mgaughan/24_deb_pkg_gov
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

further updates to mlm

Browse Source
This commit is contained in:
mjgaughan 2024-04-20 22:13:13 -05:00
parent c6c622c095
commit 91ceaf1759
2 changed files with 92 additions and 93 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

170
R/.Rhistory
View File

@ -1,88 +1,3 @@
link <- readme_df[i,]$upstream_vcs_link
age <- full_df$age_of_project[full_df$upstream_vcs_link == link]
project <- full_df$project_name[full_df$upstream_vcs_link == link]
ages <- c(ages, age)
if (length(project) != 1){
project
break
} else {
projects <- c(projects, project)
}
}
#set wd, read in data
try(setwd(dirname(rstudioapi::getActiveDocumentContext()$path)))
readme_df <- read_csv("../final_data/deb_readme_did.csv")
contributing_df <- read_csv("../final_data/deb_contrib_did.csv")
full_df <- read_csv("../final_data/deb_full_data.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")
ages <- c()
projects <- c()
for (i in 1:nrow(readme_df)){
link <- readme_df[i,]$upstream_vcs_link
age <- full_df$age_of_project[full_df$upstream_vcs_link == link]
project <- full_df$project_name[full_df$upstream_vcs_link == link]
ages <- c(ages, age)
if (length(project) != 1){
project
break
} else {
projects <- c(projects, project)
}
}
#set wd, read in data
try(setwd(dirname(rstudioapi::getActiveDocumentContext()$path)))
readme_df <- read_csv("../final_data/deb_readme_did.csv")
contributing_df <- read_csv("../final_data/deb_contrib_did.csv")
full_df <- read_csv("../final_data/deb_full_data.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")
ages <- c()
projects <- c()
for (i in 1:nrow(readme_df)){
link <- readme_df[i,]$upstream_vcs_link
age <- full_df$age_of_project[full_df$upstream_vcs_link == link]
project <- full_df$project_name[full_df$upstream_vcs_link == link]
ages <- c(ages, age)
if (length(project) != 1){
project
break
} else {
projects <- c(projects, project)
}
}
#set wd, read in data
try(setwd(dirname(rstudioapi::getActiveDocumentContext()$path)))
readme_df <- read_csv("../final_data/deb_readme_did.csv")
contributing_df <- read_csv("../final_data/deb_contrib_did.csv")
full_df <- read_csv("../final_data/deb_full_data.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")
ages <- c()
projects <- c()
for (i in 1:nrow(readme_df)){
link <- readme_df[i,]$upstream_vcs_link
age <- full_df$age_of_project[full_df$upstream_vcs_link == link]
project <- full_df$project_name[full_df$upstream_vcs_link == link]
ages <- c(ages, age)
if (length(project) != 1){
project
break
} else {
projects <- c(projects, project)
}
}
readme_df <- read_csv("../final_data/deb_readme_did.csv")
contributing_df <- read_csv("../final_data/deb_contrib_did.csv")
full_df <- read_csv("../final_data/deb_full_data.csv")
#preprocessing for readme_df
colnames(readme_df) <- c("upstream_vcs_link", "event_date", "event_hash", "before_all_ct", "before_mrg_ct", "after_all_ct", "after_mrg_ct", "before_auth_new", "after_commit_new", "after_auth_new", "before_commit_new")
col_order <- c("upstream_vcs_link", "event_date", "event_hash", "before_all_ct", "after_all_ct", "before_mrg_ct", "after_mrg_ct", "before_auth_new", "after_auth_new", "before_commit_new", "after_commit_new")
ages <- c()
projects <- c()
for (i in 1:nrow(readme_df)){ for (i in 1:nrow(readme_df)){
link <- readme_df[i,]$upstream_vcs_link link <- readme_df[i,]$upstream_vcs_link
age <- full_df$age_of_project[full_df$upstream_vcs_link == link] age <- full_df$age_of_project[full_df$upstream_vcs_link == link]
@ -510,3 +425,88 @@ poisson_all_model <- glmer(count ~ D + I(week - 26) + D:I(week - 26) + age_of_pr
summary(poisson_all_model) summary(poisson_all_model)
poisson_residuals <- residuals(poisson_all_model) poisson_residuals <- residuals(poisson_all_model)
qqnorm(poisson_residuals) qqnorm(poisson_residuals)
# this is the file with the lmer multi-level rddAnalysis
library(tidyverse)
library(plyr)
# 0 loading the readme data in
try(setwd(dirname(rstudioapi::getActiveDocumentContext()$path)))
