updating viz for ww presentation

commit_analysis/plotting/ww-bots-plot-script.R

@@ -47,7 +47,7 @@ new_unaff_authors <- new_authors_long_df |>
   geom_col(position='dodge') +
   labs(x = "Relative Week", y = "Commits", fill="Contributor Tenure (New contributors <= 5 commits before deployment announcement)") +
   geom_vline(data = long_df |> filter(source == "c1"), 
-             aes(xintercept = -30), 
+             aes(xintercept = -29), 
              linetype = "dotted", color = "black", linewidth = 1) +
   geom_vline(data = long_df |> filter(source == "c1"), 
              aes(xintercept = -9), 
@@ -63,12 +63,12 @@ new_unaff_authors <- new_authors_long_df |>
             inherit.aes = FALSE, color = "black", size = 4) +
   geom_vline(xintercept = 0, linetype = "dashed", color = "black", linewidth = 1) + # Add vertical line at week 0
   geom_text(data = data.frame(source = "c1", relative_week = 7, lengthened_commit_count = 90), 
-            aes(x = relative_week, y = lengthened_commit_count, label = "Feature Deployment"), 
+            aes(x = relative_week, y = lengthened_commit_count, label = "Wide Deployment"), 
             inherit.aes = FALSE, color = "black", size = 4) +
   scale_fill_manual(values = c("returning_unaff_commit_count" = "#FFC107",  # Color for "Returning Contributors"
                                "unaff_new_commit_count" = "#004D40"),   
-                    labels = c("returning_unaff_commit_count" = "Returning Contributors",
-                               "unaff_new_commit_count" = "New Contributors")
+                    labels = c("returning_unaff_commit_count" = "Returning",
+                               "unaff_new_commit_count" = "New")
   ) +
   ggtitle("Unaffiliated Commits to Bot Framework Libraries During Feature Deployments") +
   theme_bw() +

commit_analysis/plotting/ww-plot-script.R

@@ -37,9 +37,9 @@ commit_authors <- long_df |>
              y=lengthened_commit_count, 
              fill=factor(commit_type))) +
   geom_col(position='dodge') +
-  labs(x = "Relative Week", y = "Commits", fill="Commit Type") +
+  labs(x = "Relative Week", y = "Commits", fill="Commit Author") +
   geom_vline(data = long_df |> filter(source == "c1"), 
-             aes(xintercept = -30), 
+             aes(xintercept = -29), 
              linetype = "dotted", color = "black", linewidth = 1) +
   geom_vline(data = long_df |> filter(source == "c1"), 
              aes(xintercept = -9), 
@@ -55,11 +55,11 @@ commit_authors <- long_df |>
             inherit.aes = FALSE, color = "black", size = 4) +
   geom_vline(xintercept = 0, linetype = "dashed", color = "black", linewidth = 1) + # Add vertical line at week 0
   geom_text(data = data.frame(source = "c1", relative_week = 7, lengthened_commit_count = 50), 
-            aes(x = relative_week, y = lengthened_commit_count, label = "Feature Deployment"), 
+            aes(x = relative_week, y = lengthened_commit_count, label = "Wide Deployment"), 
             inherit.aes = FALSE, color = "black", size = 4) +
   scale_fill_manual(values = affiliationColors,
-                    labels = c("unaff_commit_count" = "Unaffiliated Commits",
-                               "wikimedia_commit_count" = "WMF Commits")) +
+                    labels = c("unaff_commit_count" = "Unaffiliated",
+                               "wikimedia_commit_count" = "WMF-affiliated")) +
   ggtitle("Feature Commits During Deployment Process") +
   theme_bw()+
   theme(

mgaughan-rstudio-server_25681892.out

@@ -0,0 +1,17 @@
+1. SSH tunnel from your workstation using the following command:
+
+   ssh -N -L 8787:n3439:39175 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: twImEJor5ex498HTzJjx
+
+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 25681892

