adding renewed FOSSY heatmap

mgaughan-rstudio-server_27817681.out

@@ -1,17 +0,0 @@
-1. SSH tunnel from your workstation using the following command:
-
-   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: 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 27817681

p2/quest/neurobiber_cosine.R

@@ -27,35 +27,69 @@ X <- do.call(rbind, neurobiber_df$normalized_features_vec)
 library(coop)
 #cos_sim1 <- coop::cosine(t(X))
 
+
 register_means <- aggregate(
   X,
   by = list(
-    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[, -(1:5)])  
+feature_mat <- as.matrix(register_means[, -(1:3)])  
 cos_sim_matrix <- coop::cosine(t(feature_mat))
-rownames(cos_sim_matrix) <- apply(register_means[, 1:5], 1, paste, collapse = "_")
+rownames(cos_sim_matrix) <- apply(register_means[, 1:3], 1, paste, collapse = "_")
 colnames(cos_sim_matrix) <- rownames(cos_sim_matrix)
 
 
-scaled_mat <- scale(cos_sim_matrix)
+annotation_row <- data.frame(
+  affiliation = register_means$affiliation,
+  source = register_means$source
+)
+rownames(annotation_row) <- rownames(cos_sim_matrix)
+
+annotation_col <- data.frame(
+  affiliation = register_means$affiliation,
+  source = register_means$source
+)
+rownames(annotation_col) <- colnames(cos_sim_matrix)
+
+annotation_row <- annotation_row |>
+  mutate(affil = case_when(
+       affiliation == "True" ~ "WMF",
+       affiliation == "False" ~ "non-WMF" 
+  )) |> select(-affiliation)
+
+annotation_col <- annotation_col |>
+  mutate(affil = case_when(
+    affiliation == "True" ~ "WMF",
+    affiliation == "False" ~ "non-WMF" 
+  )) |> select(-affiliation)
+  
+
+my_annotation_colors = list(
+  affil = c("WMF" = "green", "non-WMF" = "purple"),
+  source = c(c1 = "lightgrey", c2 = "grey", c3 = "black")
+)
+
+cos_sim_matrix[lower.tri(cos_sim_matrix)] <- NA
 #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, 
-         cluster_rows = FALSE,    # Now features are clustered (rows)
-         cluster_cols = FALSE,
-         scale='none',
-         color = viridis(100))         # Standardize featu
+fossy_heatmap <- pheatmap(cos_sim_matrix,
+           cluster_rows = FALSE,    
+           cluster_cols = FALSE,
+           scale='none', 
+           annotation_row = annotation_row,
+           annotation_col = annotation_col,
+           annotation_colors = my_annotation_colors,
+           na_col = "white")         
 
-diag(cos_sim_matrix) <- NA
-which(cos_sim_matrix == max(cos_sim_matrix, na.rm = TRUE), arr.ind = TRUE)  # Most similar
-which(cos_sim_matrix == min(cos_sim_matrix, na.rm = TRUE), arr.ind = TRUE)  # Least similar
+ggsave(filename = "073125_FOSSY_comm_heatmap.png", plot = fossy_heatmap, width = 9, height = 9, dpi = 800)
+
+#diag(cos_sim_matrix) <- NA
+#which(cos_sim_matrix == max(cos_sim_matrix, na.rm = TRUE), arr.ind = TRUE)  # Most similar
+#which(cos_sim_matrix == min(cos_sim_matrix, na.rm = TRUE), arr.ind = TRUE)  # Least similar