updating plots for ww

commit_analysis/commit_plotting.R

@@ -1,22 +1,22 @@
 library(tidyverse)
-count_data_fp <-"/mmfs1/gscratch/comdata/users/mjilg/mw-repo-lifecycles/case1/event_0217_extensions_ve_weekly_commit_count_data.csv"
+count_data_fp <-"/mmfs1/gscratch/comdata/users/mjilg/mw-repo-lifecycles/case1/en-testing_0217_extensions_ve_weekly_commit_count_data.csv"
 input_df <- read.csv(count_data_fp, header = TRUE) 
 
 input_df$nonbot_commit_count <- input_df$commit_count - input_df$bot_commit_count
 
-window_num <- 52
-input_df <- input_df |>
-  filter(relative_week >= (- window_num) & relative_week <= (window_num)) |>
+window_num <- 12
+intermediate_df <- input_df |>
   mutate(nonbot_commit_count = commit_count - bot_commit_count)|>
   mutate(other_commit_count = nonbot_commit_count - mediawiki_dev_commit_count - wikia_commit_count - wikimedia_commit_count) |>
   mutate(wikimedia_commit_count = wikimedia_commit_count + mediawiki_dev_commit_count + wikia_commit_count) |>
-  select(-mediawiki_dev_commit_count) |>
-  select(-wikia_commit_count)
+  dplyr::select(-mediawiki_dev_commit_count) |>
+  dplyr::select(-wikia_commit_count) |>
+  filter(relative_week >= (- window_num) & relative_week <= (window_num)) 
 
 library(scales)
 library(ggplot2)
 
-time_plot <- input_df |>
+time_plot <- intermediate_df |>
   ggplot(aes(x=relative_week, y=nonbot_commit_count)) +
   labs(x="Weekly Offset", y="Nonbot Commit Count") +
   geom_smooth() +
@@ -27,7 +27,7 @@ time_plot
 
 library(dplyr)
 
-share_df <- input_df |>
+share_df <- intermediate_df |>
   mutate(wikimedia_share = wikimedia_commit_count / nonbot_commit_count) |>
   mutate(other_share = other_commit_count / nonbot_commit_count)|>
   drop_na()
@@ -36,18 +36,15 @@ share_long <- share_df |>
   dplyr::select(relative_week, wikimedia_share, other_share) |>
   pivot_longer(cols = c(wikimedia_share, other_share), names_to = "category", values_to = "share")
 
-share_plot <- share_long |>
-  ggplot(aes(x=relative_week, y=share, color=category)) +
+commit_share_plot <- share_long |>
+  ggplot(aes(x=relative_week, 
+             y=share, 
+             color=category)) +
   geom_line() +
-  geom_vline(xintercept = 0)+
-  annotate("text", x = -7, y=1, label = "2012-12-12") +
-  geom_vline(xintercept = 19)+
-  annotate("text", x = 12, y=1, label = "2013-04-28") +
-  geom_vline(xintercept = 28)+
-  annotate("text", x = 35, y=1, label = "2013-07-01") +
-  labs(x = "Relative Week", y = "Share of Nonbot Commit Count", color = "Affiliation") +
-  ggtitle("VE Weekly Share of Nonbot Commit Count by Affiliation (enwiki opt-in testing 2012-12-12)") +
+  geom_point() + 
+  labs(x = "Relative Week", y = "Share of Nonbot Commits", color="Commit Author Affiliation") +
+  scale_color_discrete(labels = c("Unaffiliated", "Organizationally Affiliated")) +
+  ggtitle("VisualEditor Nonbot Commit Share Around Opt-out Deployment") +
   theme_bw() + 
   theme(legend.position = "top")
-share_plot
-
+commit_share_plot

commit_analysis/matched_rdd_models.R

@@ -10,7 +10,8 @@ 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 <- input_df |>
   mutate(nonbot_commit_count = commit_count - bot_commit_count)|>
@@ -37,16 +38,13 @@ intermediate_long_df <- long_df |>
 
 library(rdd)
 
