README.md

@@ -1,7 +1,3 @@
 # mw-lifecycle-analysis
 
-Analysis scripts and code for studying the deployment processes of three MediaWiki/Wikimedia features (2013-2015)
+Analysis scripts and code for studying lifecycles of MediaWiki projects
-
-
-
-

govdoc-cr-age-dist.R

@@ -0,0 +1,45 @@
+library(dplyr)
+contributing_df_filepath <-"/mmfs1/gscratch/comdata/users/mjilg/govdoc-cr-data/final_data/metadata/CONTRIBUTING_weekly_count_data.csv"
+contributing_df = read.csv(contributing_df_filepath, header = TRUE) 
+
+readme_df_filepath <- "/mmfs1/gscratch/comdata/users/mjilg/govdoc-cr-data/final_data/metadata/README_weekly_count_data.csv"
+readme_df = read.csv(readme_df_filepath, header = TRUE)
+
+combined_df <- bind_rows(
+  contributing_df %>%
+    group_by(project_id) %>%
+    select(project_id, age_at_commit) %>%
+    mutate(document = factor("CONTRIBUTING", levels = c("CONTRIBUTING", "README"))),
+  readme_df %>%
+    group_by(project_id) %>%
+    select(project_id, age_at_commit) %>%
+    mutate(document = factor("README", levels = c("CONTRIBUTING", "README")))
+)
+
+unique_combined_df <- combined_df %>%
+  distinct(project_id, age_at_commit, document)
+
+library(tidyverse)
+library(tidyquant)
+library(ggdist)
+library(ggthemes)
+library(ggplot2)
+
+age_raincloud <- unique_combined_df |>
+  ggplot(aes(x = factor(document), y = age_at_commit, fill = factor(document))) +
+  geom_boxplot(
+    width = 0.12,
+    # removing outliers
+    outlier.color = NA,
+    alpha = 0.5
+  ) +
+  ggplot::stat_dots(
+    # ploting on left side
+    side = "left",
+    # adjusting position
+    justification = 1.1,
+    # adjust grouping (binning) of observations
+    binwidth = 0.25
+  )
+
+age_raincloud

mgaughan-rstudio-server_27419348.out

@@ -1,18 +0,0 @@
-1. SSH tunnel from your workstation using the following command:
-
-   ssh -N -L 8787:n3439:50819 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: lM83HdgeT310p2tkyoCk
-
-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 27419348
-slurmstepd: error: *** JOB 27419348 ON n3439 CANCELLED AT 2025-07-07T13:08:38 ***

p2_EDA/phab_weekly_bins.R

@@ -34,9 +34,6 @@ c1_input_df <- c1_input_df |>
     date_created >=  as.numeric(as.POSIXct("2013-06-06", tz = "UTC"))  & date_created < as.numeric(as.POSIXct("2013-07-01", tz = "UTC")) ~ 2, # post-announcement pre-deployment
     date_created >= as.numeric(as.POSIXct("2013-07-01", tz = "UTC"))~ 3                             # post-deployment opt-out
   )) |>
-  mutate(author_closer = AuthorPHID %in% CloserPHID,
-         same_author = AuthorPHID == CloserPHID) |>
-  mutate(closed_relevance = date_closed <= as.numeric(as.POSIXct("2013-10-01", tz = "UTC"))) |>
   mutate(week_index = relative_week(date_created, as.Date("2013-07-01")))
 
 
@@ -54,9 +51,6 @@ c2_input_df <- c2_input_df |>
     date_created >=  as.numeric(as.POSIXct("2013-08-01", tz = "UTC"))  & date_created < as.numeric(as.POSIXct("2013-08-28", tz = "UTC")) ~ 2, # post-announcement pre-deployment
     date_created >= as.numeric(as.POSIXct("2013-08-28", tz = "UTC"))~ 3                             # post-deployment opt-out
   )) |>
-  mutate(author_closer = AuthorPHID %in% CloserPHID,
-         same_author = AuthorPHID == CloserPHID) |>
-  mutate(closed_relevance = date_closed <= as.numeric(as.POSIXct("2013-11-27", tz = "UTC"))) |>
   mutate(week_index = relative_week(date_created, as.Date("2013-08-28")))
 
 # c3 key dates 
@@ -72,9 +66,6 @@ c3_input_df <- c3_input_df %>%
     date_created >=  as.numeric(as.POSIXct("2015-06-12", tz = "UTC"))  & date_created < as.numeric(as.POSIXct("2015-07-02", tz = "UTC")) ~ 2, # post-announcement pre-deployment
     date_created >= as.numeric(as.POSIXct("2015-07-02", tz = "UTC"))~ 3                             # post-deployment opt-out
   )) |>
-  mutate(author_closer = AuthorPHID %in% CloserPHID,
-         same_author = AuthorPHID == CloserPHID) |>
-  mutate(closed_relevance = date_closed <= as.numeric(as.POSIXct("2015-10-02", tz = "UTC"))) |>
   mutate(week_index = relative_week(date_created, as.Date("2015-07-02")))
 
