2024-04-02 23:49:49 +00:00
|
|
|
qqnorm(octo_data$issue_mmt)
|
|
|
|
|
qqnorm(log(octo_data$issue_mmt))
|
|
|
|
|
qqnorm(residuals(octo_data$issue_mmt))
|
|
|
|
|
qqnorm(octo_data$issue_mmt)
|
|
|
|
|
qqnorm(log(octo_data$issue_mmt))
|
|
|
|
|
qqnorm(octo_data$issue_mmt)
|
|
|
|
|
hist(log(octo_data$issue_mmt))
|
|
|
|
|
hist(sqrt(octo_data$issue_mmt))
|
|
|
|
|
#below are the models for the octo data, there should be analysis for each one
|
|
|
|
|
octo_mmtmodel1 <- lm(underproduction_mean ~ mmt + new.age.factor, data=octo_data)
|
|
|
|
|
summary(octo_mmtmodel1)
|
|
|
|
|
#below are the models for the octo data, there should be analysis for each one
|
|
|
|
|
octo_mmtmodel1 <- lm(underproduction_mean ~ mmt + new.age.factor, data=octo_data)
|
|
|
|
|
summary(octo_mmtmodel1)
|
|
|
|
|
# below this is the analysis for the octo data
|
|
|
|
|
octo_data$new.age <- as.numeric(cut(octo_data$age_of_project/365, breaks=c(0,7.524197,10.323056,13.649367,17), labels=c(1,2,3,4)))
|
|
|
|
|
table(octo_data$new.age)
|
|
|
|
|
octo_data$new.age.factor <- as.factor(octo_data$new.age)
|
|
|
|
|
hist(octo_data$new.age)
|
|
|
|
|
#below are the models for the octo data, there should be analysis for each one
|
|
|
|
|
octo_mmtmodel1 <- lm(underproduction_mean ~ mmt + new.age.factor, data=octo_data)
|
|
|
|
|
summary(octo_mmtmodel1)
|
|
|
|
|
hist(sqrt(octo_data$issue_mmt))
|
|
|
|
|
hist(sqrt(octo_data$issue_mmt))
|
|
|
|
|
hist(octo_data$issue_mmt)
|
|
|
|
|
#right skewed data, need to transform
|
|
|
|
|
library(rcompanion)
|
|
|
|
|
install.packages(rcompanion)
|
|
|
|
|
hist(sqrt(octo_data$issue_mmt))
|
|
|
|
|
qqnorm(1/octo_data$issue_mmt)
|
|
|
|
|
hist(1/octo_data$issue_mmt)
|
|
|
|
|
hist(log(octo_data$issue_mmt))
|
|
|
|
|
hist(sqrt(octo_data$issue_mmt))
|
|
|
|
|
hist(log(octo_data$issue_mmt))
|
|
|
|
|
octo_data$sqrt_issue_mmt <- sqrt(octo_data$issue_mmt)
|
|
|
|
|
sqrt_issue_mmtmodel1 <- lm(underproduction_mean ~ sqrt_issue_mmt + new.age.factor, data=octo_data)
|
|
|
|
|
summary(sqrt_issue_mmtmodel1)
|
|
|
|
|
summary(issue_mmtmodel1)
|
|
|
|
|
octo_data$wiki_mmt <- ((octo_data$wiki_contrib_count * 2) + (octo_data$total_contrib - octo_data$wiki_contrib_count)) / (octo_data$total_contrib)
|
|
|
|
|
hist(octo_data$wiki_mmt)
|
|
|
|
|
wiki_mmtmodel1 <- lm(underproduction_mean ~ wiki_mmt + new.age.factor, data=octo_data)
|
|
|
|
|
summary(wiki_mmtmodel1)
|
|
|
|
|
g3 <- ggplot(octo_data, aes(wiki_mmt)) + geom_histogram(binwidth = 5)
|
|
|
|
|
g3
|
|
|
|
|
g3 <- ggplot(octo_data, aes(wiki_mmt)) + geom_histogram(binwidth = 0.05)
|
|
|
|
|
g3
|
|
|
|
|
g3 <- ggplot(octo_data, aes(wiki_mmt)) + geom_histogram(binwidth = 0.05) + theme_bw()
|
|
|
|
|
g3
|
|
|
|
|
g3 <- ggplot(octo_data, aes(wiki_mmt)) + geom_histogram(binwidth = 0.01) + theme_bw()
|
|
|
|
|
g3
|
|
|
|
|
g2 <- ggplot(octo_data, aes(issue_mmt)) + geom_histogram(binwidth = 0.01) + theme_bw()
|
|
|
|
|
g2
|
|
|
|
|
g1 <- ggplot(octo_data, aes(sqrt_issue_mmt)) + geom_histogram(binwidth = 0.01) + theme_bw()
|
|
|
|
|
g1
|
|
|
|
|
g3 <- ggplot(octo_data, aes(wiki_mmt)) + geom_histogram(binwidth = 0.01) + theme_bw()
|
|
|
|
|
g3
|
|
|
|
|
g2 <- ggplot(octo_data, aes(issue_mmt)) + geom_histogram(binwidth = 0.01) + theme_bw()
|
|
|
|
|
g2
|
|
|
|
|
texreg(list(octo_mmtmodel1, issue_mmtmodel1, wiki_mmtmodel1), stars=NULL, digits=2,
|
|
|
|
|
