diff --git a/121325_work/misc.R b/121325_work/misc.R
index 5ce8ded..94a294b 100644
--- a/121325_work/misc.R
+++ b/121325_work/misc.R
@@ -8,14 +8,19 @@ relative_week <- function(date, ref_date) {
   as.integer(as.numeric(difftime(date, ref_date, units = "days")) %/% 7)
 }
 
-core_csv <-"~/121325_work/121225_vd_data/core_2010-01-01_to_2024-12-31.csv"
+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(
-    grepl("krinkle@fastmail\\.com", author_email, ignore.case = TRUE) ~ "TRUE",
+    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"
   )) |>
@@ -27,10 +32,41 @@ core_df <- core_df |>
 
 c1_core_weekly <- core_df |>
   mutate(week_index = relative_week(commit_date, c1_event_date)) |>
-  group_by(week_index, isVE)|>
+  group_by(week_index, isAuthorWMF)|>
   summarise(count = n(), .groups = 'drop')|>
-  filter(week_index >= -33 & week_index <= 13) |>
+  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))
+
 
-true_ <- c1_core_weekly |>
-  filter(isVE == TRUE)
diff --git a/analysis_data/scratch.R b/analysis_data/scratch.R
index 218ba54..493d6c0 100644
--- a/analysis_data/scratch.R
+++ b/analysis_data/scratch.R
@@ -2,6 +2,29 @@ library(tidyverse)
 main_csv <-"~/analysis_data/120725_unified.csv"
 main_df <- read.csv(main_csv, header = TRUE) 
 
+bz_summary <- main_df |>
+  mutate(isBz = if_else(
+    AuthorPHID == "PHID-USER-ynivjflmc2dcl6w5ut5v", TRUE, FALSE
+  )) |>
+  group_by(source, comment_type)|>
+  summarise(count = n(), .groups = 'drop')
+  
+  
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
 dsl_csv <-"~/dsl/120725_DSL_frame.csv"
 dsl_df <- read.csv(dsl_csv, header = TRUE)