1
0

updating with some descriptive stats for the commit data

This commit is contained in:
Matthew Gaughan 2026-01-06 14:43:38 -08:00
parent f073136e09
commit c1dd41b095
5 changed files with 88 additions and 76 deletions

View File

@ -0,0 +1,66 @@
library(tidyverse)
library(dplyr)
library(lubridate)
c1_event_date <- as.Date("2013-07-01")
c2_event_date <- as.Date("2013-08-28")
c3_event_date <- as.Date("2015-07-02")
relative_week <- function(date, ref_date) {
as.integer(as.numeric(difftime(date, ref_date, units = "days")) %/% 7)
}
contains_http_but_not_url <- function(text) {
# Handle NA values explicitly
ifelse(
is.na(text),
FALSE,
str_detect(text, "http") &
!str_detect(text, "://") |
str_detect(text, "login") |
str_detect(text, "ssl") |
str_detect(text, "tls") |
(str_detect(text, "cert") & !str_detect(text, "certain"))
)
}
#by the time C. Scott Ananian is committing he is employed
core_csv <-"~/121325_work/121225_vd_data/core_2010-01-01_to_2024-12-31.csv"
core_df <- read.csv(core_csv, header = TRUE)
known_affil_emails <- c("krinkle@fastmail.com", "roan.kattouw@gmail.com",
"trevorparscal@gmail.com", "krinklemail@gmail.com", "moriel@gmail.com")
active_names<- c("Timo Tijhof", "Krinkle", "Roan Kattouw", "Catrope",
"Trevor Parscal", "Ed Sanders", "Moriel Schottlender", "Gabriel Wicke", "C. Scott Ananian")
core_df <- core_df |>
mutate(commit_date = ymd_hms(commit_date)) |>
mutate(isAuthorWMF = case_when(
author_name %in% active_names ~ "NAMES",
grepl("@wikimedia\\.org", author_email, ignore.case = TRUE) ~ "TRUE",
grepl("@wikimedia\\.de", author_email, ignore.case = TRUE) ~ "TRUE",
grepl("l10n-bot@translatewiki\\.net", author_email, ignore.case = TRUE) ~ "localization",
grepl("@gerrit\\.wikimedia\\.org", author_email, ignore.case = TRUE) ~ "Gerrit",
TRUE ~ "FALSE"
)) |>
mutate(isVE = case_when(
grepl("VisualEditor", message, ignore.case = TRUE) ~ TRUE,
grepl(" VE ", message, ignore.case = TRUE) ~ TRUE,
TRUE ~ FALSE
)) |>
mutate(code_location = case_when(
grepl("login", diff_info, ignore.case = TRUE) ~ "login_in_location",
grepl("auth", diff_info, ignore.case = TRUE) ~ "auth_in_location",
grepl("security", diff_info, ignore.case = TRUE) ~ "security",
TRUE ~ "Other"
))
c1_relevant <- core_df |>
mutate(week_index = relative_week(commit_date, c1_event_date)) |>
filter(week_index >= -33 & week_index <= 13) |>
filter(author_email != "jenkins-bot@gerrit.wikimedia.org") |>
filter(isVE == TRUE)
total_share <- core_df |>
filter(commit_date >= as.Date('2012-11-11') & commit_date <= as.Date("2015-10-02"))|>
group_by(isAuthorWMF)|>
summarise(count = n(), .groups = 'drop')
#moving 15 from NAMES to FALSE within this result for the 15 commits that C. Scott. Ananian made prior to his employment

View File

@ -105,15 +105,15 @@ core_commits_created <- ggplot(
geom_vline(xintercept = 0, linetype = "dashed", color = "black", linewidth = 0.5) +
geom_text(
data = subset(core_counts, source == "c1" & week_index == 6),
aes(x=week_index, y=120, label='Opt-out deployment'),
aes(x=week_index, y=10, label='Opt-out deployment'),
size = 2.5) +
geom_text(
data = subset(core_counts, source == "c1" & week_index == -33),
aes(x=week_index, y=120, label='Opt-in Testing'),
aes(x=week_index, y=10, label='Opt-in Testing'),
size = 2.5) +
geom_text(
data = subset(core_counts, source == "c2" & week_index == -12),
aes(x=week_index, y=20, label='Deployment Announcement'),
aes(x=week_index, y=10, label='Deployment Announcement'),
size = 2.5) +
theme_minimal() +
scale_fill_viridis_d() +

