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

updating new pop models with initial commit data

Browse Source
This commit is contained in:
mjgaughan 2024-06-24 15:36:36 -04:00
parent 17f6e2008e
commit 8a1bfc81d0
3 changed files with 14 additions and 33 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

BIN
R/final_models/0624_pop_rm_collab_better.rda Normal file
View File

Binary file not shown.

BIN
R/final_models/0624_pop_rm_contrib.rda Normal file
View File

Binary file not shown.

47
R/popRDDAnalyssis.R
View File

@ -9,20 +9,6 @@ readme_df <- read_csv("../final_data/deb_readme_pop_change.csv")
contrib_df <- merge(full_df, contrib_df, by="upstream_vcs_link") contrib_df <- merge(full_df, contrib_df, by="upstream_vcs_link")
readme_df <- merge(full_df, readme_df, by="upstream_vcs_link") readme_df <- merge(full_df, readme_df, by="upstream_vcs_link")
# age is calculated against December 11, 2023 # 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")))
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 #some expansion needs to happens for each project
expand_timeseries <- function(project_row) { expand_timeseries <- function(project_row) {
longer <- project_row |> longer <- project_row |>
@ -46,6 +32,9 @@ expanded_readme_data$log1pcount <- log1p(expanded_readme_data$count)
expanded_contrib_data$log1pcount <- log1p(expanded_contrib_data$count) expanded_contrib_data$log1pcount <- log1p(expanded_contrib_data$count)
expanded_readme_data$logcount <- log(expanded_readme_data$count) expanded_readme_data$logcount <- log(expanded_readme_data$count)
expanded_contrib_data$logcount <- log(expanded_contrib_data$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 #breaking out the types of population counts
collab_pop_readme <- expanded_readme_data[which(expanded_readme_data$is_collab == 1),] collab_pop_readme <- expanded_readme_data[which(expanded_readme_data$is_collab == 1),]
contrib_pop_readme <- expanded_readme_data[which(expanded_readme_data$is_collab == 0),] contrib_pop_readme <- expanded_readme_data[which(expanded_readme_data$is_collab == 0),]
@ -55,30 +44,22 @@ contrib_pop_contrib <- expanded_contrib_data[which(expanded_contrib_data$is_coll
library(lme4) library(lme4)
library(optimx) library(optimx)
library(MASS) library(MASS)
simple_collab_readme_model <- glm.nb(count ~ as.factor(after_doc), data=collab_pop_readme) #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) summary(simple_collab_readme_model)
qqnorm(residuals(simple_collab_readme_model)) qqnorm(residuals(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)
qqnorm(residuals(simple_contrib_readme_model))
# I don't think MLM is the right one # I don't think MLM is the right one
collab_readme_model <- glmer.nb(log1pcount ~ as.factor(after_doc) + (after_doc| upstream_vcs_link), data=collab_pop_readme) collab_readme_model <- glmer.nb(log1pcount ~ as.factor(after_doc) + scaled_age + (after_doc| upstream_vcs_link), data=collab_pop_readme)
collab_readme_model_plus <- glmer.nb(log1pcount ~ as.factor(after_doc) + event_date_days + (after_doc| upstream_vcs_link), data=collab_pop_readme)
collab_readme_model <- readRDS("final_models/0623_pop_rm_collab.rda")
summary(collab_readme_model) summary(collab_readme_model)
saveRDS(collab_readme_model, "final_models/0623_pop_rm_collab_better.rda") saveRDS(collab_readme_model, "final_models/0624_pop_rm_collab_better.rda")
contrib_readme_model <- glmer.nb(log1pcount ~ after_doc + (after_doc| upstream_vcs_link), data=contrib_pop_readme) contrib_readme_model <- glmer.nb(log1pcount ~ as.factor(after_doc) + scaled_age + (after_doc| upstream_vcs_link), data=contrib_pop_readme)
contrib_readme_model_plus <- glmer.nb(log1pcount ~ after_doc + event_date_days+ (after_doc| upstream_vcs_link), data=contrib_pop_readme)
summary(contrib_readme_model) summary(contrib_readme_model)
saveRDS(contrib_readme_model, "final_models/0623_pop_rm_contrib.rda") saveRDS(contrib_readme_model, "final_models/0624_pop_rm_contrib.rda")
contrib_readme_model <- readRDS("final_models/0623_pop_rm_contrib.rda") #contrib_readme_model <- readRDS("final_models/0623_pop_rm_contrib.rda")
conrm_residuals <- residuals(contrib_readme_model) #contributing models are not statistically significant``
qqnorm(conrm_residuals)
collab_contrib_model <- glmer.nb(log1pcount ~ after_doc + (after_doc| upstream_vcs_link), data=collab_pop_contrib)
summary(collab_contrib_model)
saveRDS(collab_contrib_model, "final_models/0623_pop_contrib_collab.rda")
contrib_readme_model <- readRDS("final_models/0623_pop_contrib_collab.rda")
contrib_contrib_model <- glmer.nb(log1pcount ~ after_doc + (after_doc| upstream_vcs_link), data=contrib_pop_contrib)
summary(contrib_contrib_model)
saveRDS(contrib_contrib_model, "final_models/0623_pop_contrib_contrib.rda")
library(texreg) library(texreg)
texreg(list(collab_readme_model, contrib_readme_model), stars=NULL, digits=2, texreg(list(collab_readme_model, contrib_readme_model), stars=NULL, digits=2,