custom.model.names=c( 'M1: augm. formality','M2: MMT', 'M3: milestones' ),
|
|
|
|
|
custom.coef.names=c('(Intercept)', 'Augmented formality', 'MMT', 'Age-2', 'Age-3', 'Age-4', 'Milestones'),
|
|
|
|
|
use.packages=FALSE, table=FALSE, ci.force = TRUE)
|
|
|
|
|
source('powerAnalysis.R') #my little "lib"
|
|
|
|
|
texreg(list(octo_mmtmodel1, issue_mmtmodel1, wiki_mmtmodel1), stars=NULL, digits=2,
|
|
|
|
|
custom.model.names=c( 'M1: augm. formality','M2: MMT', 'M3: milestones' ),
|
|
|
|
|
custom.coef.names=c('(Intercept)', 'Augmented formality', 'MMT', 'Age-2', 'Age-3', 'Age-4', 'Milestones'),
|
|
|
|
|
use.packages=FALSE, table=FALSE, ci.force = TRUE)
|
|
|
|
|
library(texreg) #my little "lib"
|
|
|
|
|
texreg(list(octo_mmtmodel1, issue_mmtmodel1, wiki_mmtmodel1), stars=NULL, digits=2,
|
|
|
|
|
custom.model.names=c( 'M1: augm. formality','M2: MMT', 'M3: milestones' ),
|
|
|
|
|
custom.coef.names=c('(Intercept)', 'Augmented formality', 'MMT', 'Age-2', 'Age-3', 'Age-4', 'Milestones'),
|
|
|
|
|
use.packages=FALSE, table=FALSE, ci.force = TRUE)
|
|
|
|
|
texreg(list(octo_mmtmodel1, issue_mmtmodel1, wiki_mmtmodel1), stars=NULL, digits=2,
|
|
|
|
|
custom.model.names=c( 'M1: MMT','M2: issue contrib.', 'M3: wiki_contrib.' ),
|
|
|
|
|
custom.coef.names=c('(Intercept)', 'MMT', 'Issues', 'Age-2', 'Age-3', 'Age-4', 'Wiki'),
|
|
|
|
|
use.packages=FALSE, table=FALSE, ci.force = TRUE)
|
2024-04-08 02:00:01 +00:00
|
|
|
glimpse(readme_df)
|
|
|
|
|
library(tidyverse)
|
|
|
|
|
#set wd, read in data
|
|
|
|
|
try(setwd(dirname(rstudioapi::getActiveDocumentContext()$path)))
|
|
|
|
|
readme_df <- read_csv("../final_data/deb_readme_did.csv")
|
|
|
|
|
contributing_df <- read_csv("../final_data/deb_contrib_did.csv")
|
|
|
|
|
glimpse(readme_df)
|
|
|
|
|
head(readme_df)
|
|
|
|
|
colnames(readme_df) <- c("upstream_vcs_link", "event_date", "event_hash", "before_all_cnt", "before_mrg_cnt", "after_all_cnt", "after_mrg_cnt", "before_auth_new", "after_commit_new", "after_auth_new", "before_commit_new")
|
|
|
|
|
glimpse(readme_df)
|
|
|
|
|
col_order <- c("upstream_vcs_link", "event_date", "event_hash", "before_all_cnt", "after_all_cnt", "before_mrg_cnt", "after_mrg_cnt", "before_auth_new", "after_auth_new", "before_commit_new", "after_commit_new")
|
|
|
|
|
readme_df <- readme_df[,col_order]
|
|
|
|
|
glimpse(readme_df)
|
|
|
|
|
#TODO: turn character type into vector of numbers
|
|
|
|
|
str_split(test, ", ")
|
|
|
|
|
test <- "[0, 0, 0, 0]"
|
|
|
|
|
#TODO: turn character type into vector of numbers
|
|
|
|
|
str_split(test, ", ")
|
|
|
|
|
#TODO: turn character type into vector of numbers
|
|
|
|
|
str_split(gsub("[][]","", test), ", ")
|
|
|
|
|
readme_df %>% add_column(cnt_before_all = str_split(gsub("[][]","", before_all_count), ", "))
|
|
|
|
|
readme_df %>% mutate(cnt_before_all = str_split(gsub("[][]","", before_all_count), ", "))
|
|
|
|
|
readme_df %>% mutate("cnt_before_all" = str_split(gsub("[][]","", "before_all_count"), ", "))
|
|
|
|
|
head(readme_df$before_all_cnt)
|
|
|
|
|
head(readme_df$cnt_before_all)
|
|
|
|
|
readme_df %>% mutate(cnt_before_all = str_split(gsub("[][]","", "before_all_count"), ", "))
|
|
|
|
|
head(readme_df$cnt_before_all)
|
|
|
|
|
View(readme_df)
|
|
|
|
|
View(readme_df)
|
|
|
|
|
readme_df$cnt_before_all
|
|
|
|
|
readme_df %>% mutate(cnt_before_all = str_split(gsub("[][]","", "before_all_count"), ", "))
