mgaughan/mw-lifecycle-analysis
1
0
Fork 0
Code

adding in analysis of biberplus vectors

Browse Source
This commit is contained in:
Matthew Gaughan 2025-07-23 14:22:20 -07:00
parent b0584ec1be
commit a08a49d04e
1 changed files with 34 additions and 14 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

48
p2/quest/neurobiber_EDA.R
View File

@ -1,15 +1,16 @@
library(tidyverse)
neurobiber_csv <-"~/p2/quest/071525_neurobiber_labels.csv"
neurobiber_csv <-"~/p2/quest/072325_biberplus_labels.csv"
neurobiber_df <- read.csv(neurobiber_csv , header = TRUE)
neurobiber_df$features_vec <- lapply(neurobiber_df$neurobiber_preds, function(x) {
x <- gsub("\\[|\\]", "", x)
x <- trimws(x)
as.numeric(unlist(strsplit(x, "\\s+")))
})
normalized_cols <- grep("^normalized_", names(neurobiber_df), value = TRUE)
neurobiber_df$normalized_features_vec <- lapply(
asplit(neurobiber_df[, normalized_cols], 1), as.numeric
)
X <- do.call(rbind, neurobiber_df$normalized_features_vec)
X <- do.call(rbind, neurobiber_df$features_vec )
set.seed(808)
@ -37,7 +38,7 @@ neurobiber_df$PC1 <- pca$x[,1]
neurobiber_df$PC2 <- pca$x[,2]
ggplot(neurobiber_df, aes(x = PC1, y = PC2, color = dbcluster)) +
ggplot(neurobiber_df, aes(x = PC1, y = PC2, color = phase)) +
geom_point(size = 2, alpha = 0.7) +
theme_minimal() +
labs(title = "Across-case comment clusters (DBSCAN) by cross-case PCA",
@ -53,9 +54,27 @@ ggplot(neurobiber_df, aes(x = phase, y=dbcluster, fill=AuthorWMFAffil)) +
y = "Neurobiber feature vector cluster (DBSCAN)") +
facet_wrap(~ source)
cluster_means <- aggregate(X, by = list(Cluster = neurobiber_df$dbcluster), FUN = mean)
rownames(cluster_means) <- paste0("Cluster_", cluster_means$Cluster)
cluster_means <- cluster_means[,-1] # Remove cluster label column
cluster_means <- aggregate(
X,
by = list(
WMFAffil = neurobiber_df$AuthorWMFAffil,
phase = neurobiber_df$phase,
comment_type = neurobiber_df$comment_type,
source= neurobiber_df$source
),
FUN = mean
)
rownames(cluster_means) <- apply(
cluster_means[, c("WMFAffil", "phase", "comment_type", "source")], 1,
function(x) paste(x, collapse = "_")
)
cluster_means <- cluster_means[, !(names(cluster_means) %in% c("WMFAffil", "phase", "comment_type", "source"))]
#cluster_means <- aggregate(X, by = list(Cluster = neurobiber_df$AuthorWMFAffil), FUN = mean)
#rownames(cluster_means) <- paste0("Cluster_", cluster_means$Cluster)
#cluster_means <- cluster_means[,-1] # Remove cluster label column
BIBER_FEATURES <- c(
"BIN_QUAN","BIN_QUPR","BIN_AMP","BIN_PASS","BIN_XX0","BIN_JJ",
@ -75,10 +94,11 @@ BIBER_FEATURES <- c(
"BIN_QUES","BIN_QUOT","BIN_AT","BIN_SBJP","BIN_URL","BIN_WH",
"BIN_INDA","BIN_ACCU","BIN_PGAS","BIN_CMADJ","BIN_SPADJ","BIN_X"
)
colnames(cluster_means) <- BIBER_FEATURES
BIBER_FEATURES_NO_BIN <- gsub("^BIN_", "", BIBER_FEATURES)
colnames(cluster_means) <- BIBER_FEATURES_NO_BIN
library(pheatmap)
pheatmap(cluster_means,
cluster_rows = FALSE, # Now features are clustered (rows)
cluster_cols = FALSE, # Clusters (columns) are not clustered
scale = "row") # Standardize features
cluster_cols = FALSE,
scale='none') # Standardize features