-intermediate_long_df <- intermediate_long_df |>
-  drop_na()
-
 var(intermediate_long_df$lengthened_commit_count) # 1253.343
 mean(intermediate_long_df$lengthened_commit_count) # 44.92381
 median(intermediate_long_df$lengthened_commit_count) # 39.5
 
 get_optimal_bandwidth <- function(df){
   bw <- tryCatch({
-    IKbandwidth(df$relative_week, df$lengthened_commit_count, cutpoint = 0, verbose = FALSE, kernel = "triangular")
+    IKbandwidth(df$relative_week, df$commit_share, cutpoint = 0, verbose = FALSE, kernel = "triangular")
   }, error = function(e) {
     NA
   })
@@ -63,15 +61,15 @@ library(fitdistrplus)
 descdist(final_long_df$lengthened_commit_count, discrete=FALSE)
 #start_values <- list(shape1 = 1, shape2 = 1)
 #fit <- MASS::fitdistr(as.numeric(long_df$lengthened_commit_count), "negative binomial")
-print(fit)
+#print(fit)
 
 #NOTE should not run if you've already dropped NA
 mlm <- glmer.nb(lengthened_commit_count ~ before_after*relative_week +
-                  (before_after*relative_week|commit_type) + 
-                  (before_after*relative_week|rd_event),
+                  (before_after*relative_week|commit_type),
                 control=glmerControl(optimizer="bobyqa",
                                      optCtrl=list(maxfun=2e5)), nAGQ=0,
                 data=final_long_df)
+#(before_after*relative_week|rd_event)
 #mlm <- lmer(lengthened_commit_count ~ before_after*relative_week+
 #                    (before_after*relative_week|commit_type) + 
 #                    (before_after*relative_week|rd_event) ,data=long_df)
@@ -83,24 +81,33 @@ print(res)
 #final_long_df <- final_long_df |>
 #  drop_na()
 library(performance)
-#descdist(long_df$commit_share, discrete=FALSE)
-#fit <- MASS::fitdistr(as.numeric(long_df$commit_share), "normal")
-#print(fit)
+library(texreg)
+
+descdist(final_long_df$commit_share, discrete=FALSE)
+
 wikimedia_long_df <- final_long_df |>
-  filter(commit_type == "wikimedia_commit_count")
-wikimedia_share_lmer <- lmer(commit_share ~ before_after*relative_week +
-                               (1| rd_event),
-                  data=wikimedia_long_df)
-summary(wikimedia_share_lmer)
-icc(wikimedia_share_lmer)
+  filter(commit_type == "wikimedia_commit_count")|>
+  drop_na()
+
+wikimedia_share_lm <- lm(commit_share ~ before_after*relative_week,
+                         data=wikimedia_long_df)
+summary(wikimedia_share_lm)
+qqnorm(residuals(wikimedia_share_lm))
+
+texreg(wikimedia_share_lm)
 
 other_long_df <- final_long_df |>
-  filter(commit_type == "other_commit_count")
-other_share_lmer <- lmer(commit_share ~ before_after*relative_week +
-                         (1| rd_event),
-                           data=other_long_df)
-summary(other_share_lmer)
-icc(other_share_lmer)
+  filter(commit_type == "other_commit_count") |>
+  drop_na()
+#other_share_lmer <- lmer(commit_share ~ before_after*relative_week +
+#                         (1| rd_event),
+#                           data=other_long_df)
+other_share_lm <- lm(commit_share ~ before_after*relative_week, 
+                     data=other_long_df)
+summary(other_share_lm)
+qqnorm(residuals(other_share_lm))
+
+texreg(other_share_lm)
 
