scripts.evaluation.cluster_eval

Functions

build_mean_label_vector(model, labels)	Computes the mean vector for each label using the Word2Vec model.
build_word_vectors(labels, ground_truth)	Builds a Word2Vec model from the tokenized labels.
is_word(token)	Checks whether a token is a valid word (not punctuation or too short).
load_cluster_csv(path)	Loads cluster assignments from a CSV file.
load_json(path)	Loads the ground truth JSON file.
main(args)	Main entry point for clustering visualization.
parse_arguments()	Parse command-line arguments and return the parsed arguments.
plot_tsne(label_vectors, clusters, out_path, ...)	Generates and saves a t-SNE scatter plot with cluster coloring and hover text.
tokenize_text(labels, ground_truth)	Tokenizes and lowercases text fields from labels.