1
0
mw-lifecycle-analysis/gerrit_analysis/plotting_gerrit.R
2025-02-16 14:08:16 -08:00

62 lines
1.9 KiB
R

library(tidyverse)
count_data_fp <-"/mmfs1/gscratch/comdata/users/mjilg/mw-repo-lifecycles/case1/event_0216_ve_gerrit_count.csv"
input_df <- read.csv(count_data_fp, header = TRUE)
#window_num <- 19
window_num <- 52
input_df <- input_df |>
filter(relative_week >= (- window_num) & relative_week <= (window_num)) |>
mutate(parent_projects = if_else(project == "mediawiki/extensions/VisualEditor",
"mediawiki/extensions", project))
library(scales)
library(ggplot2)
time_plot <- input_df |>
ggplot(aes(x=relative_week, y=task_count, color=parent_projects)) +
labs(x="Weekly Offset", y="New Gerrit Tasks Created", color = "Project") +
geom_smooth() +
geom_vline(xintercept = 0)+
theme_bw() +
theme(legend.position = "top")
time_plot
abandoned_df <- input_df |>
filter(status == "ABANDONED")
time_plot <- abandoned_df |>
ggplot(aes(x=relative_week, y=task_count, color=parent_projects)) +
labs(x="Weekly Offset", y="AbandonedGerrit Tasks Created", color = "Project") +
geom_line() +
geom_vline(xintercept = 0)+
theme_bw() +
theme(legend.position = "top")
time_plot
delta_df <- input_df |>
filter(task_count != 0) |>
filter(relative_week >= (- 12))
time_plot <- delta_df |>
ggplot(aes(x=relative_week, y=avg_resolution_time, color=parent_projects)) +
labs(x="Weekly Offset", y="Avg. (weekly) Time from task creation to last update (days)", color = "Project") +
geom_line() +
geom_vline(xintercept = 0)+
theme_bw() +
theme(legend.position = "top")
time_plot
loc_df <- input_df |>
filter(task_count != 0) |>
filter(status != "ABANDONED")
time_plot <- loc_df |>
ggplot(aes(x=relative_week, y=avg_deletions, color=parent_projects)) +
labs(x="Weekly Offset", y="Avg. LOC Deleted per Accepted Gerrit Task", color = "Project") +
geom_line() +
geom_vline(xintercept = 0)+
theme_bw() +
theme(legend.position = "top")
time_plot