readme_df <- read_csv("../final_data/deb_readme_did.csv")
# 1 preprocessing
#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", "age_of_project", "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)]
# 2 some expansion needs to happens for each project
expand_timeseries <- function(project_row) {
longer <- project_row |>
pivot_longer(cols = starts_with("ct"),
names_to = "window",
values_to = "count") |>
unnest(count)
longer$observation_type <- gsub("^.*_", "", longer$window)
longer <- ddply(longer, "observation_type", transform, week=seq(from=0, by=1, length.out=length(observation_type)))
longer$count <- as.numeric(longer$count)
#longer <- longer[which(longer$observation_type == "all"),]
return(longer)
}
expanded_data <- expand_timeseries(readme_df[1,])
for (i in 2:nrow(readme_df)){
expanded_data <- rbind(expanded_data, expand_timeseries(readme_df[i,]))
}
#filter out the windows of time that we're looking at
window_num <- 8
expanded_data <- expanded_data |>
filter(week >= (26 - window_num) & week <= (26 + window_num)) |>
mutate(D = ifelse(week > 26, 1, 0))
#separate out the cleaning d
all_actions_data <- expanded_data[which(expanded_data$observation_type == "all"),]
mrg_actions_data <- expanded_data[which(expanded_data$observation_type == "mrg"),]
#find some EDA to identify which types of models might be the best for this
mean(all_actions_data$count)
median(all_actions_data$count)
#if I'm reading the residuals right, the poisson is better?
poisson_all_model <- glmer(count ~ D + I(week - 26) + D:I(week - 26) + age_of_project + (1 + D |upstream_vcs_link), data=all_actions_data, family = poisson(link = "log"), nAGQ = 100)
summary(poisson_all_model)
# 3 rdd in lmer analysis
# rdd: https://rpubs.com/phle/r_tutorial_regression_discontinuity_design
# lmer: https://www.youtube.com/watch?v=LzAwEKrn2Mc
library(lme4)
#if I'm reading the residuals right, the poisson is better?
poisson_all_model <- glmer(count ~ D + I(week - 26) + D:I(week - 26) + age_of_project + (1 + D |upstream_vcs_link), data=all_actions_data, family = poisson(link = "log"), nAGQ = 100)
#if I'm reading the residuals right, the poisson is better?
poisson_all_model <- glmer(count ~ D + I(week - 26) + D:I(week - 26) + age_of_project + (1 + D |upstream_vcs_link), data=all_actions_data, family = poisson(link = "log"), nAGQ = 100)
#if I'm reading the residuals right, the poisson is better?
poisson_all_model <- glmer(count ~ D + I(week - 26) + D:I(week - 26) + age_of_project + (1 + D |upstream_vcs_link), data=all_actions_data, family = poisson(link = "log"))
summary(poisson_all_model)
poisson_residuals <- residuals(poisson_all_model)
qqnorm(poisson_residuals)
#if I'm reading the residuals right, the poisson is better?
poisson_all_model <- glmer(count ~ D + I(week - 26) + D:I(week - 26) + scale(age_of_project) + (1 + D |upstream_vcs_link), data=all_actions_data, family = poisson(link = "log"))
summary(poisson_all_model)
poisson_residuals <- residuals(poisson_all_model)
qqnorm(poisson_residuals)
qqnorm(poisson_residuals)
qqnorm(poisson_residuals)
#scale the age numbers
expanded_data$scaled_project_age <- scale(expanded_data$age_of_project)
#separate out the cleaning d
all_actions_data <- expanded_data[which(expanded_data$observation_type == "all"),]
mrg_actions_data <- expanded_data[which(expanded_data$observation_type == "mrg"),]
#find some EDA to identify which types of models might be the best for this
mean(all_actions_data$count)
median(all_actions_data$count)
table(all_actions_data$count)
var(all_actions_data$count)
qqnorm(all_actions_data$count)
y <- qunif(ppoints(length(all_actions_data$count)))
qqplot(all_actions_data$count, y)
#if I'm reading the residuals right, the poisson is better?
poisson_all_model <- glmer(count ~ D + I(week - 26) + D:I(week - 26) + scaled_project_age + (1 + D |upstream_vcs_link), data=all_actions_data, family = poisson(link = "log"))
summary(poisson_all_model)
poisson_residuals <- residuals(poisson_all_model)
qqnorm(poisson_residuals)