|
|
|
|
|
str_split(gsub("[][]","", readme_df$before_all_count), ", ")
|
|
|
|
|
#str_split(gsub("[][]","", readme_df$before_all_cnt), ", ")
|
|
|
|
|
readme_df %>% mutate(cnt_before_all = str_split(gsub("[][]","", "before_all_cnt"), ", "))
|
|
|
|
|
readme_df$cnt_before_all
|
|
|
|
|
#str_split(gsub("[][]","", readme_df$before_all_cnt), ", ")
|
|
|
|
|
readme_df %>% mutate("cnt_before_all" = str_split(gsub("[][]","", "before_all_cnt"), ", "))
|
|
|
|
|
readme_df$cnt_before_all
|
|
|
|
|
str_split(gsub("[][]","", readme_df$before_all_cnt), ", ")
|
|
|
|
|
readme_df$cnt_before_all <- str_split(gsub("[][]","", readme_df$before_all_cnt), ", ")
|
|
|
|
|
readme_df$cnt_before_all
|
|
|
|
|
readme_df$cnt_after_all <- str_split(gsub("[][]","", readme_df$after_all_cnt), ", ")
|
|
|
|
|
readme_df$cnt_after_all
|
|
|
|
|
readme_df$cnt_before_mrg <- str_split(gsub("[][]","", readme_df$before_mrg_cnt), ", ")
|
|
|
|
|
readme_df$cnt_before_mrg
|
|
|
|
|
readme_df$cnt_after_mrg <- str_split(gsub("[][]","", readme_df$after_mrg_cnt), ", ")
|
|
|
|
|
readme_df$cnt_after_mrg
|
|
|
|
|
#TODO: figure out if one needs to expand the data into a different dataframe, and if so how
|
|
|
|
|
readme_df <- subset(readme_df, select = -c("before_all_cnt", "before_mrg_cnt", "after_all_cnt", "after_mrg_cnt"))
|
|
|
|
|
drop <- c("before_all_cnt", "before_mrg_cnt", "after_all_cnt", "after_mrg_cnt")
|
|
|
|
|
readme_df = readme_df[,!(names(readme_df) %in% drop)]
|
|
|
|
|
View(readme_df)
|
|
|
|
|
library(tidyverse)
|
|
|
|
|
#set wd, read in data
|
|
|
|
|
try(setwd(dirname(rstudioapi::getActiveDocumentContext()$path)))
|
|
|
|
|
readme_df <- read_csv("../final_data/deb_readme_did.csv")
|
|
|
|
|
colnames(readme_df) <- c("upstream_vcs_link", "event_date", "event_hash", "before_all_cnt", "before_mrg_cnt", "after_all_cnt", "after_mrg_cnt", "before_auth_new", "after_commit_new", "after_auth_new", "before_commit_new")
|
|
|
|
|
col_order <- c("upstream_vcs_link", "event_date", "event_hash", "before_all_cnt", "after_all_cnt", "before_mrg_cnt", "after_mrg_cnt", "before_auth_new", "after_auth_new", "before_commit_new", "after_commit_new")
|
|
|
|
|
readme_df <- readme_df[,col_order]
|
|
|
|
|
glimpse(readme_df)
|
|
|
|
|
readme_df$cnt_before_all <- str_split(gsub("[][]","", readme_df$before_all_cnt), ", ")
|
|
|
|
|
readme_df$cnt_before_all <- as.numeric(readme_df$cnt_before_all)
|
|
|
|
|
View(readme_df)
|
|
|
|
|
readme_df$cnt_before_all
|
|
|
|
|
type(readme_df$cnt_before_all)
|
|
|
|
|
typeof(readme_df$cnt_before_all)
|
|
|
|
|
typeof(readme_df$cnt_before_all[0])
|
|
|
|
|
readme_df$cnt_before_all <- unlist(str_split(gsub("[][]","", readme_df$before_all_cnt), ", "))
|
|
|
|
|
readme_df$cnt_before_all <- str_split(gsub("[][]","", readme_df$before_all_cnt), ", ")
|
|
|
|
|
typeof(readme_df$cnt_before_all)
|
|
|
|
|
typeof(readme_df$cnt_before_all[[0]])
|
|
|
|
|
typeof(readme_df$cnt_before_all[0])
|
|
|
|
|
sapply(readme_df, class)
|
|
|
|
|
readme_df[,lapply(readme_df, unlist)]
|
|
|
|
|
readme_df[,lapply(readme_df$cnt, unlist)]
|
|
|
|
|
readme_df[,lapply(readme_df$cnt_before_all, unlist)]
|
|
|
|
|
typeof(readme_df$cnt_before_all[0])
|
|
|
|
|
View(readme_df)
|
|
|
|
|
View(readme_df)
|
|
|
|
|
readme_df$cnt_before_all <- as.numeric(str_split(gsub("[][]","", readme_df$before_all_cnt), ", "))
|
|
|
|
|
