hdbscan_density_clustering_with_synthetic_blob_data.py

1import hdbscan
2from sklearn.datasets import make_blobs
3
4# Generate sample data
5data, _ = make_blobs(n_samples=200, centers=3, cluster_std=0.5, random_state=0)
6
7# Initialize the HDBSCAN clusterer
8clusterer = hdbscan.HDBSCAN(min_cluster_size=5, gen_min_span_tree=True)
9
10# Fit the model and predict clusters
11cluster_labels = clusterer.fit_predict(data)
12
13# Print the resulting labels (-1 indicates noise)
14print(cluster_labels)