MAINT dynamically expose kulsinski and remove support in BallTree (sc…

…ikit-learn#25417) Co-authored-by: Loïc Estève <[email protected]> Co-authored-by: Julien Jerphanion <[email protected]> closes scikit-learn#25212
neurodata · Jan 26, 2023 · 8640ed7 · 8640ed7
1 parent b69abf5
commit 8640ed7
Show file tree

Hide file tree

Showing 9 changed files with 62 additions and 33 deletions.
diff --git a/doc/whats_new/v1.3.rst b/doc/whats_new/v1.3.rst
@@ -156,6 +156,13 @@ Changelog
  when the provided `sample_weight` reduces the problem to a single class in `fit`.
  :pr:`24140` by :user:`Jonathan Ohayon <Johayon>` and :user:`Chiara Marmo <cmarmo>`.
 
+:mod:`sklearn.neighbors`
+........................
+
+- |Fix| Remove support for `KulsinskiDistance` in :class:`neighbors.BallTree`. This
+ dissimilarity is not a metric and cannot be supported by the BallTree.
+ :pr:`25417` by :user:`Guillaume Lemaitre <glemaitre>`.
+
 :mod:`sklearn.pipeline`
 .......................
 

diff --git a/sklearn/cluster/_optics.py b/sklearn/cluster/_optics.py
@@ -90,6 +90,9 @@ class OPTICS(ClusterMixin, BaseEstimator):
  See the documentation for scipy.spatial.distance for details on these
  metrics.
 
+ .. note::
+ `'kulsinski'` is deprecated from SciPy 1.9 and will removed in SciPy 1.11.
+
  p : float, default=2
  Parameter for the Minkowski metric from
  :class:`~sklearn.metrics.pairwise_distances`. When p = 1, this is
@@ -489,6 +492,9 @@ def compute_optics_graph(
  See the documentation for scipy.spatial.distance for details on these
  metrics.
 
+ .. note::
+ `'kulsinski'` is deprecated from SciPy 1.9 and will be removed in SciPy 1.11.
+
  p : int, default=2
  Parameter for the Minkowski metric from
  :class:`~sklearn.metrics.pairwise_distances`. When p = 1, this is

diff --git a/sklearn/metrics/_dist_metrics.pyx.tp b/sklearn/metrics/_dist_metrics.pyx.tp
@@ -42,6 +42,7 @@ from ..utils._typedefs cimport DTYPE_t, ITYPE_t, DTYPECODE
 from ..utils._typedefs import DTYPE, ITYPE
 from ..utils._readonly_array_wrapper import ReadonlyArrayWrapper
 from ..utils import check_array
+from ..utils.fixes import parse_version, sp_base_version
 
 cdef inline double fmax(double a, double b) nogil:
  return max(a, b)
@@ -59,12 +60,14 @@ BOOL_METRICS = [
  "matching",
  "jaccard",
  "dice",
- "kulsinski",
  "rogerstanimoto",
  "russellrao",
  "sokalmichener",
  "sokalsneath",
 ]
+if sp_base_version < parse_version("1.11"):
+ # Deprecated in SciPy 1.9 and removed in SciPy 1.11
+ BOOL_METRICS += ["kulsinski"]
 
 def get_valid_metric_ids(L):
  """Given an iterable of metric class names or class identifiers,

diff --git a/sklearn/metrics/pairwise.py b/sklearn/metrics/pairwise.py
@@ -28,7 +28,7 @@
 from ..preprocessing import normalize
 from ..utils._mask import _get_mask
 from ..utils.parallel import delayed, Parallel
-from ..utils.fixes import sp_version, parse_version
+from ..utils.fixes import sp_base_version, sp_version, parse_version
 from ..utils._param_validation import validate_params
 
 from ._pairwise_distances_reduction import ArgKmin
@@ -644,6 +644,9 @@ def pairwise_distances_argmin_min(
  See the documentation for scipy.spatial.distance for details on these
  metrics.
 
+ .. note::
+ `'kulsinski'` is deprecated from SciPy 1.9 and will be removed in SciPy 1.11.
+
  metric_kwargs : dict, default=None
  Keyword arguments to pass to specified metric function.
 
@@ -761,6 +764,9 @@ def pairwise_distances_argmin(X, Y, *, axis=1, metric="euclidean", metric_kwargs
  See the documentation for scipy.spatial.distance for details on these
  metrics.
 
+ .. note::
+ `'kulsinski'` is deprecated from SciPy 1.9 and will be removed in SciPy 1.11.
+
  metric_kwargs : dict, default=None
  Keyword arguments to pass to specified metric function.
 
@@ -1639,7 +1645,6 @@ def _pairwise_callable(X, Y, metric, force_all_finite=True, **kwds):
  "dice",
  "hamming",
  "jaccard",
- "kulsinski",
  "mahalanobis",
  "matching",
  "minkowski",
@@ -1654,6 +1659,9 @@ def _pairwise_callable(X, Y, metric, force_all_finite=True, **kwds):
  "nan_euclidean",
  "haversine",
 ]
+if sp_base_version < parse_version("1.11"):
+ # Deprecated in SciPy 1.9 and removed in SciPy 1.11
+ _VALID_METRICS += ["kulsinski"]
 
 _NAN_METRICS = ["nan_euclidean"]
 
@@ -1908,6 +1916,9 @@ def pairwise_distances(
  See the documentation for scipy.spatial.distance for details on these
  metrics. These metrics do not support sparse matrix inputs.
 
