ENH Preserving dtype for np.float32 in SparsePCA and MiniBatchSparsePCA (#22111)

Co-authored-by: takoika <>

doc/whats_new/v1.1.rst

@@ -168,6 +168,10 @@ Changelog
   and :class:`decomposition.SparseCoder` preserve dtype for `numpy.float32`.
   :pr:`22002` by :user:`Takeshi Oura <takoika>`.
 
+- |Enhancement| :class:`decomposition.SparsePCA` and :class:`decomposition.MiniBatchSparsePCA`
+  preserve dtype for `numpy.float32`.
+  :pr:`22111` by :user:`Takeshi Oura <takoika>`.
+
 - |API| Adds :term:`get_feature_names_out` to all transformers in the
   :mod:`~sklearn.decomposition` module:
   :class:`~sklearn.decomposition.DictionaryLearning`,

sklearn/decomposition/_sparse_pca.py

@@ -241,6 +241,11 @@ class SparsePCA(_ClassNamePrefixFeaturesOutMixin, TransformerMixin, BaseEstimato
         """Number of transformed output features."""
         return self.components_.shape[0]
 
+    def _more_tags(self):
+        return {
+            "preserves_dtype": [np.float64, np.float32],
+        }
+
 
 class MiniBatchSparsePCA(SparsePCA):
     """Mini-batch Sparse Principal Components Analysis.

sklearn/decomposition/tests/test_sparse_pca.py

@@ -206,6 +206,53 @@ def test_spca_n_components_(SPCA, n_components):
         assert model.n_components_ == n_features
 
 
+@pytest.mark.parametrize("SPCA", (SparsePCA, MiniBatchSparsePCA))
+@pytest.mark.parametrize("method", ("lars", "cd"))
+@pytest.mark.parametrize(
+    "data_type, expected_type",
+    (
+        (np.float32, np.float32),
+        (np.float64, np.float64),
+        (np.int32, np.float64),
+        (np.int64, np.float64),
+    ),
+)
+def test_sparse_pca_dtype_match(SPCA, method, data_type, expected_type):
+    # Verify output matrix dtype
+    n_samples, n_features, n_components = 12, 10, 3
+    rng = np.random.RandomState(0)
+    input_array = rng.randn(n_samples, n_features).astype(data_type)
+    model = SPCA(n_components=n_components, method=method)
+    transformed = model.fit_transform(input_array)
+
+    assert transformed.dtype == expected_type
+    assert model.components_.dtype == expected_type
+
+
+@pytest.mark.parametrize("SPCA", (SparsePCA, MiniBatchSparsePCA))
+@pytest.mark.parametrize("method", ("lars", "cd"))
+def test_sparse_pca_numerical_consistency(SPCA, method):
+    # Verify numericall consistentency among np.float32 and np.float64
+    rtol = 1e-3
+    alpha = 2
+    n_samples, n_features, n_components = 12, 10, 3
+    rng = np.random.RandomState(0)
+    input_array = rng.randn(n_samples, n_features)
+
+    model_32 = SPCA(
+        n_components=n_components, alpha=alpha, method=method, random_state=0
+    )
+    transformed_32 = model_32.fit_transform(input_array.astype(np.float32))
+
+    model_64 = SPCA(
+        n_components=n_components, alpha=alpha, method=method, random_state=0
+    )
+    transformed_64 = model_64.fit_transform(input_array.astype(np.float64))
+
+    assert_allclose(transformed_64, transformed_32, rtol=rtol)
+    assert_allclose(model_64.components_, model_32.components_, rtol=rtol)
+
+
 @pytest.mark.parametrize("SPCA", [SparsePCA, MiniBatchSparsePCA])
 def test_spca_feature_names_out(SPCA):
     """Check feature names out for *SparsePCA."""