TST Check estimator pairwise (#9701)

GKjohns · jnothman · commit de0581aea7fa · 2017-11-14T09:09:19.000+11:00
diff --git a/doc/whats_new/v0.20.rst b/doc/whats_new/v0.20.rst
@@ -196,3 +196,10 @@ Cluster
 - Deprecate ``pooling_func`` unused parameter in
   :class:`cluster.AgglomerativeClustering`. :issue:`9875` by :user:`Kumar Ashutosh
   <thechargedneutron>`.
+
+Changes to estimator checks
+---------------------------
+
+- Allow tests in :func:`estimator_checks.check_estimator` to test functions
+  that accept pairwise data.
+  :issue:`9701` by :user:`Kyle Johnson <gkjohns>`
diff --git a/sklearn/base.py b/sklearn/base.py
@@ -551,7 +551,6 @@ def is_classifier(estimator):
 def is_regressor(estimator):
     """Returns True if the given estimator is (probably) a regressor.
 
-
     Parameters
     ----------
     estimator : object
diff --git a/sklearn/neighbors/regression.py b/sklearn/neighbors/regression.py
@@ -9,6 +9,7 @@
 # License: BSD 3 clause (C) INRIA, University of Amsterdam
 
 import numpy as np
+from scipy.sparse import issparse
 
 from .base import _get_weights, _check_weights, NeighborsBase, KNeighborsMixin
 from .base import RadiusNeighborsMixin, SupervisedFloatMixin
@@ -139,6 +140,11 @@ def predict(self, X):
         y : array of int, shape = [n_samples] or [n_samples, n_outputs]
             Target values
         """
+        if issparse(X) and self.metric == 'precomputed':
+            raise ValueError(
+                "Sparse matrices not supported for prediction with "
+                "precomputed kernels. Densify your matrix."
+            )
         X = check_array(X, accept_sparse='csr')
 
         neigh_dist, neigh_ind = self.kneighbors(X)
diff --git a/sklearn/neighbors/tests/test_neighbors.py b/sklearn/neighbors/tests/test_neighbors.py
@@ -2,7 +2,7 @@
 
 import numpy as np
 from scipy.sparse import (bsr_matrix, coo_matrix, csc_matrix, csr_matrix,
-                          dok_matrix, lil_matrix)
+                          dok_matrix, lil_matrix, issparse)
 
 from sklearn import metrics
 from sklearn import neighbors, datasets
@@ -731,10 +731,22 @@ def test_kneighbors_regressor_sparse(n_samples=40,
         knn = neighbors.KNeighborsRegressor(n_neighbors=n_neighbors,
                                             algorithm='auto')
         knn.fit(sparsemat(X), y)
+
+        knn_pre = neighbors.KNeighborsRegressor(n_neighbors=n_neighbors,
+                                                metric='precomputed')
+        knn_pre.fit(pairwise_distances(X, metric='euclidean'), y)
+
         for sparsev in SPARSE_OR_DENSE:
             X2 = sparsev(X)
             assert_true(np.mean(knn.predict(X2).round() == y) > 0.95)
 
+            X2_pre = sparsev(pairwise_distances(X, metric='euclidean'))
+            if issparse(sparsev(X2_pre)):
+                assert_raises(ValueError, knn_pre.predict, X2_pre)
+            else:
+                assert_true(
+                    np.mean(knn_pre.predict(X2_pre).round() == y) > 0.95)
+
 
 def test_neighbors_iris():
     # Sanity checks on the iris dataset
diff --git a/sklearn/utils/estimator_checks.py b/sklearn/utils/estimator_checks.py
diff --git a/sklearn/utils/tests/test_estimator_checks.py b/sklearn/utils/tests/test_estimator_checks.py