readme_df$cnt_before_all <- as.numeric(str_split(gsub("[][]","", readme_df$before_all_cnt), ", ")[[1]])
|
|
|
|
|
readme_df$cnt_before_all <- str_split(gsub("[][]","", readme_df$before_all_cnt), ", ")
|
|
|
|
|
typeof(readme_df$cnt_before_all[0])
|
|
|
|
|
typeof(readme_df$cnt_before_all[0][0])
|
|
|
|
|
readme_df$cnt_before_all[0]
|
|
|
|
|
unlist(readme_df$cnt_before_all[0])
|
|
|
|
|
readme_df$cnt_before_all[0]
|
|
|
|
|
readme_df$cnt_before_all
|
|
|
|
|
test <- readme_df$cnt_before_all
|
|
|
|
|
test
|
|
|
|
|
as.numeric(test)
|
|
|
|
|
test[0]
|
|
|
|
|
test[1]
|
|
|
|
|
as.numeric(test[1])
|
|
|
|
|
unlist(test[1])
|
|
|
|
|
as.numeric(unlist(test[1]))
|
|
|
|
|
test2 <- as.numeric(unlist(test))
|
|
|
|
|
test2
|
|
|
|
|
print(entry)
|
|
|
|
|
for (entry in test) {
|
|
|
|
|
print(entry)
|
|
|
|
|
}
|
|
|
|
|
print(as.numeric(unlist(entry)))
|
|
|
|
|
for (entry in test) {
|
|
|
|
|
print(as.numeric(unlist(entry)))
|
|
|
|
|
}
|
|
|
|
|
test_two <- append(test_two, as.numeric(unlist(entry)))
|
|
|
|
|
print(as.numeric(unlist(entry)))
|
|
|
|
|
for (entry in test) {
|
|
|
|
|
test_two <- append(test_two, as.numeric(unlist(entry)))
|
|
|
|
|
print(as.numeric(unlist(entry)))
|
|
|
|
|
}
|
|
|
|
|
test_two <- c()
|
|
|
|
|
for (entry in test) {
|
|
|
|
|
test_two <- append(test_two, as.numeric(unlist(entry)))
|
|
|
|
|
print(as.numeric(unlist(entry)))
|
|
|
|
|
}
|
|
|
|
|
readme_df$cnt_before_all <- as.numeric(readme_df$cnt_before_all)
|
|
|
|
|
test_two
|
|
|
|
|
readme_df$cnt_before_all[iterator] <- as.numeric(unlist(entry))
|
|
|
|
|
iterator <- 0
|
|
|
|
|
for (entry in test) {
|
|
|
|
|
readme_df$cnt_before_all[iterator] <- as.numeric(unlist(entry))
|
|
|
|
|
print(as.numeric(unlist(entry)))
|
|
|
|
|
iterator <- iterator + 1
|
|
|
|
|
}
|
|
|
|
|
View(readme_df)
|
|
|
|
|
library(tidyverse)
|
|
|
|
|
#set wd, read in data
|
|
|
|
|
try(setwd(dirname(rstudioapi::getActiveDocumentContext()$path)))
|
|
|
|
|
readme_df <- read_csv("../final_data/deb_readme_did.csv")
|
|
|
|
|
colnames(readme_df) <- c("upstream_vcs_link", "event_date", "event_hash", "before_all_cnt", "before_mrg_cnt", "after_all_cnt", "after_mrg_cnt", "before_auth_new", "after_commit_new", "after_auth_new", "before_commit_new")
|
|
|
|
|
col_order <- c("upstream_vcs_link", "event_date", "event_hash", "before_all_cnt", "after_all_cnt", "before_mrg_cnt", "after_mrg_cnt", "before_auth_new", "after_auth_new", "before_commit_new", "after_commit_new")
|
|
|
|
|
readme_df <- readme_df[,col_order]
|
|
|
|
|
glimpse(readme_df)
|
|
|
|
|
head(readme_df)
|
|
|
|
|
#this has to happen on the analysis side of things for a given row, it cannot happen on the storage side
|
|
|
|
|
#this is a conversation of whether or not the data should be saved in terms of
|
|
|
|
|
readme_df$cnt_before_all <- str_split(gsub("[][]","", readme_df$before_all_cnt), ", ")
|
|
|
|
|
# test <- readme_df$cnt_before_all
|
|
|
|
|
# as.numeric(unlist(test[1]))
|
|
|
|
|
# test_two <- c()
|
|
|
|
|
# iterator <- 0
|
|
|
|
|
# for (entry in test) {
|
|
|
|
|
# readme_df$cnt_before_all[iterator] <- as.numeric(unlist(entry))
|
|
|
|
|
# print(as.numeric(unlist(entry)))
|
|
|
|
|
# iterator <- iterator + 1
|
|
|
|
|
# }
|
|
|
|
|
# test_two
|
|
|
|
|
readme_df$cnt_after_all <- str_split(gsub("[][]","", readme_df$after_all_cnt), ", ")
|
|
|
|
|
readme_df$cnt_before_mrg <- str_split(gsub("[][]","", readme_df$before_mrg_cnt), ", ")
