DOC Added information about space complexity to docs DBSCAN (scikit-learn#26783)

StefanieSenger · glemaitre · web-flow · commit 889b8290c5ea · 2023-07-20T23:06:03.000Z
Co-authored-by: Guillaume Lemaitre &lt;g.lemaitre58@gmail.com&gt;
diff --git a/sklearn/cluster/_dbscan.py b/sklearn/cluster/_dbscan.py
@@ -172,6 +172,9 @@ class DBSCAN(ClusterMixin, BaseEstimator):
     Finds core samples of high density and expands clusters from them.
     Good for data which contains clusters of similar density.
 
+    The worst case memory complexity of DBSCAN is :math:`O({n}^2)`, which can
+    occur when the `eps` param is large and `min_samples` is low.
+
     Read more in the :ref:`User Guide <dbscan>`.
 
     Parameters
@@ -184,8 +187,11 @@ class DBSCAN(ClusterMixin, BaseEstimator):
         and distance function.
 
     min_samples : int, default=5
-        The number of samples (or total weight) in a neighborhood for a point
-        to be considered as a core point. This includes the point itself.
+        The number of samples (or total weight) in a neighborhood for a point to
+        be considered as a core point. This includes the point itself. If
+        `min_samples` is set to a higher value, DBSCAN will find denser clusters,
+        whereas if it is set to a lower value, the found clusters will be more
+        sparse.
 
     metric : str, or callable, default='euclidean'
         The metric to use when calculating distance between instances in a