 # Combine the dataframes into one
@@ -89,8 +80,7 @@ combined_df <- combined_df %>%
   arrange(date_created, .by_group = TRUE) %>%
   mutate(
     task_index_prev = cumsum(comment_type == "task_description") - (comment_type == "task_description"),
-    comment_index_prev = cumsum(comment_type == "task_subcomment") - (comment_type == "task_subcomment"),
+    comment_index_prev = cumsum(comment_type == "task_subcomment") - (comment_type == "task_subcomment")
-    author_prior_phab_contrib = task_index_prev + comment_index_prev
   ) %>%
   ungroup() |> 
   rowwise() %>%
@@ -113,47 +103,52 @@ combined_df <- combined_df %>%
 
 
 combined_task_df <- combined_df %>% 
-  add_count(TaskPHID, name = "task_event_comment_count") |>
+  add_count(TaskPHID, name = "TaskPHID_count") |>
   filter(comment_type == "task_description") |>
   mutate(time_to_close = date_closed - date_created,
          time_to_close_hours = as.numeric(difftime(date_closed, date_created, units = "hours"))
   ) |>
   group_by(AuthorPHID, source) %>%
   arrange(date_created, .by_group = TRUE) %>% # recommended: order by date_created
-  mutate(author_task_index = row_number()) %>%
+  mutate(task_index = row_number()) %>%
   ungroup()
 
-library(dplyr)
+ggplot(combined_task_df, aes(x = week_index, y = priority_score, color = source)) +
-
-combined_task_df <- combined_task_df |>
-  group_by(source) %>%
-  mutate(
-    time_to_close_percentile = 1- percent_rank(time_to_close_hours),
-    comment_count_percentile = percent_rank(task_event_comment_count),
-    author_task_percentile = percent_rank(task_index_prev)
-    # inverting it so that higher percentile is faster
-  ) %>%
-  ungroup()
-
-ggplot(combined_task_df, aes(x = author_task_percentile, y =priority_score, color = source)) +
   geom_point(alpha = 0.6) +                # Points, with some transparency
   geom_smooth(method = "loess", se = TRUE) + # LOESS curve, no confidence band
-  theme_minimal() +
+  theme_minimal()        
-  facet_grid(source ~ author_closer)
 
+library(stringr)
+
+# 1. Count modal verbs in each task comment_text
+combined_task_df <- combined_task_df %>%
+  rowwise() %>%
+  mutate(
+    modal_verb_count = sum(str_detect(
+      str_to_lower(comment_text),
+      paste0("\\b", modal_verbs, "\\b", collapse = "|")
+    )),
+    modal_subset_count = sum(str_detect(
+      str_to_lower(comment_text),
+      paste0("\\b", modal_subset, "\\b", collapse = "|")
+    )),
+    user_count = sum(str_detect(
+      str_to_lower(comment_text),
+      paste0("\\b", whatever_subset, "\\b", collapse = "|")
+    ))
+  ) %>%
+  ungroup()
 library(ggdist)
-
+ggplot(combined_df, aes(x = week_index, y = modal_subset_count, color = source, linetype=AuthorWMFAffil)) +
-ggplot(combined_task_df, aes(x=phase, y=comment_count_percentile)) +
+  geom_point(alpha=0.1) +             # Points, with some transparency
-  stat_slabinterval() +
+  geom_smooth(method = "loess", se = FALSE) + 
-  theme_minimal()+
+  theme_minimal()      
-  facet_grid(source ~ AuthorWMFAffil)
 
 
-closed_combined_task_df <- combined_task_df |>
-  filter(!is.na(closed_relevance))
 
-ggplot(combined_task_df, aes(x=time_to_close_percentile, y=priority_score)) + 
+combined_task_df_subset <- subset(combined_task_df, time_to_close_hours < 1000)
-  geom_point(alpha = 0.6) + 
+
-  geom_smooth(method = "loess", se = TRUE) + # LOESS curve, no confidence band# Points, with some transparency
+ggplot(combined_task_df_subset, aes(x = TaskPHID_count, y = task_index, color = source)) +
-  theme_minimal()+
+  geom_smooth(method = "loess", se = TRUE) + 
-  facet_grid(source ~ author_closer)
+  geom_point(alpha=0.1) +   
+  theme_minimal()

phab_data_exploration.R

@@ -0,0 +1,4 @@
+library(tidyverse)
+
+c1_phab <-"/mmfs1/gscratch/comdata/users/mjilg/mw-repo-lifecycles/case1/0228_ve_phab_comments.csv "
+c1_phab_df <- read.csv(c1_count , header = TRUE)