|
|
|
|
|
readme_df$cnt_after_mrg <- str_split(gsub("[][]","", readme_df$after_mrg_cnt), ", ")
|
|
|
|
|
drop <- c("before_all_cnt", "before_mrg_cnt", "after_all_cnt", "after_mrg_cnt")
|
|
|
|
|
readme_df = readme_df[,!(names(readme_df) %in% drop)]
|
|
|
|
|
#Yes, need to expand the dataframe, but again, for the sake of clarity, do not want to until analysis step
|
|
|
|
|
new_test <- head(readme_df, 1)
|
|
|
|
|
View(new_test)
|
|
|
|
|
write.csv(readme_df, "r_readme_did.csv", row.names=FALSE)
|
|
|
|
|
# as.numeric(unlist(test[1]))
|
|
|
|
|
# test_two <- c()
|
|
|
|
|
# iterator <- 0
|
|
|
|
|
# for (entry in test) {
|
|
|
|
|
# readme_df$cnt_before_all[iterator] <- as.numeric(unlist(entry))
|
|
|
|
|
# print(as.numeric(unlist(entry)))
|
|
|
|
|
# iterator <- iterator + 1
|
|
|
|
|
# }
|
|
|
|
|
# test_two
|
|
|
|
|
#Yes, need to expand the dataframe, but again, for the sake of clarity, do not want to until analysis step
|
|
|
|
|
new_test <- head(readme_df, 1)
|
|
|
|
|
View(new_test)
|
|
|
|
|
longer <- new_test |>
|
|
|
|
|
pivot_longer(cols = starts_with("cnt"),
|
|
|
|
|
names_to = "window",
|
|
|
|
|
values_to = "count"))
|
|
|
|
|
longer <- new_test |>
|
|
|
|
|
pivot_longer(cols = starts_with("cnt"),
|
|
|
|
|
names_to = "window",
|
|
|
|
|
values_to = "count")
|
|
|
|
|
longer
|
|
|
|
|
View(longer)
|
|
|
|
|
longer |> unnest(count)
|
|
|
|
|
new_longer <- longer |> unnest(count)
|
|
|
|
|
View(new_longer)
|
|
|
|
|
longer
|
|
|
|
|
View(new_longer)
|
|
|
|
|
longer <- new_test |>
|
|
|
|
|
pivot_longer(cols = starts_with("cnt"),
|
|
|
|
|
names_to = "window",
|
|
|
|
|
values_to = "count") |>
|
|
|
|
|
unnest(as.numeric(unlist(count)))
|
|
|
|
|
longer
|
|
|
|
|
longer <- new_test |>
|
|
|
|
|
pivot_longer(cols = starts_with("cnt"),
|
|
|
|
|
names_to = "window",
|
|
|
|
|
values_to = "count") |>
|
|
|
|
|
unnest(count))
|
|
|
|
|
longer <- new_test |>
|
|
|
|
|
pivot_longer(cols = starts_with("cnt"),
|
|
|
|
|
names_to = "window",
|
|
|
|
|
values_to = "count") |>
|
|
|
|
|
unnest(count)
|
|
|
|
|
longer
|
|
|
|
|
longer <- new_test |>
|
|
|
|
|
pivot_longer(cols = starts_with("cnt"),
|
|
|
|
|
names_to = "window",
|
|
|
|
|
values_to = "count") |>
|
|
|
|
|
unnest(count) |>
|
|
|
|
|
as.numeric(unlist(count))
|
|
|
|
|
longer <- new_test |>
|
|
|
|
|
pivot_longer(cols = starts_with("cnt"),
|
|
|
|
|
names_to = "window",
|
|
|
|
|
values_to = "count") |>
|
|
|
|
|
unnest(count) |>
|
|
|
|
|
unlist(count)
|
|
|
|
|
View(new_longer)
|
|
|
|
|
new_longer
|
|
|
|
|
longer <- new_test |>
|
|
|
|
|
pivot_longer(cols = starts_with("cnt"),
|
|
|
|
|
names_to = "window",
|
|
|
|
|
values_to = "count") |>
|
|
|
|
|
unnest(count) |>
|
|
|
|
|
unlist(count) |>
|
|
|
|
|
as.numeric(count)
|
|
|
|
|
View(new_longer)
|
|
|
|
|
new_longer
|
|
|
|
|
longer <- new_test |>
|
|
|
|
|
pivot_longer(cols = starts_with("cnt"),
|
|
|
|
|
names_to = "window",
|
|
|
|
|
values_to = "count") |>
|
|
|
|
|
unnest(count) |>
|
|
|
|
|
unlist(count) |>
|
|
|
|
|
as.numeric(count)
|
|
|
|
|
longer
|
|
|
|
|
longer <- new_test |>
|
|
|
|
|
pivot_longer(cols = starts_with("cnt"),
|
|
|
|
|
names_to = "window",
|
|
|
|
|
values_to = "count") |>
|
|
|
|
|
unnest(count) |>
|
|
|
|
|
unlist(count)
|
|
|
|
|
longer
|
|
|
|
|
longer <- new_test |>
|
|
|
|
|
pivot_longer(cols = starts_with("cnt"),
