")
|
|
|
|
|
texreg(list(readme_rdd, contrib_rdd), stars=NULL, digits=3, use.packages=FALSE,
|
|
|
|
|
custom.model.names=c( 'README','CONTRIBUTING'),
|
|
|
|
|
custom.coef.names=c('(Intercept)', 'Indtroduction', 'Week (Time)', 'Project Age', 'Introduction:Week', 'Event Gap'),
|
|
|
|
|
table=FALSE, ci.force = TRUE)
|
|
|
|
|
source("~/Desktop/git/24_deb_gov/R/contribCrescAnalysis.R")
|
|
|
|
|
#all_gmodel <- readRDS("0710_contrib_all.rda")
|
|
|
|
|
summary(all_gmodel)
|
|
|
|
|
saveRDS(all_gmodel, "0710_contrib_cresc.rda")
|
|
|
|
|
range(all_actions_data$log1p_count)
|
|
|
|
|
source("~/Desktop/git/24_deb_gov/R/contribRDDAnalysis.R")
|
|
|
|
|
source("~/Desktop/git/24_deb_gov/R/contribRDDAnalysis.R")
|
|
|
|
|
all_gmodel <- readRDS("0711_contrib_all.rda")
|
|
|
|
|
summary(all_gmodel)
|
|
|
|
|
library(tidyverse)
|
|
|
|
|
library(texreg)
|
|
|
|
|
library(tidyverse)
|
|
|
|
|
library(texreg)
|
|
|
|
|
readme_rdd <- readRDS("final_models/0624_readme_all_rdd.rda")
|
|
|
|
|
contrib_rdd <- readRDS("final_models/0711_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)
|
|
|
|
|
contrib_rdd <- readRDS("final_models/0711_contrib_all_rdd.rda")
|
|
|
|
|
contrib_rdd <- readRDS("final_models/0711_contrib_all_rdd.rda")
|
|
|
|
|
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)
|
|
|
|
|
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'),
|
|
|
|
|
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')
|
|
|
|
|
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)
|
|
|
|
|
source("~/Desktop/git/24_deb_gov/R/contribRDDAnalysis.R")
|
2024-07-15 22:20:46 +00:00
|
|
|
source("~/Desktop/git/24_deb_gov/R/documentReadabilityAnalysis.R")
|
|
|
|
|
contrib_pop_df <- read_csv("../final_data/deb_contrib_pop_change.csv")
|
|
|
|
|
contrib_df <- read_csv("../final_data/deb_contrib_did.csv")
|
|
|
|
|
View(contrib_pop_df)
|
|
|
|
|
contrib_readability_df <- read_csv('../text_analysis/dwo_readability_contributing.csv')
|
|
|
|
|
View(contrib_readability_df)
|
|
|
|
|
View(contrib_pop_df)
|
|
|
|
|
View(contrib_readability_df)
|
|
|
|
|
View(contrib_pop_df)
|
|
|
|
|
View(contrib_readability_df)
|
|
|
|
|
View(contrib_pop_df)
|
|
|
|
|
View(contrib_pop_df)
|
|
|
|
|
View(contrib_df)
|
|
|
|
|
View(contrib_pop_df)
|
|
|
|
|
View(contrib_readability_df)
|
|
|
|
|
View(contrib_pop_df)
|
|
|
|
|
#concat dataframes into central data
|
|
|
|
|
contrib_df_total <- contrib_pop_df |>
|
|
|
|
|
mutate(project_name = str_split(upstream_vcs_link, pattern="/")[-1])
|
|
|
|
|
View(contrib_pop_df)
|
|
|
|
|
View(contrib_readability_df)
|
|
|
|
|
View(contrib_readability_df)
|
|
|
|
|
contrib_df_total <- contrib_readability_df |>
|
|
|
|
|
mutate(project_name = str_split(filename, pattern="_")[-2])
|
|
|
|
|
View(contrib_readability_df)
|
|
|
|
|
contrib_df_total <- contrib_readability_df |>
|
|
|
|
|
mutate(project_name = str_split(filename, pattern="_"))
|
|
|
|
|
View(contrib_df_total)
|
|
|
|
|
contrib_df_total <- contrib_readability_df |>
|
|
|
|
|
mutate(project_name = str_split(filename, pattern="_")[0])
|
|
|
|
|
contrib_df_total <- contrib_readability_df |>
|
|
|
|
|
mutate(project_name = str_split(filename, pattern="_")[1])
|
|
|
|
|
View(contrib_df_total)
|
|
|
|
|
