148 lines
4.6 KiB
R
148 lines
4.6 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$normalized_features_vec <- lapply(
|
|
asplit(neurobiber_df[, normalized_cols], 1), as.numeric
|
|
)
|
|
library(dplyr)
|
|
# duplicate, declined, invalid -> declined
|
|
# stalled, open, progress -> open
|
|
# resolved -> resolved
|
|
neurobiber_df <- neurobiber_df |>
|
|
filter(comment_type == "task_description") |>
|
|
mutate(
|
|
task_status = case_when(
|
|
status %in% c("duplicate", "declined", "invalid") ~ "declined",
|
|
status %in% c("stalled", "open", "progress") ~ "open",
|
|
status == "resolved" ~ "resolved",
|
|
TRUE ~ status # fallback for unexpected values
|
|
))
|
|
|
|
X <- do.call(rbind, neurobiber_df$normalized_features_vec)
|
|
|
|
library(coop)
|
|
#cos_sim1 <- coop::cosine(t(X))
|
|
|
|
|
|
register_means <- aggregate(
|
|
X,
|
|
by = list(
|
|
outcome= neurobiber_df$task_status,
|
|
source = neurobiber_df$source,
|
|
affiliation = neurobiber_df$AuthorWMFAffil
|
|
),
|
|
FUN = mean
|
|
)
|
|
|
|
feature_mat <- as.matrix(register_means[, -(1:3)])
|
|
cos_sim_matrix <- coop::cosine(t(feature_mat))
|
|
rownames(cos_sim_matrix) <- apply(register_means[, 1:3], 1, paste, collapse = "_")
|
|
colnames(cos_sim_matrix) <- rownames(cos_sim_matrix)
|
|
|
|
#finding the most dissimilar pairs
|
|
|
|
compare_feature_vectors <- function(
|
|
pair1, pair2,
|
|
cos_sim_matrix,
|
|
feature_mat,
|
|
normalized_cols,
|
|
top_n = 5
|
|
) {
|
|
# Allow for both index and name input
|
|
if (is.character(pair1)) row_idx <- which(rownames(cos_sim_matrix) == pair1) else row_idx <- pair1
|
|
if (is.character(pair2)) col_idx <- which(colnames(cos_sim_matrix) == pair2) else col_idx <- pair2
|
|
|
|
# Get feature vectors
|
|
vec1 <- feature_mat[row_idx, ]
|
|
vec2 <- feature_mat[col_idx, ]
|
|
|
|
# Feature-wise absolute differences
|
|
feature_diff <- abs(vec1 - vec2)
|
|
top_features_idx <- order(feature_diff, decreasing = TRUE)[1:top_n]
|
|
top_features <- names(feature_diff)[top_features_idx]
|
|
top_diffs <- feature_diff[top_features_idx]
|
|
|
|
# Map Vxx to normalized column names
|
|
feature_nums <- as.integer(sub("V", "", top_features))
|
|
feature_colnames <- normalized_cols[feature_nums]
|
|
|
|
# Determine which vector is larger for each feature
|
|
larger_in <- ifelse(vec1[top_features_idx] > vec2[top_features_idx],
|
|
rownames(cos_sim_matrix)[row_idx],
|
|
colnames(cos_sim_matrix)[col_idx])
|
|
|
|
# Assemble results
|
|
top_features_df <- data.frame(
|
|
feature = top_features,
|
|
normalized_colname = feature_colnames,
|
|
vec1_value = vec1[top_features_idx],
|
|
vec2_value = vec2[top_features_idx],
|
|
abs_difference = top_diffs,
|
|
larger_in = larger_in
|
|
)
|
|
|
|
# Print pair and return
|
|
cat("Comparing:", rownames(cos_sim_matrix)[row_idx], "and", colnames(cos_sim_matrix)[col_idx], "\n")
|
|
print(top_features_df)
|
|
invisible(top_features_df)
|
|
}
|
|
|
|
compare_feature_vectors("resolved_c1_True", "resolved_c2_True", cos_sim_matrix, feature_mat, normalized_cols, top_n = 10)
|
|
|
|
|
|
|
|
#plotting stuff beneath here
|
|
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)
|
|
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")
|
|
|
|
#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
|