|
|
|
|
|
names_to = "window",
|
|
|
|
|
values_to = "count") |>
|
|
|
|
|
unnest(count)
|
|
|
|
|
longer
|
|
|
|
|
View(longer)
|
|
|
|
|
longer <- new_test |>
|
|
|
|
|
pivot_longer(cols = starts_with("cnt"),
|
|
|
|
|
names_to = "window",
|
|
|
|
|
values_to = "count") |>
|
|
|
|
|
unnest(count) |>
|
|
|
|
|
as.numeric(count)
|
|
|
|
|
longer
|
|
|
|
|
longer <- new_test |>
|
|
|
|
|
pivot_longer(cols = starts_with("cnt"),
|
|
|
|
|
names_to = "window",
|
|
|
|
|
values_to = "count") |>
|
|
|
|
|
unnest(count)
|
|
|
|
|
longer
|
|
|
|
|
library(tidyverse)
|
|
|
|
|
#set wd, read in data
|
|
|
|
|
try(setwd(dirname(rstudioapi::getActiveDocumentContext()$path)))
|
|
|
|
|
readme_df <- read_csv("../final_data/deb_readme_did.csv")
|
|
|
|
|
#preprocessing for readme_df
|
|
|
|
|
colnames(readme_df) <- c("upstream_vcs_link", "event_date", "event_hash", "before_all_ct", "before_mrg_ct", "after_all_ct", "after_mrg_ct", "before_auth_new", "after_commit_new", "after_auth_new", "before_commit_new")
|
|
|
|
|
col_order <- c("upstream_vcs_link", "event_date", "event_hash", "before_all_ct", "after_all_ct", "before_mrg_ct", "after_mrg_ct", "before_auth_new", "after_auth_new", "before_commit_new", "after_commit_new")
|
|
|
|
|
readme_df <- readme_df[,col_order]
|
|
|
|
|
readme_df$cnt_before_all <- str_split(gsub("[][]","", readme_df$before_all_cnt), ", ")
|
|
|
|
|
readme_df$cnt_after_all <- str_split(gsub("[][]","", readme_df$after_all_cnt), ", ")
|
|
|
|
|
readme_df$cnt_before_mrg <- str_split(gsub("[][]","", readme_df$before_mrg_cnt), ", ")
|
|
|
|
|
readme_df$cnt_after_mrg <- str_split(gsub("[][]","", readme_df$after_mrg_cnt), ", ")
|
|
|
|
|
drop <- c("before_all_ct", "before_mrg_ct", "after_all_ct", "after_mrg_ct")
|
|
|
|
|
library(tidyverse)
|
|
|
|
|
#set wd, read in data
|
|
|
|
|
try(setwd(dirname(rstudioapi::getActiveDocumentContext()$path)))
|
|
|
|
|
readme_df <- read_csv("../final_data/deb_readme_did.csv")
|
|
|
|
|
#preprocessing for readme_df
|
|
|
|
|
colnames(readme_df) <- c("upstream_vcs_link", "event_date", "event_hash", "before_all_ct", "before_mrg_ct", "after_all_ct", "after_mrg_ct", "before_auth_new", "after_commit_new", "after_auth_new", "before_commit_new")
|
|
|
|
|
col_order <- c("upstream_vcs_link", "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")
|
|
|
|
|
readme_df <- readme_df[,col_order]
|
|
|
|
|
readme_df$cnt_before_all <- str_split(gsub("[][]","", readme_df$before_all_cnt), ", ")
|
|
|
|
|
library(tidyverse)
|
|
|
|
|
#set wd, read in data
|
|
|
|
|
try(setwd(dirname(rstudioapi::getActiveDocumentContext()$path)))
|
|
|
|
|
readme_df <- read_csv("../final_data/deb_readme_did.csv")
|
|
|
|
|
contributing_df <- read_csv("../final_data/deb_contrib_did.csv")
|
|
|
|
|
#preprocessing for readme_df
|
|
|
|
|
colnames(readme_df) <- c("upstream_vcs_link", "event_date", "event_hash", "before_all_ct", "before_mrg_ct", "after_all_ct", "after_mrg_ct", "before_auth_new", "after_commit_new", "after_auth_new", "before_commit_new")
|
|
|
|
|
col_order <- c("upstream_vcs_link", "event_date", "event_hash", "before_all_ct", "after_all_ct", "before_mrg_ct", "after_mrg_ct", "before_auth_new", "after_auth_new", "before_commit_new", "after_commit_new")
|
|
|
|
|
readme_df <- readme_df[,col_order]
|
|
|
|
|
readme_df$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$after_mrg_ct), ", ")
