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

update with eventgap model, which does not convernge

Browse Source
This commit is contained in:
Matthew Gaughan 2024-06-25 10:36:29 -05:00
parent 76da2cbe73
commit d68544efc8
5 changed files with 2285 additions and 6 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2280
R/062424_readme_grouped_1.csv Normal file
View File

File diff suppressed because it is too large Load Diff

BIN
R/0624_eventgap_rm_rdd.rda Normal file
View File

Binary file not shown.

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

Binary file not shown.

7
R/readmeRDDAnalysis.R
View File

@ -38,7 +38,7 @@ windowed_data <- expanded_data |>
mutate(D = ifelse(week > 27, 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_in_days) windowed_data$scaled_project_age <- scale(windowed_data$age_in_days)
windowed_data$scaled_event_gap <- scale(event_gap) windowed_data$scaled_event_gap <- scale(windowed_data$event_gap)
windowed_data$week_offset <- windowed_data$week - 27 windowed_data$week_offset <- windowed_data$week - 27
#break out the different types of commit actions that are studied #break out the different types of commit actions that are studied
all_actions_data <- windowed_data[which(windowed_data$observation_type == "all"),] all_actions_data <- windowed_data[which(windowed_data$observation_type == "all"),]
@ -62,11 +62,10 @@ var(all_actions_data$count) # 268.4449
mean (all_actions_data$count) # 3.757298 mean (all_actions_data$count) # 3.757298
median(all_actions_data$count) # 0 median(all_actions_data$count) # 0
print("fitting model") print("fitting model")
all_log1p_gmodel <- glmer.nb(log1p_count ~ D * week_offset+ scaled_project_age + scaled_event_gap + (D * week_offset | upstream_vcs_link), data=all_actions_data, nAGQ=1, control=glmerControl(optimizer="bobyqa", #all_log1p_gmodel <- glmer.nb(log1p_count ~ D * week_offset+ scaled_project_age + scaled_event_gap + (D * week_offset | upstream_vcs_link), data=all_actions_data, nAGQ=1, control=glmerControl(optimizer="bobyqa",
optCtrl=list(maxfun=1e5))) optCtrl=list(maxfun=1e5)))
#all_log1p_gmodel <- readRDS("0624_log1p_nagq_gmodel_backup.rda") all_log1p_gmodel <- readRDS("0624_log1p_nagq_gmodel_backup.rda")
summary(all_log1p_gmodel) summary(all_log1p_gmodel)
saveRDS(all_log1p_gmodel, "0624_eventgap_rm_rdd.rda")
print("model fit") print("model fit")
#I grouped the ranef D effects on 0624 #I grouped the ranef D effects on 0624
all_residuals <- residuals(all_log1p_gmodel) all_residuals <- residuals(all_log1p_gmodel)

4
text_analysis/partitioning_files.py
View File

@ -7,7 +7,7 @@ from pathlib import Path
working_dir = "/data/users/mgaughan/kkex/time_specific_files/readme2/" working_dir = "/data/users/mgaughan/kkex/time_specific_files/readme2/"
dest_dir = "/data/users/mgaughan/kkex/time_specific_files/partitioned_readme/p" dest_dir = "/data/users/mgaughan/kkex/time_specific_files/partitioned_readme1/p"
def move_file(vcs_link, group): def move_file(vcs_link, group):
if "github" in vcs_link or "gitlab" in vcs_link: if "github" in vcs_link or "gitlab" in vcs_link:
@ -91,5 +91,5 @@ def for_all_files(csv_path):
print(len(already_seen)) print(len(already_seen))
if __name__ == "__main__": if __name__ == "__main__":
for_all_files("R/051224_readme_grouped.csv") for_all_files("final_data/contrib_rdd_groupings.csv")
#for_all_files("R/051224_contrib_grouped.csv") #for_all_files("R/051224_contrib_grouped.csv")