 #power analysis 
 #library(simr)

commit_analysis/testing-share-plotting.R

@@ -11,6 +11,7 @@ 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 <- event_df
 
 input_df <- input_df |>
   mutate(nonbot_commit_count = commit_count - bot_commit_count)|>
@@ -30,42 +31,52 @@ intermediate_long_df <- long_df |>
   mutate(log_commits = log1p(lengthened_commit_count))|>
   mutate(scaled_long_commits = lengthened_commit_count / 10) 
 
-intermediate_long_df <- intermediate_long_df |>
-  drop_na()
 
 window_num <- 4
 final_long_df <- intermediate_long_df |>
   filter(relative_week >= (- window_num) & relative_week <= (window_num)) 
 
+affiliationColors <-
+  setNames( c('#5da2d8', '#c7756a')
+            ,c("other_commit_count", "wikimedia_commit_count"))
+
+
 commit_plot <- final_long_df |>
   ggplot(aes(x=relative_week, 
               y=lengthened_commit_count, 
-              color=commit_type,
+              color=factor(commit_type),
               linetype = rd_event)) +
   geom_line() +
   geom_point() + 
   labs(x = "Relative Week", y = "Nonbot Commits", linetype = "Testing Event", color="Commit Author Affiliation") +
+  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)")) + 
-  scale_color_discrete(labels = c("Unaffiliated", "Organizationally Affiliated")) +
   ggtitle("VisualEditor Nonbot Commit Count Around Opt-In Testing Events (by Affiliation)") +
   theme_bw() + 
   theme(legend.position = "top")
 commit_plot
 
 total_commit_plot <- final_long_df |>
-  filter(commit_type == "other_commit_count")|>
   ggplot(aes(x=relative_week, 
              y=nonbot_commit_count, 
              linetype = rd_event)) +
   geom_line() +
   geom_point() + 
+  geom_vline(xintercept = 0, linetype = "dotted", color = "black") +
   labs(x = "Relative Week", y = "Nonbot Commit Count", linetype = "Testing Event") +
   scale_linetype_discrete(labels = c("enwiki testing (2012-12-12)", "wide testing (2013-04-25)")) + 
-  ggtitle("VisualEditor Nonbot Commit Count Around Opt-In Testing Events") +
+  ggtitle("VisualEditor Weekly Nonbot Commits Surrounding Opt-In Testing Events") +
   theme_bw() + 
   theme(legend.position = "top")
 total_commit_plot
 
+ggsave(filename = "0305-ve-total-commits.png", plot = total_commit_plot, width = 15, height = 9, dpi = 800)
+
+
+final_long_df <- final_long_df|>
+  drop_na()
+
 commit_share_plot <- final_long_df |>
   ggplot(aes(x=relative_week, 
              y=commit_share, 
@@ -74,9 +85,12 @@ commit_share_plot <- final_long_df |>
   geom_line() +
   geom_point() + 
   labs(x = "Relative Week", y = "Share of Nonbot Commits", linetype = "Testing Event", color="Commit Author Affiliation") +
+  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)")) + 
-  scale_color_discrete(labels = c("Unaffiliated", "Organizationally Affiliated")) +
-  ggtitle("VisualEditor Nonbot Commit Share Around Opt-In Testing Events") +
+  ggtitle("Share of Weekly VisualEditor Commits Surrounding Opt-in Testing Events") +
   theme_bw() + 
   theme(legend.position = "top")
 commit_share_plot
+
+ggsave(filename = "0305-ve-testing-share.png", plot = commit_share_plot, width = 12, height = 9, dpi = 800)

mgaughan-rstudio-server_24539959.out

@@ -0,0 +1,17 @@
+1. SSH tunnel from your workstation using the following command:
+
+   ssh -N -L 8787:n3439:56597 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: wO04FrVKQP5bSLRuzEi5
+
+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 24539959

text_analysis/phab_topic_trends.R

@@ -72,7 +72,7 @@ grouped_results <- results |>
 
 plot <- grouped_results |>
   ggplot(aes(x=week,
-             y=X5, 
+             y=X1, 
              color=affil)) +
   geom_line()
 plot