updating with new heatmap for FOSSY presentation

mgaughan-rstudio-server_27817681.out

@@ -1,17 +1,17 @@
 1. SSH tunnel from your workstation using the following command:
 
-   ssh -N -L 8787:n3439:41317 mjilg@klone.hyak.uw.edu
+   ssh -N -L 8787:n3441:48367 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: yo0riOVPbQWPzplKhedd
+   password: WYkG3aRTe0NQjsw3Ayg6
 
 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 27815770
+      scancel -f 27817681

p2/quest/neurobiber_cosine.R

@@ -9,8 +9,18 @@ neurobiber_df$normalized_features_vec <- lapply(
   asplit(neurobiber_df[, normalized_cols], 1), as.numeric
 )
 library(dplyr)
+# duplicate, declined, invalid -> declined 
+# stalled, open, progress -> open
+# resolved -> resolved
 neurobiber_df <- neurobiber_df |>
-  filter(comment_type == "task_description")
+  filter(comment_type == "task_description") |>
+  mutate(
+    task_status = case_when(
+      status %in% c("duplicate", "declined", "invalid") ~ "declined",
+      status %in% c("stalled", "open", "progress") ~ "open",
+      status == "resolved" ~ "resolved",
+      TRUE ~ status  # fallback for unexpected values
+    ))
 
 X <- do.call(rbind, neurobiber_df$normalized_features_vec)
 
@@ -20,34 +30,31 @@ library(coop)
 register_means <- aggregate(
   X,
   by = list(
-    affiliation = neurobiber_df$AuthorWMFAffil,
-    outcome= neurobiber_df$status
+    priority = neurobiber_df$priority,
+    outcome= neurobiber_df$task_status,
+    phase = neurobiber_df$phase,
+    source = neurobiber_df$source,
+    affiliation = neurobiber_df$AuthorWMFAffil
   ),
   FUN = mean
 )
 
-feature_mat <- as.matrix(register_means[, -(1:2)])  
+feature_mat <- as.matrix(register_means[, -(1:5)])  
 cos_sim_matrix <- coop::cosine(t(feature_mat))
-rownames(cos_sim_matrix) <- apply(register_means[, 1:2], 1, paste, collapse = "_")
+rownames(cos_sim_matrix) <- apply(register_means[, 1:5], 1, paste, collapse = "_")
 colnames(cos_sim_matrix) <- rownames(cos_sim_matrix)
 
 
 scaled_mat <- scale(cos_sim_matrix)
 #pheatmap(scaled_mat, symm = TRUE)
 #heatmap(cos_sim_matrix, col=heat.colors(256), breaks=seq(-1, 1, length.out=257))
+library(viridis)
 library(pheatmap)
 pheatmap(cos_sim_matrix, 
-         register_rows = FALSE,    # Now features are clustered (rows)
-         register_cols = FALSE,
-         scale='none')         # Standardize featu
-
-library(reshape2)
-library(ggplot2)
-sim_df <- melt(cos_sim_matrix, na.rm = TRUE)
-ggplot(sim_df, aes(Var1, Var2, fill = value)) +
-  geom_tile() +
-  scale_fill_gradient2(low = "white", high = "red", mid = "blue", midpoint = 0.5, limit = c(0,1)) +
-  theme(axis.text.x = element_text(angle = 90, hjust = 1))
+         cluster_rows = FALSE,    # Now features are clustered (rows)
+         cluster_cols = FALSE,
+         scale='none',
+         color = viridis(100))         # Standardize featu
 
 diag(cos_sim_matrix) <- NA
 which(cos_sim_matrix == max(cos_sim_matrix, na.rm = TRUE), arr.ind = TRUE)  # Most similar