+ .. note::
+ `'kulsinski'` is deprecated from SciPy 1.9 and will be removed in SciPy 1.11.
+
  Note that in the case of 'cityblock', 'cosine' and 'euclidean' (which are
  valid scipy.spatial.distance metrics), the scikit-learn implementation
  will be used, which is faster and has support for sparse matrices (except
@@ -2043,14 +2054,16 @@ def pairwise_distances(
 PAIRWISE_BOOLEAN_FUNCTIONS = [
  "dice",
  "jaccard",
- "kulsinski",
  "matching",
  "rogerstanimoto",
  "russellrao",
  "sokalmichener",
  "sokalsneath",
  "yule",
 ]
+if sp_base_version < parse_version("1.11"):
+ # Deprecated in SciPy 1.9 and removed in SciPy 1.11
+ PAIRWISE_BOOLEAN_FUNCTIONS += ["kulsinski"]
 
 # Helper functions - distance
 PAIRWISE_KERNEL_FUNCTIONS = {

diff --git a/sklearn/metrics/tests/test_pairwise.py b/sklearn/metrics/tests/test_pairwise.py
@@ -226,7 +226,7 @@ def test_pairwise_boolean_distance(metric):
  with ignore_warnings(category=DataConversionWarning):
  for Z in [Y, None]:
  res = pairwise_distances(X, Z, metric=metric)
- res[np.isnan(res)] = 0
+ np.nan_to_num(res, nan=0, posinf=0, neginf=0, copy=False)
  assert np.sum(res != 0) == 0
 
  # non-boolean arrays are converted to boolean for boolean

diff --git a/sklearn/neighbors/_ball_tree.pyx b/sklearn/neighbors/_ball_tree.pyx
@@ -11,7 +11,7 @@ VALID_METRICS = ['EuclideanDistance', 'SEuclideanDistance',
  'MahalanobisDistance', 'HammingDistance',
  'CanberraDistance', 'BrayCurtisDistance',
  'JaccardDistance', 'MatchingDistance',
- 'DiceDistance', 'KulsinskiDistance',
+ 'DiceDistance',
  'RogersTanimotoDistance', 'RussellRaoDistance',
  'SokalMichenerDistance', 'SokalSneathDistance',
  'PyFuncDistance', 'HaversineDistance']

diff --git a/sklearn/neighbors/_base.py b/sklearn/neighbors/_base.py
@@ -38,39 +38,39 @@
 from ..utils.validation import check_non_negative
 from ..utils._param_validation import Interval, StrOptions
 from ..utils.parallel import delayed, Parallel
-from ..utils.fixes import parse_version, sp_version
+from ..utils.fixes import parse_version, sp_base_version, sp_version
 from ..exceptions import DataConversionWarning, EfficiencyWarning
 
+SCIPY_METRICS = [
+ "braycurtis",
+ "canberra",
+ "chebyshev",
+ "correlation",
+ "cosine",
+ "dice",
+ "hamming",
+ "jaccard",
+ "mahalanobis",
+ "matching",
+ "minkowski",
+ "rogerstanimoto",
+ "russellrao",
+ "seuclidean",
+ "sokalmichener",
+ "sokalsneath",
+ "sqeuclidean",
+ "yule",
+]
+if sp_base_version < parse_version("1.11"):
+ # Deprecated in SciPy 1.9 and removed in SciPy 1.11
+ SCIPY_METRICS += ["kulsinski"]
+
 VALID_METRICS = dict(
  ball_tree=BallTree.valid_metrics,
  kd_tree=KDTree.valid_metrics,
  # The following list comes from the
  # sklearn.metrics.pairwise doc string
- brute=sorted(
- set(PAIRWISE_DISTANCE_FUNCTIONS).union(
- [
- "braycurtis",
- "canberra",
- "chebyshev",
- "correlation",
- "cosine",
- "dice",
- "hamming",
- "jaccard",
- "kulsinski",
- "mahalanobis",
- "matching",
- "minkowski",
- "rogerstanimoto",
- "russellrao",
- "seuclidean",
- "sokalmichener",
- "sokalsneath",
- "sqeuclidean",
- "yule",
- ]
- )
- ),
+ brute=sorted(set(PAIRWISE_DISTANCE_FUNCTIONS).union(SCIPY_METRICS)),
 )
 
 # TODO: Remove filterwarnings in 1.3 when wminkowski is removed

diff --git a/sklearn/neighbors/tests/test_ball_tree.py b/sklearn/neighbors/tests/test_ball_tree.py
@@ -30,7 +30,6 @@
  "matching",
  "jaccard",
  "dice",
- "kulsinski",
  "rogerstanimoto",
  "russellrao",
  "sokalmichener",

diff --git a/sklearn/utils/fixes.py b/sklearn/utils/fixes.py
@@ -25,6 +25,7 @@
 
 np_version = parse_version(np.__version__)
 sp_version = parse_version(scipy.__version__)
+sp_base_version = parse_version(sp_version.base_version)
 
 
 if sp_version >= parse_version("1.4"):