Update src/streamlit_app.py

src/streamlit_app.py

@@ -221,7 +221,12 @@ def get_clusters_from_r_matrix(r_matrix):
         # Using default parameters for min_cluster_size and min_samples
         # These might need tuning based on data characteristics and desired cluster granularity
         # allow_single_cluster=True prevents an error if all points form one cluster
-        clusterer = hdbscan.HDBSCAN(metric=hamming_distance_with_nan, allow_single_cluster=True)
+        clusterer = hdbscan.HDBSCAN(
+            metric=hamming_distance_with_nan,
+            allow_single_cluster=True,
+            min_cluster_size=max(int(np.sqrt(len(r_matrix))), 3),
+            min_samples=None,
+        )
 
         # Fit the model directly to the DataFrame values
         # HDBSCAN fit expects a numpy array or similar structure