55 lines
1.7 KiB
R
55 lines
1.7 KiB
R
library(tidyverse)
|
|
|
|
neurobiber_csv <-"~/p2/quest/072525_pp_biberplus_labels.csv"
|
|
neurobiber_df <- read.csv(neurobiber_csv , header = TRUE)
|
|
|
|
normalized_cols <- grep("^normalized_", names(neurobiber_df), value = TRUE)
|
|
|
|
neurobiber_df$normalized_features_vec <- lapply(
|
|
asplit(neurobiber_df[, normalized_cols], 1), as.numeric
|
|
)
|
|
library(dplyr)
|
|
neurobiber_df <- neurobiber_df |>
|
|
filter(comment_type == "task_description")
|
|
|
|
X <- do.call(rbind, neurobiber_df$normalized_features_vec)
|
|
|
|
library(coop)
|
|
#cos_sim1 <- coop::cosine(t(X))
|
|
|
|
register_means <- aggregate(
|
|
X,
|
|
by = list(
|
|
affiliation = neurobiber_df$AuthorWMFAffil,
|
|
outcome= neurobiber_df$status
|
|
),
|
|
FUN = mean
|
|
)
|
|
|
|
feature_mat <- as.matrix(register_means[, -(1:2)])
|
|
cos_sim_matrix <- coop::cosine(t(feature_mat))
|
|
rownames(cos_sim_matrix) <- apply(register_means[, 1:2], 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(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))
|
|
|
|
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
|