updating with some plots for new results, results updated with new work

analysis_data/scratch.R

@@ -1,5 +1,5 @@
 library(tidyverse)
-main_csv <-"~/analysis_data/120725_unified.csv"
+main_csv <-"~/analysis_data/121625_unified.csv"
 main_df <- read.csv(main_csv, header = TRUE) 
 
 bz_summary <- main_df |>
@@ -11,23 +11,6 @@ bz_summary <- main_df |>
   
   
 
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-dsl_csv <-"~/dsl/120725_DSL_frame.csv"
-dsl_df <- read.csv(dsl_csv, header = TRUE) 
-
 needs_triage <- dsl_df |>
   filter(week_index >= -4) |>
   filter(priority=="Needs Triage") |>

dsl/121625_final_dsl.R

@@ -24,6 +24,7 @@ dev_model <- dsl(
 summary(dev_model)
 #saveRDS(dev_model, "121625_logit_dsl.RDS")
 dev_model <- readRDS("dsl/121625_logit_dsl.RDS")
+summary(dev_model)
 library(broom)
 library(dplyr)
 tidy.dsl <- function(x, conf.int = FALSE, conf.level = 0.95, exponentiate = FALSE, ...) {

dsl/final_bivariate.R

@@ -1,7 +1,7 @@
 library(tidyverse)
 #library(dsl)
 library(dplyr)
-dsl_csv <-"~/dsl/120725_DSL_frame.csv"
+dsl_csv <-"~/dsl/121625_DSL_frame.csv"
 dsl_df <- read.csv(dsl_csv, header = TRUE) 
 
 dsl_df <- dsl_df |>
@@ -74,7 +74,7 @@ c1_ttr_plot <- dsl_df |>
   ggplot(
     aes(
       x=as.factor(week_index),
-      y= TTR/168, 
+      y= TTR_hours/168, 
       fill=priority
     )
   ) + 
@@ -97,11 +97,11 @@ c1_ttr_plot <- dsl_df |>
   theme(legend.position = "top")
 c1_ttr_plot
 ggsave(
-  filename = "120825_c1_ttr.png",
+  filename = "121625_c1_ttr.png",
   plot = c1_ttr_plot,
-  width = 12,    # inches
+  width = 8,    # inches
   height = 6,   # inches
-  dpi = 600     # high resolution
+  dpi = 800     # high resolution
 )
 
 dsl_df_long <- dsl_df %>%
@@ -148,7 +148,8 @@ weekly_summary <- dsl_df |>
     median_olmo_TSOL_prop_adac = median(olmo_TSOL_prop_adac),
     median_olmo_RK_prop_adac = median(olmo_RK_prop_adac),
     median_comments_before_resolution = median(n_comments_before)
-  )
+  ) |>
+  mutate(isAuthorWMF = factor(isAuthorWMF, levels = c("FALSE", "BzImport", "TRUE")))
 
 tasks_created <- ggplot(
   weekly_summary,
@@ -199,20 +200,23 @@ tasks_created <- ggplot(
     aes(x=week_index, y=20, label='Deployment Announcement'),
     size = 2.5) + 
   theme_minimal() + 
-  scale_fill_viridis_d() + 
+  scale_fill_viridis_d(
+    breaks = c("FALSE", "TRUE", "BzImport"),    
+    labels = c("Nonaffiliate", "WMF-affiliate", "BzImport")  
+  ) + 
   labs(
     x = "Weeks from Feature Deployment", 
     y = "Count of Tasks Created", 
-    fill = "Task Author Affiliated with WMF?"
+    fill = "Task Author"
   ) + 
   theme(legend.position = "top")
 tasks_created
 ggsave(
-  filename = "120825_tasks_created.png",
+  filename = "121625_tasks_created.png",
   plot = tasks_created,
   width = 12,    # inches
   height = 6,   # inches
-  dpi = 600     # high resolution
+  dpi = 800     # high resolution
 )
 
 outcome_summary <- dsl_df |>

dsl/rq1_plots.R

@@ -1,7 +1,7 @@
 library(tidyverse)
 #library(dsl)
 library(dplyr)
-dsl_csv <-"~/dsl/126725_DSL_frame.csv"
+dsl_csv <-"~/dsl/121625_DSL_frame.csv"
 dsl_df <- read.csv(dsl_csv, header = TRUE) 
 
 dsl_df <- dsl_df |>
@@ -73,14 +73,14 @@ dsl_df |>
 
 # % of tasks declined per week 
 declined_summary <- dsl_df %>%
-  group_by(week_index, task_status, source) %>%
+  group_by(week_index, status, source) %>%
   summarise(count = n(), .groups = 'drop') |>
   group_by(week_index, source) %>%
   mutate(proportion = count / sum(count)) %>%
   ungroup()
 
 task_status_plot <- declined_summary|>
-  ggplot(aes(x = week_index, y = proportion, fill=task_status,)) +
+  ggplot(aes(x = week_index, y = proportion, fill=status,)) +
   facet_grid(source ~ ., 
              scales = "free_y",
              labeller = labeller(source = c("c1" = "VisualEditor", 
@@ -98,12 +98,13 @@ task_status_plot <- declined_summary|>
     size = 2.5) +
   theme_minimal() + 
   theme(legend.position = "top")
+task_status_plot
 ggsave(
-  filename = "120825_tasks_status.png",
+  filename = "121625_tasks_status.png",
   plot = task_status_plot,
   width = 12,    # inches
   height = 6,   # inches
-  dpi = 600     # high resolution
+  dpi = 800     # high resolution
 )
 
 

dsl/scratch.R

@@ -0,0 +1,24 @@
+library(tidyverse)
+
+dsl_csv <-"~/dsl/121625_DSL_frame.csv"
+dsl_df <- read.csv(dsl_csv, header = TRUE) 
+
+dsl_df |>
+  filter(week_index >= 4)|>
+  filter(source == "c1") |>
+  filter(priority == "Needs Triage")|>
+  mutate(ttr_weeks = TTR_hours / 168) |>
+  group_by(isAuthorWMF) |>
+  summarise(
+    mean_ttr = mean(ttr_weeks, na.rm = TRUE),
+    sd_ttr = sd(ttr_weeks, na.rm = TRUE)
+  )
+
+triage <- dsl_df |>
+  group_by(source, isAuthorWMF, priority)|>
+  summarise(
+    count = n()
+  )
+
+
+

mgaughan-rstudio-server_31867859.out

@@ -0,0 +1,17 @@
+1. SSH tunnel from your workstation using the following command:
+
+   ssh -N -L 8787:n3441:34063 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: mGALb8Ae1rRJIi4jmNUf
+
+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 31867859