Fix prediction data not honoring cluster_selection_epsilon

Author: n9Mtq4

hdbscan/_hdbscan_tree.pyx

@@ -705,6 +705,9 @@ cpdef tuple get_clusters(np.ndarray tree, dict stability,
 
  stabilities : ndarray (n_clusters,)
  The cluster coherence strengths of each cluster.
+ 
+ selected clusters : ndarray (n_clusters,)
+ The ids of the selected clusters
  """
  cdef list node_list
  cdef np.ndarray cluster_tree
@@ -803,4 +806,4 @@ cpdef tuple get_clusters(np.ndarray tree, dict stability,
  probs = get_probabilities(tree, reverse_cluster_map, labels)
  stabilities = get_stability_scores(labels, clusters, stability, max_lambda)
 
- return (labels, probs, stabilities)
+ return (labels, probs, stabilities, np.array(sorted(clusters)))

hdbscan/flat.py

@@ -184,7 +184,8 @@ def HDBSCAN_flat(X, n_clusters=None,
  new_clusterer.probabilities_,
  new_clusterer.cluster_persistence_,
  new_clusterer._condensed_tree,
- new_clusterer._single_linkage_tree) = output
+ new_clusterer._single_linkage_tree,
+ new_clusterer._selected_clusters) = output
 
  # PredictionData attached to HDBSCAN should also change.
  # A function re_init is defined in this module to handle this.

hdbscan/hdbscan_.py

@@ -62,7 +62,7 @@ def _tree_to_labels(
  """
  condensed_tree = condense_tree(single_linkage_tree, min_cluster_size)
  stability_dict = compute_stability(condensed_tree)
- labels, probabilities, stabilities = get_clusters(
+ labels, probabilities, stabilities, selected_clusters = get_clusters(
  condensed_tree,
  stability_dict,
  cluster_selection_method,
@@ -72,7 +72,8 @@ def _tree_to_labels(
  max_cluster_size,
  )
 
- return (labels, probabilities, stabilities, condensed_tree, single_linkage_tree)
+ return (labels, probabilities, stabilities, condensed_tree, single_linkage_tree,
+ selected_clusters)
 
 
 def _hdbscan_generic(
@@ -1130,6 +1131,7 @@ def __init__(
  self._outlier_scores = None
  self._prediction_data = None
  self._relative_validity = None
+ self._selected_clusters = None
 
  def fit(self, X, y=None):
  """Perform HDBSCAN clustering from features or distance matrix.
@@ -1186,6 +1188,7 @@ def fit(self, X, y=None):
  self.cluster_persistence_,
  self._condensed_tree,
  self._single_linkage_tree,
+ self._selected_clusters,
  self._min_spanning_tree,
  ) = hdbscan(clean_data, **kwargs)
 
@@ -1248,6 +1251,7 @@ def generate_prediction_data(self):
  self._prediction_data = PredictionData(
  self._raw_data,
  self.condensed_tree_,
+ self._selected_clusters,
  min_samples,
  tree_type=tree_type,
  metric=self.metric,

hdbscan/prediction.py

@@ -95,15 +95,14 @@ def _recurse_leaf_dfs(self, current_node):
  return sum(
  [recurse_leaf_dfs(self.cluster_tree, child) for child in children], [])
 
- def __init__(self, data, condensed_tree, min_samples,
+ def __init__(self, data, condensed_tree, selected_clusters, min_samples,
  tree_type='kdtree', metric='euclidean', **kwargs):
  self.raw_data = data.astype(np.float64)
  self.tree = self._tree_type_map[tree_type](self.raw_data,
  metric=metric, **kwargs)
  self.core_distances = self.tree.query(data, k=min_samples)[0][:, -1]
  self.dist_metric = DistanceMetric.get_metric(metric, **kwargs)
 
- selected_clusters = sorted(condensed_tree._select_clusters())
  # raw_condensed_tree = condensed_tree.to_numpy()
  raw_condensed_tree = condensed_tree._raw_tree