15
R/didAnalysis.R
View File

@ -33,14 +33,14 @@ for (i in 2:nrow(readme_df)){
} }
#filter out the windows of time that we're looking at #filter out the windows of time that we're looking at
window_num <- 8 window_num <- 8
expanded_data <- expanded_data |> windowed_data <- expanded_data |>
filter(week >= (26 - window_num) & week <= (26 + window_num)) |> filter(week >= (26 - window_num) & week <= (26 + window_num)) |>
mutate(D = ifelse(week > 26, 1, 0)) mutate(D = ifelse(week > 26, 1, 0))
#scale the age numbers #scale the age numbers
expanded_data$scaled_project_age <- scale(expanded_data$age_of_project) windowed_data$scaled_project_age <- scale(windowed_data$age_of_project)
#separate out the cleaning d #separate out the cleaning d
all_actions_data <- expanded_data[which(expanded_data$observation_type == "all"),] all_actions_data <- windowed_data[which(windowed_data$observation_type == "all"),]
mrg_actions_data <- expanded_data[which(expanded_data$observation_type == "mrg"),] mrg_actions_data <- windowed_data[which(windowed_data$observation_type == "mrg"),]
#find some EDA to identify which types of models might be the best for this #find some EDA to identify which types of models might be the best for this
mean(all_actions_data$count) mean(all_actions_data$count)
median(all_actions_data$count) median(all_actions_data$count)
@ -53,14 +53,13 @@ qqplot(all_actions_data$count, y)
# rdd: https://rpubs.com/phle/r_tutorial_regression_discontinuity_design # rdd: https://rpubs.com/phle/r_tutorial_regression_discontinuity_design
# lmer: https://www.youtube.com/watch?v=LzAwEKrn2Mc # lmer: https://www.youtube.com/watch?v=LzAwEKrn2Mc
library(lme4) library(lme4)
flat_all_model <- lm(count ~ D + I(week - 26) + D:I(week - 26) + scaled_project_age, REML=FALSE, data=all_actions_data) lmer_all_model <- lmer(count ~ D + I(week - 26) + D:I(week - 26) + scaled_project_age + (D ||upstream_vcs_link), REML=FALSE, data=all_actions_data)
summary(flat_all_model)
lmer_all_model <- lmer(count ~ D + I(week - 26) + D:I(week - 26) + scaled_project_age + (1 + D |upstream_vcs_link), REML=FALSE, data=all_actions_data)
summary(lmer_all_model) summary(lmer_all_model)
lmer_residuals <- residuals(lmer_all_model) lmer_residuals <- residuals(lmer_all_model)
qqnorm(lmer_residuals) qqnorm(lmer_residuals)
#if I'm reading the residuals right, the poisson is better? #if I'm reading the residuals right, the poisson is better?
poisson_all_model <- glmer(count ~ D + I(week - 26) + D:I(week - 26) + scaled_project_age + (1 + D |upstream_vcs_link), data=all_actions_data, family = poisson(link = "log")) # there's a conversation to be had between whether (D |upstream_vcs_link) or (D || upstream_vcs_link)
poisson_all_model <- glmer(count ~ D + I(week - 26) + D:I(week - 26) + scaled_project_age + (D |upstream_vcs_link), data=all_actions_data, family = poisson(link = "log"))
summary(poisson_all_model) summary(poisson_all_model)
poisson_residuals <- residuals(poisson_all_model) poisson_residuals <- residuals(poisson_all_model)
qqnorm(poisson_residuals) qqnorm(poisson_residuals)