updated ve analysis w new en-testing and wide-testing dates

commit_analysis/case1/0312_core_ve_testing_ba_ranefs.csv

@@ -1,9 +0,0 @@
-"","effect","group","level","term","estimate","std.error","conf.low","conf.high"
-"1","ran_vals","commit_type","other_commit_count","(Intercept)",0.0685032418929246,0.0181064985041167,0.0330151569387276,0.103991326847122
-"2","ran_vals","commit_type","wikimedia_commit_count","(Intercept)",-0.0685032418929394,0.0191716559555347,-0.10607899708978,-0.0309274866960986
-"3","ran_vals","commit_type","other_commit_count","before_after",0.153698714908258,0.0406250196955685,0.0740751394337131,0.233322290382802
-"4","ran_vals","commit_type","wikimedia_commit_count","before_after",-0.153698714908291,0.0430148822329188,-0.238006334884044,-0.0693910949325384
-"5","ran_vals","commit_type","other_commit_count","relative_week",0.00806617338695213,0.00213201816920638,0.00388749456092261,0.0122448522129817
-"6","ran_vals","commit_type","wikimedia_commit_count","relative_week",-0.00806617338695388,0.00225743916316379,-0.0124906728440451,-0.00364167392986262
-"7","ran_vals","commit_type","other_commit_count","before_after:relative_week",-0.00542528453738445,0.00143398916095857,-0.00823585164708405,-0.00261471742768485
-"8","ran_vals","commit_type","wikimedia_commit_count","before_after:relative_week",0.00542528453738562,0.00151834695324874,0.00244937919298198,0.00840118988178927

commit_analysis/case1/0312_ve_core_testing_ba_ranefs.csv

@@ -0,0 +1,9 @@
+"","effect","group","level","term","estimate","std.error","conf.low","conf.high"
+"1","ran_vals","commit_type","other_commit_count","(Intercept)",0,0,0,0
+"2","ran_vals","commit_type","wikimedia_commit_count","(Intercept)",0,0,0,0
+"3","ran_vals","commit_type","other_commit_count","before_after",0.210100230315908,0.0587264628069004,0.0949984782749522,0.325201982356864
+"4","ran_vals","commit_type","wikimedia_commit_count","before_after",-0.210100230315902,0.0620161983828405,-0.331649745604361,-0.0885507150274436
+"5","ran_vals","commit_type","other_commit_count","relative_week",0.000197187070261459,5.51170240557305e-05,8.91596881771995e-05,0.000305214452345719
+"6","ran_vals","commit_type","wikimedia_commit_count","relative_week",-0.000197187070261453,5.82045661455467e-05,-0.000311265923642504,-8.31082168804025e-05
+"7","ran_vals","commit_type","other_commit_count","before_after:relative_week",0.00296979606367595,0.000830106744433257,0.00134281674126297,0.00459677538608893
+"8","ran_vals","commit_type","wikimedia_commit_count","before_after:relative_week",-0.00296979606367587,0.00087660761567573,-0.00468791541897383,-0.00125167670837791

