From 918066e98b91c5fbe95d8bf23ddf7b3a87a9d0ef Mon Sep 17 00:00:00 2001 From: mgaughan Date: Sat, 2 Nov 2024 17:35:06 -0500 Subject: [PATCH] moving to kibo --- 110124_supp_analysis/contrib_supp_analysis.r | 51 +++++++++++++++++ 110124_supp_analysis/readme_supp_analysis.R | 60 ++++++++++++++++++++ 2 files changed, 111 insertions(+) create mode 100644 110124_supp_analysis/contrib_supp_analysis.r create mode 100644 110124_supp_analysis/readme_supp_analysis.R diff --git a/110124_supp_analysis/contrib_supp_analysis.r b/110124_supp_analysis/contrib_supp_analysis.r new file mode 100644 index 0000000..d065077 --- /dev/null +++ b/110124_supp_analysis/contrib_supp_analysis.r @@ -0,0 +1,51 @@ +#library(tidyverse) +#library(plyr) + +contrib_df <- read_csv("110124_contrib_strict_subset.csv") +#some preprocessing and expansion +col_order <- c("upstream_vcs_link", "age_in_days", "first_commit", "first_commit_dt", "event_gap", "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") +contrib_df <- contrib_df[,col_order] +contrib_df$ct_before_all <- str_split(gsub("[][]","", contrib_df$before_all_ct), ", ") +contrib_df$ct_after_all <- str_split(gsub("[][]","", contrib_df$after_all_ct), ", ") +contrib_df$ct_before_mrg <- str_split(gsub("[][]","", contrib_df$before_mrg_ct), ", ") +contrib_df$ct_after_mrg <- str_split(gsub("[][]","", contrib_df$after_mrg_ct), ", ") +drop <- c("before_all_ct", "before_mrg_ct", "after_all_ct", "after_mrg_ct") +# 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$observation_type == "all"),] + return(longer) +} +expanded_data <- expand_timeseries(contrib_df[1,]) +for (i in 2:nrow(contrib_df)){ + expanded_data <- rbind(expanded_data, expand_timeseries(contrib_df[i,])) +} +#filter out the windows of time that we're looking at +window_num <- 8 +windowed_data <- expanded_data |> + filter(week >= (27 - window_num) & week <= (27 + window_num)) |> + mutate(D = ifelse(week > 27, 1, 0)) +#scale the age numbers and calculate the week offset here +windowed_data$scaled_project_age <- scale(windowed_data$age_in_days) +windowed_data$scaled_event_gap <- scale(windowed_data$event_gap) +windowed_data$week_offset <- windowed_data$week - 27 +#break out the different type of commit actions +all_actions_data <- windowed_data[which(windowed_data$observation_type == "all"),] +mrg_actions_data <- windowed_data[which(windowed_data$observation_type == "mrg"),] +# data is expanded, can look at things now +all_actions_data$logged_count <- log(all_actions_data$count) +all_actions_data$log1p_count <- log1p(all_actions_data$count) + +#all_gmodel <- glmer.nb(log1p_count ~ D * week_offset + scaled_project_age + scaled_event_gap + (D * week_offset | upstream_vcs_link), +# control=glmerControl(optimizer="bobyqa", +# optCtrl=list(maxfun=2e5)), nAGQ=0, data=all_actions_data) +#saveRDS(all_gmodel, "0711_contrib_all_01.rda") + +#all_residuals <- residuals(all_gmodel) \ No newline at end of file diff --git a/110124_supp_analysis/readme_supp_analysis.R b/110124_supp_analysis/readme_supp_analysis.R new file mode 100644 index 0000000..37af840 --- /dev/null +++ b/110124_supp_analysis/readme_supp_analysis.R @@ -0,0 +1,60 @@ +library(readr) +library(plyr) +library(lme4) +library(stringr) +library(tidyr) + +readme_df <- read_csv("110124_supp_analysis/110124_readme_strict_subset.csv") + +col_order <- c("upstream_vcs_link", "age_in_days", "first_commit", "first_commit_dt", "event_gap", "event_date", "event_hash", "before_all_ct", "after_all_ct", "before_mrg_ct", "after_mrg_ct", "before_auth_new", "after_auth_new", "before_commit_new", "after_commit_new") +readme_df <- readme_df[,col_order] +readme_df$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$after_mrg_ct), ", ") +drop <- c("before_all_ct", "before_mrg_ct", "after_all_ct", "after_mrg_ct") + +# 2 some expansion needs to happens for each project +expand_timeseries <- function(project_row) { + longer <- project_row |> + pivot_longer(cols = starts_with("ct"), + names_to = "window", + values_to = "count") |> + unnest(count) + longer$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,])) +} +head(expanded_data) +#filter out the windows of time that we're looking at +window_num <- 8 +windowed_data <- expanded_data |> + filter(week >= (27 - window_num) & week <= (27 + window_num)) |> + mutate(D = ifelse(week > 27, 1, 0)) +#scale the age numbers +windowed_data$scaled_project_age <- scale(windowed_data$age_in_days) +windowed_data$scaled_event_gap <- scale(windowed_data$event_gap) +windowed_data$week_offset <- windowed_data$week - 27 +#break out the different types of commit actions that are studied +all_actions_data <- windowed_data[which(windowed_data$observation_type == "all"),] +mrg_actions_data <- windowed_data[which(windowed_data$observation_type == "mrg"),] +#log the dependent +all_actions_data$logged_count <- log(all_actions_data$count) +all_actions_data$log1p_count <- log1p(all_actions_data$count) +range(all_actions_data$log1p_count) + + +var(all_actions_data$log1p_count) +mean (all_actions_data$log1p_count) +sd(all_actions_data$log1p_count) +median(all_actions_data$log1p_count) +var(all_actions_data$count) +mean (all_actions_data$count) +sd (all_actions_data$count) +median(all_actions_data$count) \ No newline at end of file