Support sparse matrices in KernelRidge.

mblondel · mblondel · commit 7fa9b0edc0f3 · 2015-03-12T23:08:10.000+09:00
Fixes scikit-learn#4384.
diff --git a/sklearn/kernel_ridge.py b/sklearn/kernel_ridge.py
@@ -141,7 +141,7 @@ def fit(self, X, y=None, sample_weight=None):
         self : returns an instance of self.
         """
         # Convert data
-        X, y = check_X_y(X, y, multi_output=True)
+        X, y = check_X_y(X, y, accept_sparse=("csr", "csc"), multi_output=True)
 
         n_samples = X.shape[0]
         K = self._get_kernel(X)
diff --git a/sklearn/tests/test_kernel_ridge.py b/sklearn/tests/test_kernel_ridge.py
@@ -1,4 +1,5 @@
 import numpy as np
+import scipy.sparse as sp
 
 from sklearn.datasets import make_regression
 from sklearn.linear_model import Ridge
@@ -10,6 +11,8 @@
 
 
 X, y = make_regression(n_features=10)
+Xcsr = sp.csr_matrix(X)
+Xcsc = sp.csc_matrix(X)
 Y = np.array([y, y]).T
 
 
@@ -19,6 +22,20 @@ def test_kernel_ridge():
     assert_array_almost_equal(pred, pred2)
 
 
+def test_kernel_ridge_csr():
+    pred = Ridge(alpha=1, fit_intercept=False,
+                 solver="cholesky").fit(Xcsr, y).predict(Xcsr)
+    pred2 = KernelRidge(kernel="linear", alpha=1).fit(Xcsr, y).predict(Xcsr)
+    assert_array_almost_equal(pred, pred2)
+
+
+def test_kernel_ridge_csc():
+    pred = Ridge(alpha=1, fit_intercept=False,
+                 solver="cholesky").fit(Xcsc, y).predict(Xcsc)
+    pred2 = KernelRidge(kernel="linear", alpha=1).fit(Xcsc, y).predict(Xcsc)
+    assert_array_almost_equal(pred, pred2)
+
+
 def test_kernel_ridge_singular_kernel():
     # alpha=0 causes a LinAlgError in computing the dual coefficients,
     # which causes a fallback to a lstsq solver. This is tested here.