commit_analysis/case1/0312_ve_ve_testing_ba_ranefs.csv

@@ -1,9 +1,9 @@
 "","effect","group","level","term","estimate","std.error","conf.low","conf.high"
-"1","ran_vals","commit_type","other_commit_count","(Intercept)",0,0,0,0
+"1","ran_vals","commit_type","other_commit_count","(Intercept)",0.00187325921107161,0.00396272055679488,-0.00589353036104286,0.00964004878318609
-"2","ran_vals","commit_type","wikimedia_commit_count","(Intercept)",0,0,0,0
+"2","ran_vals","commit_type","wikimedia_commit_count","(Intercept)",-0.00187325921107161,0.00396516815152807,-0.00964484598071188,0.00589832755856866
-"3","ran_vals","commit_type","other_commit_count","before_after",0.0119022181828498,0.0145794598343909,-0.0166729980066047,0.0404774343723042
+"3","ran_vals","commit_type","other_commit_count","before_after",-0.00139801727712659,0.00295738666067831,-0.00719438862041525,0.00439835406616207
-"4","ran_vals","commit_type","wikimedia_commit_count","before_after",-0.0119022181828497,0.0146331623043827,-0.0405826892793688,0.0167782529136695
+"4","ran_vals","commit_type","wikimedia_commit_count","before_after",0.00139801727712659,0.00295921330575988,-0.00440193422473448,0.00719796877898766
-"5","ran_vals","commit_type","other_commit_count","relative_week",-0.000674853711220998,0.000826652849473679,-0.00229506352390682,0.000945356101464824
+"5","ran_vals","commit_type","other_commit_count","relative_week",-8.07243856905614e-05,0.000170765986989873,-0.000415419569975148,0.000253970798594025
-"6","ran_vals","commit_type","wikimedia_commit_count","relative_week",0.000674853711220992,0.000829697770228994,-0.000951324036481026,0.00230103145892301
+"6","ran_vals","commit_type","wikimedia_commit_count","relative_week",8.07243856905613e-05,0.000170871460969434,-0.00025417752379527,0.000415626295176393
-"7","ran_vals","commit_type","other_commit_count","before_after:relative_week",0.0134416522215151,0.0164651685602625,-0.0188294851559806,0.0457127895990109
+"7","ran_vals","commit_type","other_commit_count","before_after:relative_week",0.00635509368794709,0.0134436571769782,-0.0199939901994337,0.0327041775753279
-"8","ran_vals","commit_type","wikimedia_commit_count","before_after:relative_week",-0.013441652221515,0.0165258169128779,-0.0458316581858585,0.0189483537428285
+"8","ran_vals","commit_type","wikimedia_commit_count","before_after:relative_week",-0.00635509368794708,0.0134519607247868,-0.0327204522299765,0.0200102648540824

commit_analysis/commit_count_collation.R

@@ -15,9 +15,9 @@ transform_commit_data <- function(filepath){
 
   
   # TODO: this is project/event specific
-  event_date <- as.Date("2013-07-01")
+  #event_date <- as.Date("2013-07-01")
-  #event_date <- as.Date("2013-04-28")
+  #event_date <- as.Date("2013-04-25")
-  #event_date <- as.Date("2012-12-12")
+  event_date <- as.Date("2012-12-11")
   
   # isolate project id
   project_id <- sub("_.*$", "", file_name)
@@ -144,7 +144,7 @@ transform_commit_data <- function(filepath){
 }
 
 transformed <- transform_commit_data(ve_commit_fp)
-output_filepath <-"/mmfs1/gscratch/comdata/users/mjilg/mw-repo-lifecycles/case1/event_0312_mediawiki_core_weekly_commit_count_data.csv"
+output_filepath <-"/mmfs1/gscratch/comdata/users/mjilg/mw-repo-lifecycles/case1/en-testing_0312_mediawiki_core_weekly_commit_count_data.csv"
 
 write.csv(transformed, output_filepath, row.names = FALSE)
 

commit_analysis/matched_rdd_models.R

@@ -1,18 +1,18 @@
 library(tidyverse)
 library(dplyr)
-entest_fp <-"/mmfs1/gscratch/comdata/users/mjilg/mw-repo-lifecycles/case1/en-testing_0312_extensions_ve_weekly_commit_count_data.csv"
+entest_fp <-"/mmfs1/gscratch/comdata/users/mjilg/mw-repo-lifecycles/case1/en-testing_0312_mediawiki_core_weekly_commit_count_data.csv"
 entest_df <- read.csv(entest_fp, header = TRUE) |> mutate(rd_event = "en-testing")
 
-widetest_fp <-"/mmfs1/gscratch/comdata/users/mjilg/mw-repo-lifecycles/case1/wide-testing_0312_extensions_ve_weekly_commit_count_data.csv"
+widetest_fp <-"/mmfs1/gscratch/comdata/users/mjilg/mw-repo-lifecycles/case1/wide-testing_0312_mediawiki_core_weekly_commit_count_data.csv"
 widetest_df <- read.csv(widetest_fp, header = TRUE) |> mutate(rd_event = "wide-testing")
 
