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

further specification of model and formula

Browse Source
This commit is contained in:
mjgaughan 2024-04-23 13:59:06 -05:00
parent 634f60b6a8
commit 67946e6e10
1 changed files with 33 additions and 13 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

46
R/readmeRDDAnalysis.R
View File

@ -34,10 +34,11 @@ 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
windowed_data <- expanded_data |> windowed_data <- expanded_data |>
filter(week >= (26 - window_num) & week <= (26 + window_num)) |> filter(week >= (27 - window_num) & week <= (27 + window_num)) |>
mutate(D = ifelse(week > 26, 1, 0)) mutate(D = ifelse(week > 27, 1, 0))
#scale the age numbers #scale the age numbers
windowed_data$scaled_project_age <- scale(windowed_data$age_of_project) windowed_data$scaled_project_age <- scale(windowed_data$age_of_project)
windowed_data$week_offset <- windowed_data$week - 27
#separate out the cleaning d #separate out the cleaning d
all_actions_data <- windowed_data[which(windowed_data$observation_type == "all"),] all_actions_data <- windowed_data[which(windowed_data$observation_type == "all"),]
mrg_actions_data <- windowed_data[which(windowed_data$observation_type == "mrg"),] mrg_actions_data <- windowed_data[which(windowed_data$observation_type == "mrg"),]
@ -54,18 +55,37 @@ qqplot(all_actions_data$count, y)
# lmer: https://www.youtube.com/watch?v=LzAwEKrn2Mc # lmer: https://www.youtube.com/watch?v=LzAwEKrn2Mc
library(lme4) library(lme4)
# https://www.bristol.ac.uk/cmm/learning/videos/random-intercepts.html#exvar # https://www.bristol.ac.uk/cmm/learning/videos/random-intercepts.html#exvar
# (D |upstream_vcs_link) or (week | upstream_vcs_link) #making some random data
poisson_all_model <- glmer(count ~ D + I(week - 26) + D:I(week - 26) + scaled_project_age + (week || upstream_vcs_link), data=all_actions_data, family = poisson(link = "log")) sampled_data <- readme_df[sample(nrow(readme_df), 220), ]
summary(poisson_all_model) expanded_sample_data <- expand_timeseries(sampled_data[1,])
poisson_residuals <- residuals(poisson_all_model) for (i in 2:nrow(sampled_data)){
qqnorm(poisson_residuals) expanded_sample_data <- rbind(expanded_sample_data, expand_timeseries(sampled_data[i,]))
}
windowed_sample_data <- expanded_sample_data |>
filter(week >= (27 - window_num) & week <= (27 + window_num)) |>
mutate(D = ifelse(week > 27, 1, 0))
windowed_sample_data$scaled_project_age <- scale(windowed_sample_data$age_of_project)
windowed_sample_data$week_offset <- windowed_sample_data$week - 27
all_actions_sample_data <- windowed_sample_data[which(windowed_sample_data$observation_type == "all"),]
#test model
test_model <- lmer(count ~ D * I(week_offset) + scaled_project_age + (D * I(week_offset)|upstream_vcs_link), data=all_actions_sample_data, REML=FALSE)
summary(test_model)
#plot results
p <- ggplot(all_actions_sample_data, aes(x=week_offset, y=count, color=upstream_vcs_link), show.legend = FALSE) +
geom_point(size=3, show.legend = FALSE) +
geom_line(aes(y=predict(test_model)), show.legend = FALSE) +
theme_bw()
p
##end of the model testing and plotting section
all_model <- lmer(count ~ D * I(week_offset)+ scaled_project_age + (D * I(week_offset)| upstream_vcs_link), data=all_actions_data, REML=FALSE)
summary(all_model)
all_residuals <- residuals(all_model)
qqnorm(all_residuals)
# for visualization, may have to run model for each project and then identify top 5 projects for RDD graphs # for visualization, may have to run model for each project and then identify top 5 projects for RDD graphs
# mrg_model <- lmer(count ~ D * I(week_offset)+ scaled_project_age + (D * I(week_offset)| upstream_vcs_link), data=mrg_actions_data, REML=FALSE)
# summary(mrg_model)
poisson_mrg_model <- glmer(count ~ D + I(week - 26) + D:I(week - 26) + scaled_project_age + (week |upstream_vcs_link), data=mrg_actions_data, family = poisson(link = "log")) mrg_residuals <- residuals(mrg_model)
summary(poisson_mrg_model) qqnorm(mrg_residuals)
poisson_mrg_residuals <- residuals(poisson_mrg_model)
qqnorm(poisson_mrg_residuals)
# Performance: # Performance:
library(merTools) library(merTools)