24_deb_pkg_gov/R/.Rhistory
2024-04-08 21:20:50 -04:00

513 lines
20 KiB
R

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)
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$observation_type <- gsub("^.*_", "", longer$window)
longer <- ddply(longer, "observation_type", transform, week=seq(from=0, by=1, length.out=length(observation_type)))
View(longer)
#testing out analysis below
longer[which(longer$observation_type == all)] |>
ggplot(aes(x = week, y = count)) +
geom_point() +
geom_vline(xintercept = 26)
#testing out analysis below
longer[which(longer$observation_type == "all")] |>
ggplot(aes(x = week, y = count)) +
geom_point() +
geom_vline(xintercept = 26)
#testing out analysis below
longer[which(longer$observation_type == "all"),] |>
ggplot(aes(x = week, y = count)) +
geom_point() +
geom_vline(xintercept = 26)
View(readme_df)
# as.numeric(unlist(test[1]))
# test_two <- c()
# iterator <- 0
# for (entry in test) {
# readme_df$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 <- readme_df[5,]
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)))
#testing out analysis below
longer[which(longer$observation_type == "all"),] |>
ggplot(aes(x = week, y = count)) +
geom_point() +
geom_vline(xintercept = 26)
View(readme_df)
# as.numeric(unlist(test[1]))
# test_two <- c()
# iterator <- 0
# for (entry in test) {
# readme_df$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 <- readme_df[76,]
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)))
#testing out analysis below
longer[which(longer$observation_type == "all"),] |>
ggplot(aes(x = week, y = count)) +
geom_point() +
geom_vline(xintercept = 26)
# as.numeric(unlist(test[1]))
# test_two <- c()
# iterator <- 0
# for (entry in test) {
# readme_df$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 <- readme_df[77,]
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)))
#testing out analysis below
longer[which(longer$observation_type == "all"),] |>
ggplot(aes(x = week, y = count)) +
geom_point() +
geom_vline(xintercept = 26)
# as.numeric(unlist(test[1]))
# test_two <- c()
# iterator <- 0
# for (entry in test) {
# readme_df$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 <- readme_df[143,]
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)))
#testing out analysis below
longer[which(longer$observation_type == "all"),] |>
ggplot(aes(x = week, y = count)) +
geom_point() +
geom_vline(xintercept = 26)
# as.numeric(unlist(test[1]))
# test_two <- c()
# iterator <- 0
# for (entry in test) {
# readme_df$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 <- readme_df[185,]
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)))
#testing out analysis below
longer[which(longer$observation_type == "all"),] |>
ggplot(aes(x = week, y = count)) +
geom_point() +
geom_vline(xintercept = 26)
# as.numeric(unlist(test[1]))
# test_two <- c()
# iterator <- 0
# for (entry in test) {
# readme_df$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 <- readme_df[231,]
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)))
#testing out analysis below
longer[which(longer$observation_type == "all"),] |>
ggplot(aes(x = week, y = count)) +
geom_point() +
geom_vline(xintercept = 26)
longer[which(longer$observation_type == "all"),] |>
mutate(D = ifelse(week >= 26, 1, 0)) |>
lm(count ~ D + I(week - 26)) |>
summary()
longer[which(longer$observation_type == "all"),] |>
mutate(D = ifelse(week >= 26, 1, 0)) |>
lm(count ~ D * I(week - 26)) |>
summary()
longer[which(longer$observation_type == "all"),] |>
mutate(D = ifelse(week >= 26, 1, 0)) |>
lm(formula = count ~ D * I(week - 26)) |>
summary()
longer[which(longer$observation_type == "all"),] |>
select(count, week) |>
mutate(D = ifelse(week >= 26, 1, 0)) |>
ggplot(aes(x = week, y = count, color = D)) +
geom_point() +
geom_smooth(method = "lm")
longer[which(longer$observation_type == "all"),] |>
select(count, week) |>
mutate(D = as.factor(ifelse(week >= 26, 1, 0))) |>
ggplot(aes(x = week, y = count, color = D)) +
geom_point() +
geom_smooth(method = "lm")
longer[which(longer$observation_type == "all"),] |>
select(count, week) |>
mutate(D = as.factor(ifelse(week >= 26, 1, 0))) |>
ggplot(aes(x = week, y = count, color = D)) +
geom_point() +
geom_smooth()
longer[which(longer$observation_type == "all"),] |>
select(count, week) |>
mutate(D = as.factor(ifelse(week >= 26, 1, 0))) |>
ggplot(aes(x = week, y = count, color = D)) +
geom_point() +
geom_smooth()
longer[which(longer$observation_type == "all"),] |>
select(count, week) |>
mutate(D = as.factor(ifelse(week >= 26, 1, 0))) |>
ggplot(aes(x = week, y = count, color = D)) +
geom_point() +
geom_smooth(aes(x = week, y = count, color = D))
longer[which(longer$observation_type == "all"),] |>
select(count, week) |>
mutate(D = as.factor(ifelse(week >= 26, 1, 0))) |>
ggplot(aes(x = week, y = count, color = D)) +
geom_point() +
geom_smooth()
sapply(longer, class)
longer$count <- as.numeric(longer$count)
sapply(longer, class)
#testing out analysis below
longer[which(longer$observation_type == "all"),] |>
ggplot(aes(x = week, y = count)) +
geom_point() +
geom_vline(xintercept = 26)
longer[which(longer$observation_type == "all"),] |>
mutate(D = ifelse(week >= 26, 1, 0)) |>
lm(formula = count ~ D * I(week - 26)) |>
summary()
longer[which(longer$observation_type == "all"),] |>
select(count, week) |>
mutate(D = as.factor(ifelse(week >= 26, 1, 0))) |>
ggplot(aes(x = week, y = count, color = D)) +
geom_point() +
geom_smooth()
longer[which(longer$observation_type == "all"),] |>
select(count, week) |>
mutate(D = as.factor(ifelse(week >= 26, 1, 0))) |>
ggplot(aes(x = week, y = count, color = D)) +
geom_point() +
geom_smooth(se = False)
longer[which(longer$observation_type == "all"),] |>
select(count, week) |>
mutate(D = as.factor(ifelse(week >= 26, 1, 0))) |>
ggplot(aes(x = week, y = count, color = D)) +
geom_point() +
geom_smooth(se = FALSE)