-event_fp <-"/mmfs1/gscratch/comdata/users/mjilg/mw-repo-lifecycles/case1/event_0312_extensions_ve_weekly_commit_count_data.csv"
+event_fp <-"/mmfs1/gscratch/comdata/users/mjilg/mw-repo-lifecycles/case1/event_0312_mediawiki_core_weekly_commit_count_data.csv"
 event_df <- read.csv(event_fp, header = TRUE) |> mutate(rd_event = "default")
 
 #input_df <- bind_rows(entest_df, widetest_df, event_df)
 #dropping the event (2013-07-01) from the modeling
-#input_df <- bind_rows(entest_df, widetest_df)
+input_df <- bind_rows(entest_df, widetest_df)
-input_df <- event_df
+#input_df <- event_df
 
 input_df <- input_df |>
   mutate(nonbot_commit_count = commit_count - bot_commit_count)|>
@@ -57,7 +57,7 @@ intermediate_long_df <- intermediate_long_df |>
 optimal_bandwidth <- get_optimal_bandwidth(intermediate_long_df)
 
 library(dplyr)
-window_num <- 10
+window_num <- 12
 final_long_df <- intermediate_long_df |>
   filter(relative_week >= (-window_num) & relative_week <= window_num) |>
   filter(commit_type != "unaff_ft_commit_count")
@@ -76,7 +76,7 @@ mlm <- glmer.nb(lengthened_commit_count ~ before_after*relative_week +
                 data=final_long_df)
 #(before_after*relative_week|rd_event)
 
-saveRDS(mlm, file = "0312_ve_ve_event_commits_mlm.rds")
+saveRDS(mlm, file = "0312_ve_core_event_commits_mlm.rds")
 #mlm <- readRDS("commit_analysis/case1/0312_core_ve_testing_commits_mlm.rds")
 summary(mlm)
 qqnorm(residuals(mlm))
@@ -88,7 +88,7 @@ library(broom.mixed)
 library(ggplot2)
 condvals <- broom.mixed::tidy(mlm, effects = "ran_vals", conf.int = TRUE)
 glmer_ranef_ba <- condvals
-write.csv(glmer_ranef_ba, "0312_ve_ve_event_ba_ranefs.csv")
+write.csv(glmer_ranef_ba, "0312_ve_core_event_ba_ranefs.csv")
 
 
 

commit_analysis/testing-share-plotting.R

@@ -1,11 +1,11 @@
 library(tidyverse)
-entest_fp <-"/mmfs1/gscratch/comdata/users/mjilg/mw-repo-lifecycles/case1/en-testing_0312_mediawiki_core_weekly_commit_count_data.csv"
+entest_fp <-"/mmfs1/gscratch/comdata/users/mjilg/mw-repo-lifecycles/case1/en-testing_0312_extensions_ve_weekly_commit_count_data.csv"
 entest_df <- read.csv(entest_fp, header = TRUE) |> mutate(rd_event = "en-testing")
 
-widetest_fp <-"/mmfs1/gscratch/comdata/users/mjilg/mw-repo-lifecycles/case1/wide-testing_0312_mediawiki_core_weekly_commit_count_data.csv"
+widetest_fp <-"/mmfs1/gscratch/comdata/users/mjilg/mw-repo-lifecycles/case1/wide-testing_0312_extensions_ve_weekly_commit_count_data.csv"
 widetest_df <- read.csv(widetest_fp, header = TRUE) |> mutate(rd_event = "wide-testing")
 
-event_fp <-"/mmfs1/gscratch/comdata/users/mjilg/mw-repo-lifecycles/case1/event_0312_mediawiki_core_weekly_commit_count_data.csv"
+event_fp <-"/mmfs1/gscratch/comdata/users/mjilg/mw-repo-lifecycles/case1/event_0312_extensions_ve_weekly_commit_count_data.csv"
 event_df <- read.csv(event_fp, header = TRUE) |> mutate(rd_event = "default")
 