View File

@ -1,72 +0,0 @@
library(tidyverse)
library(dplyr)
library(lubridate)
c1_event_date <- as.Date("2013-07-01")
c2_event_date <- as.Date("2013-08-28")
c3_event_date <- as.Date("2015-07-02")
relative_week <- function(date, ref_date) {
as.integer(as.numeric(difftime(date, ref_date, units = "days")) %/% 7)
}
core_csv <-"~/121325_work/121225_vd_data/extension_VisualEditor_2000-01-01_to_2016-12-31.csv"
core_df <- read.csv(core_csv, header = TRUE)
known_affil_emails <- c("krinkle@fastmail.com", "roan.kattouw@gmail.com",
"trevorparscal@gmail.com", "krinklemail@gmail.com", "moriel@gmail.com")
active_names<- c("Timo Tijhof", "Krinkle", "Roan Kattouw", "Catrope",
"Trevor Parscal", "Ed Sanders")
core_df <- core_df |>
mutate(commit_date = ymd_hms(commit_date)) |>
mutate(isAuthorWMF = case_when(
author_name %in% active_names ~ "FIVE",
grepl("@wikimedia\\.org", author_email, ignore.case = TRUE) ~ "TRUE",
grepl("@wikimedia\\.de", author_email, ignore.case = TRUE) ~ "TRUE",
grepl("l10n-bot@translatewiki\\.net", author_email, ignore.case = TRUE) ~ "localization",
grepl("@gerrit\\.wikimedia\\.org", author_email, ignore.case = TRUE) ~ "Gerrit",
TRUE ~ "FALSE"
)) |>
mutate(isVE = case_when(
grepl("VisualEditor", message, ignore.case = TRUE) ~ TRUE,
grepl(" VE ", message, ignore.case = TRUE) ~ TRUE,
TRUE ~ FALSE
))
c1_core_weekly <- core_df |>
mutate(week_index = relative_week(commit_date, c1_event_date)) |>
group_by(week_index, isAuthorWMF)|>
summarise(count = n(), .groups = 'drop')|>
filter(week_index >= -9 & week_index < -4) |>
mutate(source = 'c1')
c1summary <- c1_core_weekly |>
group_by(isAuthorWMF)|>
summarize(total = sum(count))
c2_core_weekly <- core_df |>
mutate(week_index = relative_week(commit_date, c2_event_date)) |>
group_by(week_index, isAuthorWMF)|>
summarise(count = n(), .groups = 'drop')|>
filter(week_index >= -104 & week_index <= 13) |>
mutate(source = 'c2')
c3_core_weekly <- core_df |>
mutate(week_index = relative_week(commit_date, c3_event_date)) |>
group_by(week_index, isAuthorWMF)|>
summarise(count = n(), .groups = 'drop')|>
filter(week_index >= -83 & week_index <= 13) |>
mutate(source = 'c3')
#collate and save
core_weekly <- rbind(c1_core_weekly, c2_core_weekly, c3_core_weekly)
c1summary <- c1_core_weekly |>
group_by(isAuthorWMF)|>
summarize(total = sum(count))
c2summary <- c2_core_weekly |>
group_by(isAuthorWMF)|>
summarize(total = sum(count))
c3summary <- c3_core_weekly |>
group_by(isAuthorWMF)|>
summarize(total = sum(count))

View File

@ -36,7 +36,7 @@ ve_counts <- ve_df |>
ve_counts <- ve_counts |>
filter(isAuthorWMF != "Gerrit")|>
filter(source == 'c1')
library(ggplot2)
ve_new_commits_created <- ggplot(
ve_counts,
aes(

View File

@ -0,0 +1,18 @@
1. SSH tunnel from your workstation using the following command:
ssh -N -L 8787:n3439:57601 mjilg@klone.hyak.uw.edu
and point your web browser to http://localhost:8787
2. log in to RStudio Server using the following credentials:
user: mjilg
password: OmvStzwArWC2NNHj/j8p
When done using RStudio Server, terminate the job by:
1. Exit the RStudio Session ("power" button in the top right corner of the RStudio window)
2. Issue the following command on the login node:
scancel -f 32164721
[2026-01-06T14:05:14.031] error: *** JOB 32164721 ON n3439 CANCELLED AT 2026-01-06T14:05:14 DUE TO TIME LIMIT ***