|
|
|
|
|
drop <- c("before_all_ct", "before_mrg_ct", "after_all_ct", "after_mrg_ct")
|
|
|
|
|
readme_df = readme_df[,!(names(readme_df) %in% drop)]
|
|
|
|
|
# as.numeric(unlist(test[1]))
|
|
|
|
|
# test_two <- c()
|
|
|
|
|
# iterator <- 0
|
|
|
|
|
# for (entry in test) {
|
|
|
|
|
# readme_df$cnt_before_all[iterator] <- as.numeric(unlist(entry))
|
|
|
|
|
# print(as.numeric(unlist(entry)))
|
|
|
|
|
# iterator <- iterator + 1
|
|
|
|
|
# }
|
|
|
|
|
# test_two
|
|
|
|
|
#Yes, need to expand the dataframe, but again, for the sake of clarity, do not want to until analysis step
|
|
|
|
|
new_test <- head(readme_df, 1)
|
|
|
|
|
longer <- new_test |>
|
|
|
|
|
pivot_longer(cols = starts_with("ct"),
|
|
|
|
|
names_to = "window",
|
|
|
|
|
values_to = "count") |>
|
|
|
|
|
unnest(count)
|
|
|
|
|
longer
|
|
|
|
|
View(longer)
|
|
|
|
|
library(tidyverse)
|
|
|
|
|
#set wd, read in data
|
|
|
|
|
try(setwd(dirname(rstudioapi::getActiveDocumentContext()$path)))
|
|
|
|
|
readme_df <- read_csv("../final_data/deb_readme_did.csv")
|
|
|
|
|
contributing_df <- read_csv("../final_data/deb_contrib_did.csv")
|
|
|
|
|
#preprocessing for readme_df
|
|
|
|
|
colnames(readme_df) <- c("upstream_vcs_link", "event_date", "event_hash", "before_all_ct", "before_mrg_ct", "after_all_ct", "after_mrg_ct", "before_auth_new", "after_commit_new", "after_auth_new", "before_commit_new")
|
|
|
|
|
col_order <- c("upstream_vcs_link", "event_date", "event_hash", "before_all_ct", "after_all_ct", "before_mrg_ct", "after_mrg_ct", "before_auth_new", "after_auth_new", "before_commit_new", "after_commit_new")
|
|
|
|
|
readme_df <- readme_df[,col_order]
|
|
|
|
|
readme_df$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$after_mrg_ct), ", ")
|
|
|
|
|
drop <- c("before_all_ct", "before_mrg_ct", "after_all_ct", "after_mrg_ct")
|
|
|
|
|
readme_df = readme_df[,!(names(readme_df) %in% drop)]
|
|
|
|
|
# as.numeric(unlist(test[1]))
|
|
|
|
|
# test_two <- c()
|
|
|
|
|
# iterator <- 0
|
|
|
|
|
# for (entry in test) {
|
|
|
|
|
# readme_df$cnt_before_all[iterator] <- as.numeric(unlist(entry))
|
|
|
|
|
# print(as.numeric(unlist(entry)))
|
|
|
|
|
# iterator <- iterator + 1
|
|
|
|
|
# }
|
|
|
|
|
# test_two
|
|
|
|
|
#Yes, need to expand the dataframe, but again, for the sake of clarity, do not want to until analysis step
|
|
|
|
|
new_test <- head(readme_df, 1)
|
|
|
|
|
longer <- new_test |>
|
|
|
|
|
pivot_longer(cols = starts_with("ct"),
|
|
|
|
|
names_to = "window",
|
|
|
|
|
values_to = "count") |>
|
|
|
|
|
unnest(count)
|
|
|
|
|
longer
|
|
|
|
|
View(longer)
|
|
|
|
|
longer <- ddply(longer, "window", transform, t=seq(from=0, by=1, length.out=length(window)))
|
|
|
|
|
library(plyr)
|
|
|
|
|
longer <- ddply(longer, "window", transform, t=seq(from=0, by=1, length.out=length(window)))
|
|
|
|
|
View(longer)
|
|
|
|
|
library(plyr)
|
|
|
|
|
library(tidyverse)
|
|
|
|
|
#set wd, read in data
|
|
|
|
|
try(setwd(dirname(rstudioapi::getActiveDocumentContext()$path)))
|
|
|
|
|
readme_df <- read_csv("../final_data/deb_readme_did.csv")
|
|
|
|
|
contributing_df <- read_csv("../final_data/deb_contrib_did.csv")
|
|
|
|
|
#preprocessing for readme_df
|
|
|
|
|
colnames(readme_df) <- c("upstream_vcs_link", "event_date", "event_hash", "before_all_ct", "before_mrg_ct", "after_all_ct", "after_mrg_ct", "before_auth_new", "after_commit_new", "after_auth_new", "before_commit_new")