 #input_df <- bind_rows(entest_df, widetest_df, event_df)
@@ -21,20 +21,19 @@ input_df <- input_df |>
   dplyr::select(-wikia_commit_count)
 
 #get into mlm format
-#long_df <- input_df |>
-#  tidyr::pivot_longer(cols = c(other_commit_count, wikimedia_commit_count),
-#               names_to = "commit_type",
-#               values_to = "lengthened_commit_count")
 long_df <- input_df |>
-  tidyr::pivot_longer(cols = c(wmf_ft_commit_count, unaff_ft_commit_count, nonbot_commit_count),
+  tidyr::pivot_longer(cols = c(other_commit_count, wikimedia_commit_count),
                names_to = "commit_type",
                values_to = "lengthened_commit_count")
+#long_df <- input_df |>
+#  tidyr::pivot_longer(cols = c(wmf_ft_commit_count, unaff_ft_commit_count, nonbot_commit_count),
+#               names_to = "commit_type",
+#               values_to = "lengthened_commit_count")
 
-intermediate_long_df <- long_df 
+intermediate_long_df <- long_df |>
-#|>
+  mutate(commit_share = lengthened_commit_count / (nonbot_commit_count)) |>
-#  mutate(commit_share = lengthened_commit_count / (nonbot_commit_count)) |>
+  mutate(log_commits = log1p(lengthened_commit_count))|>
-#  mutate(log_commits = log1p(lengthened_commit_count))|>
+  mutate(scaled_long_commits = lengthened_commit_count / 10) 
-# mutate(scaled_long_commits = lengthened_commit_count / 10) 
 
 
 window_num <- 8
@@ -42,8 +41,8 @@ final_long_df <- intermediate_long_df |>
   filter(relative_week >= (- window_num) & relative_week <= (window_num)) 
 
 affiliationColors <-
-  setNames( c('#5da2d8', '#c7756a', 'black')
+  setNames( c('#5da2d8', '#c7756a')
-            ,c("unaff_ft_commit_count", "wmf_ft_commit_count", "nonbot_commit_count"))
+            ,c("other_commit_count", "wikimedia_commit_count"))
 
 
 commit_plot <- final_long_df |>
@@ -57,7 +56,7 @@ commit_plot <- final_long_df |>
   scale_color_manual(values = affiliationColors,
                      labels = c("other_commit_count" = "Unaffiliated", "wikimedia_commit_count" = "WMF Affiliated")) + 
   scale_linetype_discrete(labels = c("enwiki testing (2012-12-12)", "wide testing (2013-04-25)")) + 
-  ggtitle("VisualEditor New Contributors Commits Around Opt-In Testing Events (by Affiliation)") +
+  ggtitle("mw-core New Contributors Commits Around Opt-In Testing Events (by Affiliation)") +
   theme_bw() + 
   theme(legend.position = "top")
 commit_plot
@@ -99,4 +98,4 @@ commit_share_plot <- final_long_df |>
   theme(legend.position = "top")
 commit_share_plot
 
-ggsave(filename = "0312-ve-testing-share.png", plot = commit_share_plot, width = 12, height = 9, dpi = 800)
+ggsave(filename = "0312-ve-ve-testing-share.png", plot = commit_share_plot, width = 12, height = 9, dpi = 800)

mgaughan-rstudio-server_24810962.out

@@ -1,17 +1,17 @@
 1. SSH tunnel from your workstation using the following command:
 
-   ssh -N -L 8787:n3439:57439 mjilg@klone.hyak.uw.edu
+   ssh -N -L 8787:n3439:36687 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: Q5pJ0QUFUjx7RBFTzpvm
+   password: kYV6l/rzT7dbLI0xaX1j
 
 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 24802792
+      scancel -f 24810962