updating plots for results

dsl/121625_final_dsl.R

@@ -93,9 +93,11 @@ dsl_coefs <- ggplot(coef_df, aes(x = estimate, y = term)) +
   theme_minimal()
 dsl_coefs
 ggsave(
-  filename = "121625_dsl_coefs.png",
+  filename = "011125_dsl_coefs.png",
   plot = dsl_coefs,
   width = 6,    # inches
-  height = 6,   # inches
+  height = 4,   # inches
   dpi = 800     # high resolution
 )
+library(texreg)
+texreg(dev_model)

dsl/dsl.R

@@ -156,4 +156,3 @@ ggsave(
   dpi = 800     # high resolution
 )
 
-library(texreg)

mgaughan-rstudio-server_32251441.out

@@ -1,17 +0,0 @@
-1. SSH tunnel from your workstation using the following command:
-
-   ssh -N -L 8787:n3443:42777 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: u+Vtuz9i8I2EYxQXIDps
-
-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 32251441

p2/quest/neurobiber_PCA_analysis.R

@@ -5,6 +5,9 @@ main_csv <- "~/analysis_data/121625_unified.csv"
 main_df <- read.csv(main_csv  , header = TRUE)
 length(unique(main_df$id))
 
+main_df <- main_df |>
+  mutate(isTaskAuthor = task_desc_author == AuthorPHID)
+
 preprocess_comment <- function(message) {
   library(stringr)
   comment_text <- message
@@ -55,11 +58,13 @@ comments_style <- main_df |>
       fill = comment_type
     )
   ) + 
-  facet_grid(~source, scales="fixed",
+  facet_grid(~source + isTaskAuthor, scales="fixed",
              labeller = as_labeller(c(
                "c1" = "VisualEditor",
                "c2"   = "HTTPS-login",
-               "c3"  = "HTTP-deprecation"
+               "c3"  = "HTTP-deprecation",
+               "FALSE" = "Not Task Author",
+               "TRUE" = "Task Author"
              ))) +
   geom_point(shape = 21, alpha=0.3, size=2) +
   xlim(-50, 50) + 
@@ -74,16 +79,18 @@ comments_style <- main_df |>
     x = "Lengthy Discussion v. Brief Updates (PC1)",
     y = "Technical Jargon v. Non-technical Observations (PC4)",
   )
+comments_style
 ggsave(
-  filename = "121625_comments_style.png",
+  filename = "011125_comments_style.png",
   plot = comments_style,
-  width = 12,    # inches
-  height = 8,   # inches
+  width = 10,    # inches
+  height = 5,   # inches
   dpi = 800     # high resolution
 )
 
 adac_style <- main_df |>
   filter(ADAC == 1) |>
+  mutate(isAuthorWMF = factor(isAuthorWMF, levels = c("FALSE", "BzImport", "TRUE")))|>
   ggplot(
     aes(
       x = PC3,
@@ -102,19 +109,24 @@ adac_style <- main_df |>
   geom_point(shape = 21, alpha=0.3, size=2) +
   xlim(-50, 50) + 
   ylim(-50, 50) +
-  scale_fill_viridis_d()+
+    scale_fill_viridis_d(
+      breaks = c("FALSE", "TRUE", "BzImport"),    
+      labels = c("Nonaffiliate", "WMF-affiliate", "BzImport")  
+    ) + 
   theme_minimal() +
   theme(legend.position = "top") +
   labs(
     x = "Expressive, first-person v. Dry, third-person (PC3)",
     y = "Technical Jargon v. Non-technical Observations (PC4)",
+    fill = "Task Author"
   )
+adac_style
 #"PCs for Pre-Resolution Comments Written by Task Author (by Author Affiliation, Case, and Comment Type)"
 ggsave(
-  filename = "121625_adac_affil_style.png",
+  filename = "011125_adac_affil_style.png",
   plot = adac_style,
-  width = 12,    # inches
-  height = 8,   # inches
+  width = 10,    # inches
+  height = 5,   # inches
   dpi = 800     # high resolution
 )