Merge pull request scikit-learn#2 from jjerphan/pairwise_aggregation_…

…cython-oop ParallelReduction class hierarchy (POC for scikit-learn#20254)
mbatoul · Jul 1, 2021 · 3cdc476 · 3cdc476
2 parents cac7313 + ad496f0
commit 3cdc476
Show file tree

Hide file tree

Showing 23 changed files with 958 additions and 626 deletions.
diff --git a/sklearn/cluster/_agglomerative.py b/sklearn/cluster/_agglomerative.py
@@ -16,8 +16,8 @@
 
 from ..base import BaseEstimator, ClusterMixin
 from ..metrics.pairwise import paired_distances, pairwise_distances
-from ..neighbors import DistanceMetric
-from ..neighbors._dist_metrics import METRIC_MAPPING
+from ..metrics import DistanceMetric
+from ..metrics._dist_metrics import METRIC_MAPPING
 from ..utils import check_array
 from ..utils._fast_dict import IntFloatDict
 from ..utils.fixes import _astype_copy_false

diff --git a/sklearn/cluster/_hierarchical_fast.pyx b/sklearn/cluster/_hierarchical_fast.pyx
@@ -13,7 +13,7 @@ ctypedef np.int8_t INT8
 
 np.import_array()
 
-from ..neighbors._dist_metrics cimport DistanceMetric
+from ..metrics._dist_metrics cimport DistanceMetric
 from ..utils._fast_dict cimport IntFloatDict
 
 # C++
@@ -236,8 +236,8 @@ def max_merge(IntFloatDict a, IntFloatDict b,
 def average_merge(IntFloatDict a, IntFloatDict b,
               np.ndarray[ITYPE_t, ndim=1] mask,
               ITYPE_t n_a, ITYPE_t n_b):
-    """Merge two IntFloatDicts with the average strategy: when the 
-    same key is present in the two dicts, the weighted average of the two 
+    """Merge two IntFloatDicts with the average strategy: when the
+    same key is present in the two dicts, the weighted average of the two
     values is used.
 
     Parameters
@@ -290,13 +290,13 @@ def average_merge(IntFloatDict a, IntFloatDict b,
 
 
 ###############################################################################
-# An edge object for fast comparisons 
+# An edge object for fast comparisons
 
 cdef class WeightedEdge:
     cdef public ITYPE_t a
     cdef public ITYPE_t b
     cdef public DTYPE_t weight
-    
+
     def __init__(self, DTYPE_t weight, ITYPE_t a, ITYPE_t b):
         self.weight = weight
         self.a = a
@@ -326,7 +326,7 @@ cdef class WeightedEdge:
             return self.weight > other.weight
         elif op == 5:
             return self.weight >= other.weight
-        
+
     def __repr__(self):
         return "%s(weight=%f, a=%i, b=%i)" % (self.__class__.__name__,
                                               self.weight,
@@ -475,7 +475,7 @@ def mst_linkage_core(
 
     dist_metric: DistanceMetric
         A DistanceMetric object conforming to the API from
-        ``sklearn.neighbors._dist_metrics.pxd`` that will be
+        ``sklearn.metrics._dist_metrics.pxd`` that will be
         used to compute distances.
 
     Returns
@@ -534,4 +534,3 @@ def mst_linkage_core(
         current_node = new_node
 
     return np.array(result)
-
diff --git a/sklearn/cluster/tests/test_hierarchical.py b/sklearn/cluster/tests/test_hierarchical.py
@@ -16,7 +16,7 @@
 from scipy.cluster import hierarchy
 
 from sklearn.metrics.cluster import adjusted_rand_score
-from sklearn.neighbors.tests.test_dist_metrics import METRICS_DEFAULT_PARAMS
+from sklearn.metrics.tests.test_dist_metrics import METRICS_DEFAULT_PARAMS
 from sklearn.utils._testing import assert_almost_equal, create_memmap_backed_data
 from sklearn.utils._testing import assert_array_almost_equal
 from sklearn.utils._testing import ignore_warnings
@@ -30,14 +30,15 @@
     _fix_connectivity,
 )
 from sklearn.feature_extraction.image import grid_to_graph
+from sklearn.metrics import DistanceMetric
 from sklearn.metrics.pairwise import (
     PAIRED_DISTANCES,
     cosine_distances,
     manhattan_distances,
     pairwise_distances,
 )
 from sklearn.metrics.cluster import normalized_mutual_info_score
-from sklearn.neighbors import kneighbors_graph, DistanceMetric
+from sklearn.neighbors import kneighbors_graph
 from sklearn.cluster._hierarchical_fast import (
     average_merge,
     max_merge,

diff --git a/sklearn/metrics/__init__.py b/sklearn/metrics/__init__.py
@@ -36,6 +36,8 @@
 from ._classification import brier_score_loss
 from ._classification import multilabel_confusion_matrix
 
+from ._dist_metrics import DistanceMetric
+
 from . import cluster
 from .cluster import adjusted_mutual_info_score
 from .cluster import adjusted_rand_score
@@ -113,6 +115,7 @@
     "davies_bouldin_score",
     "DetCurveDisplay",
     "det_curve",
+    "DistanceMetric",
     "euclidean_distances",
     "explained_variance_score",
     "f1_score",