|
|
|
|
|
col_order <- c("upstream_vcs_link", "event_date", "event_hash", "before_all_ct", "after_all_ct", "before_mrg_ct", "after_mrg_ct", "before_auth_new", "after_auth_new", "before_commit_new", "after_commit_new")
|
|
|
|
|
readme_df <- readme_df[,col_order]
|
|
|
|
|
readme_df$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$after_mrg_ct), ", ")
|
|
|
|
|
drop <- c("before_all_ct", "before_mrg_ct", "after_all_ct", "after_mrg_ct")
|
|
|
|
|
readme_df = readme_df[,!(names(readme_df) %in% drop)]
|
|
|
|
|
# as.numeric(unlist(test[1]))
|
|
|
|
|
# test_two <- c()
|
|
|
|
|
# iterator <- 0
|
|
|
|
|
# for (entry in test) {
|
|
|
|
|
# readme_df$cnt_before_all[iterator] <- as.numeric(unlist(entry))
|
|
|
|
|
# print(as.numeric(unlist(entry)))
|
|
|
|
|
# iterator <- iterator + 1
|
|
|
|
|
# }
|
|
|
|
|
# test_two
|
|
|
|
|
#Yes, need to expand the dataframe, but again, for the sake of clarity, do not want to until analysis step
|
|
|
|
|
new_test <- head(readme_df, 1)
|
|
|
|
|
longer <- new_test |>
|
|
|
|
|
pivot_longer(cols = starts_with("ct"),
|
|
|
|
|
names_to = "window",
|
|
|
|
|
values_to = "count") |>
|
|
|
|
|
unnest(count)
|
|
|
|
|
longer <- ddply(longer, "window", transform, t=seq(from=0, by=1, length.out=length(window)))
|
|
|
|
|
View(longer)
|
|
|
|
|
longer <- ddply(longer, strsplit("window", split="_")[-1], transform, week=seq(from=0, by=1, length.out=length(window)))
|
|
|
|
|
longer <- ddply(longer, strsplit(window, split="_")[-1], transform, week=seq(from=0, by=1, length.out=length(window)))
|
|
|
|
|
longer <- new_test |>
|
|
|
|
|
pivot_longer(cols = starts_with("ct"),
|
|
|
|
|
names_to = "window",
|
|
|
|
|
values_to = "count") |>
|
|
|
|
|
unnest(count) |>
|
|
|
|
|
add_column(rel = gsub("^.*_", "", window))
|
|
|
|
|
longer <- new_test |>
|
|
|
|
|
pivot_longer(cols = starts_with("ct"),
|
|
|
|
|
names_to = "window",
|
|
|
|
|
values_to = "count") |>
|
|
|
|
|
unnest(count) |>
|
|
|
|
|
add_column(rel = gsub("^.*_", "", "window"))
|
|
|
|
|
View(longer)
|
|
|
|
|
longer$rel <- gsub("^.*_", "", longer$window)
|
|
|
|
|
View(longer)
|
|
|
|
|
# as.numeric(unlist(test[1]))
|
|
|
|
|
# test_two <- c()
|
|
|
|
|
# iterator <- 0
|
|
|
|
|
# for (entry in test) {
|
|
|
|
|
# readme_df$cnt_before_all[iterator] <- as.numeric(unlist(entry))
|
|
|
|
|
# print(as.numeric(unlist(entry)))
|
|
|
|
|
# iterator <- iterator + 1
|
|
|
|
|
# }
|
|
|
|
|
# test_two
|
|
|
|
|
#Yes, need to expand the dataframe, but again, for the sake of clarity, do not want to until analysis step
|
|
|
|
|
new_test <- head(readme_df, 1)
|
|
|
|
|
new_testr$observation_type <- gsub("^.*_", "", new_test$window)
|
|
|
|
|
# as.numeric(unlist(test[1]))
|
|
|
|
|
# test_two <- c()
|
|
|
|
|
# iterator <- 0
|
|
|
|
|
# for (entry in test) {
|
|
|
|
|
# readme_df$cnt_before_all[iterator] <- as.numeric(unlist(entry))
|
|
|
|
|
# print(as.numeric(unlist(entry)))
|
|
|
|
|
# iterator <- iterator + 1
|
|
|
|
|
# }
|
|
|
|
|
# test_two
|
|
|
|
|
#Yes, need to expand the dataframe, but again, for the sake of clarity, do not want to until analysis step
|
|
|
|
|
new_test <- head(readme_df, 1)
|
|
|
|
|
longer <- new_test |>
|
|
|
|
|
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)))
|
|
|
|
|
View(longer)
|
|
|
|
|
head(longer)
|
|
|
|
|
sapply(longer, class)
|
