Merge pull request scikit-learn#5098 from olologin/OneClassSvm_sparse_test

[MRG + 1] OneClassSVM sparsity regression test added

Author: ogrisel

sklearn/svm/tests/test_sparse.py

@@ -59,9 +59,12 @@ def check_svm_model_equal(dense_svm, sparse_svm, X_train, y_train, X_test):
                               sparse_svm.decision_function(X_test))
     assert_array_almost_equal(dense_svm.decision_function(X_test_dense),
                               sparse_svm.decision_function(X_test_dense))
-    assert_array_almost_equal(dense_svm.predict_proba(X_test_dense),
-                              sparse_svm.predict_proba(X_test), 4)
-    msg = "cannot use sparse input in 'SVC' trained on dense data"
+    if isinstance(dense_svm, svm.OneClassSVM):
+        msg = "cannot use sparse input in 'OneClassSVM' trained on dense data"
+    else:
+        assert_array_almost_equal(dense_svm.predict_proba(X_test_dense),
+            sparse_svm.predict_proba(X_test), 4)
+        msg = "cannot use sparse input in 'SVC' trained on dense data"
     if sparse.isspmatrix(X_test):
         assert_raise_message(ValueError, msg, dense_svm.predict, X_test)
 
@@ -255,6 +258,23 @@ def test_sparse_liblinear_intercept_handling():
     test_svm.test_dense_liblinear_intercept_handling(svm.LinearSVC)
 
 
+def test_sparse_oneclasssvm():
+    """Check that sparse OneClassSVM gives the same result as dense OneClassSVM"""
+    # many class dataset:
+    X_blobs, _ = make_blobs(n_samples=100, centers=10, random_state=0)
+    X_blobs = sparse.csr_matrix(X_blobs)
+
+    datasets = [[X_sp, None, T], [X2_sp, None, T2],
+                [X_blobs[:80], None, X_blobs[80:]],
+                [iris.data, None, iris.data]]
+    kernels = ["linear", "poly", "rbf", "sigmoid"]
+    for dataset in datasets:
+        for kernel in kernels:
+            clf = svm.OneClassSVM(kernel=kernel, random_state=0)
+            sp_clf = svm.OneClassSVM(kernel=kernel, random_state=0)
+            check_svm_model_equal(clf, sp_clf, *dataset)
+
+
 def test_sparse_realdata():
     # Test on a subset from the 20newsgroups dataset.
     # This catchs some bugs if input is not correctly converted into