ww-task-plot-script.R

@@ -0,0 +1,90 @@
+library(tidyverse)
+
+c1_count <-"/mmfs1/gscratch/comdata/users/mjilg/mw-repo-lifecycles/case1/phab_tasks.csv"
+c1_input_df <- read.csv(c1_count , header = TRUE) 
+
+c3_count <-"/mmfs1/gscratch/comdata/users/mjilg/mw-repo-lifecycles/case3/phab_tasks.csv"
+c3_input_df <- read.csv(c3_count , header = TRUE) 
+
+c1_unique_counts <- c1_input_df %>%
+  group_by(meta.affil, week_bin) %>%
+  summarise(unique_count = n_distinct(conversation_id), .groups = "drop")
+
+c3_unique_counts <- c3_input_df %>%
+  group_by(meta.affil, week_bin) %>%
+  summarise(unique_count = n_distinct(conversation_id), .groups = "drop")
+
+c1_unique_counts <- c1_unique_counts%>% mutate(source = "c1")
+c2_unique_counts <- data.frame(
+  meta.affil = rep("False", 117), 
+  week_bin = -103:13,          
+  unique_count = rep(0, 117),  
+  source = rep("c2", 117)       
+)
+c3_unique_counts <- c3_unique_counts %>% mutate(source = "c3")
+
+combined_df <- bind_rows(c1_unique_counts, c2_unique_counts, c3_unique_counts)
+
+library(scales)
+library(ggplot2)
+
+
+affiliationColors <-
+  setNames( c('#5da2d8', '#c7756a')
+            ,c("False", "True"))
+
+commit_authors <- combined_df |>
+  ggplot(aes(x=week_bin, 
+             y=unique_count, 
+             fill=factor(meta.affil))) +
+  geom_col(position='dodge') +
+  labs(x = "Relative Week", y = "Tasks", fill="Task Author") +
+  geom_vline(data = combined_df |> filter(source == "c1"), 
+             aes(xintercept = -29), 
+             linetype = "dotted", color = "black", linewidth = 1) +
+  geom_vline(data = combined_df |> filter(source == "c1"), 
+             aes(xintercept = -9), 
+             linetype = "dotted", color = "black", linewidth = 1) +
+  geom_vline(data = combined_df |> filter(source == "c1"), 
+             aes(xintercept = -4), 
+             linetype = "3313", color = "black", linewidth = 1) +
+  geom_vline(data = combined_df |> filter(source == "c3"), 
+             aes(xintercept = -97), 
+             linetype = "dotted", color = "black", linewidth = 1) +
+  geom_vline(data = combined_df |> filter(source == "c3"), 
+             aes(xintercept = -3), 
+             linetype = "3313", color = "black", linewidth = 1) +
+  geom_text(data = data.frame(source = "c1", relative_week = -40, lengthened_commit_count = 130), 
+            aes(x = relative_week, y = lengthened_commit_count, label = "Opt-In Testing Deployment"), 
+            inherit.aes = FALSE, color = "black", size = 4) +
+  geom_vline(xintercept = 0, linetype = "dashed", color = "black", linewidth = 1) + # Add vertical line at week 0
+  geom_text(data = data.frame(source = "c1", relative_week = 7, lengthened_commit_count = 130), 
+            aes(x = relative_week, y = lengthened_commit_count, label = "Wide Deployment"), 
+            inherit.aes = FALSE, color = "black", size = 4) +
+  geom_text(data = data.frame(source = "c3", relative_week = -15, lengthened_commit_count = 130), 
+            aes(x = relative_week, y = lengthened_commit_count, label = "Wide Deployment Announcement"), 
+            inherit.aes = FALSE, color = "black", size = 4) +
+  scale_fill_manual(values = affiliationColors,
+                    labels = c("False" = "Unaffiliated",
+                               "True" = "WMF-affiliated")) +
+  ggtitle("New Phabricator Tasks During Deployment Process") +
+  theme_bw()+
+  theme(
+    legend.position = "top",
+    plot.title = element_text(size = 18, face = "bold"), # Increase title font size
+    axis.title.x = element_text(size = 16),             # Increase x-axis title font size
+    axis.title.y = element_text(size = 16),             # Increase y-axis title font size
+    axis.text.x = element_text(size = 16),              # Increase x-axis text font size
+    axis.text.y = element_text(size = 16),              # Increase y-axis text font size
+    legend.text = element_text(size = 16),              # Increase legend text font size
+    legend.title = element_text(size = 16),
+    strip.text = element_text(size = 14)# Increase legend title font size
+  ) +
+  facet_wrap(~source, nrow = 3, labeller = labeller(source = c(
+    "c1" = "VisualEditor",
+    "c2" = "HTTPS-as-default",
+    "c3" = "HTTP-deprecation"
+  )))
+commit_authors
+
+ggsave(filename = "ww-0501-tasks-faceted.png", plot = commit_authors, width = 15, height = 9, dpi = 800)