ENH BaseLabelPropagation to accept sparse matrices (#19664)

cozek · Kaushik Amar Das · glemaitre · web-flow · commit 05c0e088c6bd · 2023-02-07T22:04:48.000-05:00
Co-authored-by: Kaushik Amar Das &lt;kaushik.amar.das@accenture.com&gt;
Co-authored-by: Guillaume Lemaitre &lt;g.lemaitre58@gmail.com&gt;
diff --git a/doc/whats_new/v1.3.rst b/doc/whats_new/v1.3.rst
@@ -214,6 +214,13 @@ Changelog
   during `transform` with no prior call to `fit` or `fit_transform`.
   :pr:`25190` by :user:`Vincent Maladière <Vincent-Maladiere>`.
 
+:mod:`sklearn.semi_supervised`
+..............................
+
+- |Enhancement| :meth:`LabelSpreading.fit` and :meth:`LabelPropagation.fit` now
+  accepts sparse metrics.
+  :pr:`19664` by :user:`Kaushik Amar Das <cozek>`.
+
 Code and Documentation Contributors
 -----------------------------------
 
diff --git a/sklearn/semi_supervised/_label_propagation.py b/sklearn/semi_supervised/_label_propagation.py
@@ -241,7 +241,7 @@ def fit(self, X, y):
 
         Parameters
         ----------
-        X : array-like of shape (n_samples, n_features)
+        X : {array-like, sparse matrix} of shape (n_samples, n_features)
             Training data, where `n_samples` is the number of samples
             and `n_features` is the number of features.
 
@@ -256,7 +256,12 @@ def fit(self, X, y):
             Returns the instance itself.
         """
         self._validate_params()
-        X, y = self._validate_data(X, y)
+        X, y = self._validate_data(
+            X,
+            y,
+            accept_sparse=["csr", "csc"],
+            reset=True,
+        )
         self.X_ = X
         check_classification_targets(y)
 
@@ -365,7 +370,7 @@ class LabelPropagation(BaseLabelPropagation):
 
     Attributes
     ----------
-    X_ : ndarray of shape (n_samples, n_features)
+    X_ : {array-like, sparse matrix} of shape (n_samples, n_features)
         Input array.
 
     classes_ : ndarray of shape (n_classes,)
@@ -463,7 +468,7 @@ def fit(self, X, y):
 
         Parameters
         ----------
-        X : array-like of shape (n_samples, n_features)
+        X : {array-like, sparse matrix} of shape (n_samples, n_features)
             Training data, where `n_samples` is the number of samples
             and `n_features` is the number of features.
 
diff --git a/sklearn/semi_supervised/tests/test_label_propagation.py b/sklearn/semi_supervised/tests/test_label_propagation.py
@@ -15,6 +15,9 @@
     assert_allclose,
     assert_array_equal,
 )
+from sklearn.utils._testing import _convert_container
+
+CONSTRUCTOR_TYPES = ("array", "sparse_csr", "sparse_csc")
 
 ESTIMATORS = [
     (label_propagation.LabelPropagation, {"kernel": "rbf"}),
@@ -122,9 +125,27 @@ def test_label_propagation_closed_form(global_dtype):
     assert_allclose(expected, clf.label_distributions_, atol=1e-4)
 
 
-def test_convergence_speed():
+@pytest.mark.parametrize("accepted_sparse_type", ["sparse_csr", "sparse_csc"])
+@pytest.mark.parametrize("index_dtype", [np.int32, np.int64])
+@pytest.mark.parametrize("dtype", [np.float32, np.float64])
+@pytest.mark.parametrize("Estimator, parameters", ESTIMATORS)
+def test_sparse_input_types(
+    accepted_sparse_type, index_dtype, dtype, Estimator, parameters
+):
+    # This is non-regression test for #17085
+    X = _convert_container([[1.0, 0.0], [0.0, 2.0], [1.0, 3.0]], accepted_sparse_type)
+    X.data = X.data.astype(dtype, copy=False)
+    X.indices = X.indices.astype(index_dtype, copy=False)
+    X.indptr = X.indptr.astype(index_dtype, copy=False)
+    labels = [0, 1, -1]
+    clf = Estimator(**parameters).fit(X, labels)
+    assert_array_equal(clf.predict([[0.5, 2.5]]), np.array([1]))
+
+
+@pytest.mark.parametrize("constructor_type", CONSTRUCTOR_TYPES)
+def test_convergence_speed(constructor_type):
     # This is a non-regression test for #5774
-    X = np.array([[1.0, 0.0], [0.0, 1.0], [1.0, 2.5]])
+    X = _convert_container([[1.0, 0.0], [0.0, 1.0], [1.0, 2.5]], constructor_type)
     y = np.array([0, 1, -1])
     mdl = label_propagation.LabelSpreading(kernel="rbf", max_iter=5000)
     mdl.fit(X, y)