contrib_df_total <- contrib_readability_df |>
|
|
|
|
|
mutate(project_name = str_split(filename, pattern="_")[1] |>
|
|
|
|
|
sapply("[[", 1))
|
|
|
|
|
View(contrib_df_total)
|
|
|
|
|
contrib_df_total <- contrib_readability_df |>
|
|
|
|
|
mutate(project_name = str_split(filename, pattern="_"))
|
|
|
|
|
View(contrib_df_total)
|
|
|
|
|
contrib_df_total <- contrib_readability_df |>
|
|
|
|
|
mutate(project_name_array = str_split(filename, pattern="_")) |>
|
|
|
|
|
mutate(projes_name = project_name_array[1])
|
|
|
|
|
View(contrib_df_total)
|
|
|
|
|
View(contrib_readability_df)
|
|
|
|
|
View(contrib_pop_df)
|
|
|
|
|
#concat dataframes into central data
|
|
|
|
|
contrib_pop_df <- contrib_pop_df %>%
|
|
|
|
|
mutate(first_element = map_chr(upstream_vcs_link, ~ {
|
|
|
|
|
parts <- str_split(.x, pattern = "/")[[1]]
|
|
|
|
|
if (length(parts) >= 1) {
|
|
|
|
|
parts[1] # Extract the first element after splitting
|
|
|
|
|
} else {
|
|
|
|
|
NA_character_
|
|
|
|
|
}
|
|
|
|
|
}))
|
|
|
|
|
View(contrib_pop_df)
|
|
|
|
|
contrib_df_total <- contrib_readability_df |>
|
|
|
|
|
mutate(project_name = map_chr(filename, ~ {
|
|
|
|
|
parts <- str_split(.x, pattern = "_")[[1]]
|
|
|
|
|
if (length(parts) >= 1) {
|
|
|
|
|
parts[1]
|
|
|
|
|
} else {
|
|
|
|
|
NA_character_
|
|
|
|
|
}
|
|
|
|
|
}))
|
|
|
|
|
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_df_total <- contrib_readability_df |>
|
|
|
|
|
mutate(project_name = map_chr(filename, ~ {
|
|
|
|
|
parts <- str_split(.x, pattern = "_")[[1]]
|
|
|
|
|
if (length(parts) >= 1) {
|
|
|
|
|
parts[1]
|
|
|
|
|
} else {
|
|
|
|
|
NA_character_
|
|
|
|
|
}
|
|
|
|
|
}))
|
|
|
|
|
View(contrib_df_total)
|
|
|
|
|
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[-1]
|
|
|
|
|
} else {
|
|
|
|
|
NA_character_
|
|
|
|
|
}
|
|
|
|
|
}))
|
|
|
|
|
parts[length(parts)]
|
|
|
|
|
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_
|
|
|
|
|
}
|
|
|
|
|
}))
|
|
|
|
|
View(contrib_pop_df)
|
|
|
|
|
source("~/Desktop/git/24_deb_gov/R/docChar_outcomes.R")
|
|
|
|
|
source("~/Desktop/git/24_deb_gov/R/docChar_outcomes.R")
|
|
|
|
|
contrib_total_df <- contrib_pop_df |>
|
|
|
|
|
left_join(contrib_readability_df, by="project_name")
|
|
|
|
|
View(contrib_total_df)
|
|
|
|
|
# test regressions
|
|
|
|
|
lm1 <- glm.nb(after_contrib_new ~ word_count, data = contrib_total_df)
|
|
|
|
|
# test regressions
|
|
|
|
|
library(MASS)
|
|
|
|
|
lm1 <- glm.nb(after_contrib_new ~ word_count, data = contrib_total_df)
|
|
|
|
|
summary(lm1)
|
|
|
|
|
View(contrib_total_df)
|
|
|
|
|
contrib_total_df <- contrib_pop_df |>
|
|
|
|
|
join(contrib_readability_df, by="project_name")
|
|
|
|
|
View(contrib_total_df)
|
|
|
|
|
View(contrib_readability_df)
|
|
|
|
|
qqnorm(residuals(lm1))
|
|
|
|
|
source("~/Desktop/git/24_deb_gov/R/docChar_outcomes.R")
|
|
|
|
|
lm1 <- glm.nb(after_contrib_new ~ linsear_write, data = contrib_total_df)
|
|
|
|
|
lm1 <- glm.nb(after_contrib_new ~ linsear, data = contrib_total_df)
|
|
|
|
|
View(contrib_total_df)
|
|
|
|
|
lm1 <- glm.nb(after_contrib_new ~ linsear_write_formula, data = contrib_total_df)
|
|
|
|
|
qqnorm(residuals(lm1))
|
|
|
|
|
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)
|
