LDA & QDA: Extended tests

andreArtelt · May 8, 2020 · 5794716 · 5794716
1 parent 5619300
commit 5794716
Show file tree

Hide file tree

Showing 2 changed files with 32 additions and 2 deletions.
diff --git a/tests/sklearn/test_sklearn_lda.py b/tests/sklearn/test_sklearn_lda.py
@@ -34,6 +34,14 @@ def test_lda():
     assert y_cf == 0
     assert model.predict(np.array([x_cf])) == 0
 
+    x_cf, y_cf, delta = generate_counterfactual(model, x_orig, 1, features_whitelist=features_whitelist, regularization="l1", optimizer="mp", return_as_dict=False)
+    assert y_cf == 1
+    assert model.predict(np.array([x_cf])) == 1
+
+    cf = generate_counterfactual(model, x_orig, 0, features_whitelist=features_whitelist, regularization="l1", optimizer="mp", return_as_dict=True)
+    assert cf["y_cf"] == 0
+    assert model.predict(np.array([cf["x_cf"]])) == 0
+
     x_cf, y_cf, delta = generate_counterfactual(model, x_orig, 0, features_whitelist=features_whitelist, regularization="l2", optimizer="mp", return_as_dict=False)
     assert y_cf == 0
     assert model.predict(np.array([x_cf])) == 0
@@ -89,4 +97,11 @@ def test_lda():
     # Other stuff
     from ceml.sklearn import LdaCounterfactual
     with pytest.raises(TypeError):
-        LdaCounterfactual(sklearn.linear_model.LogisticRegression())
+        LdaCounterfactual(sklearn.linear_model.LogisticRegression())
+
+    model = LinearDiscriminantAnalysis()
+    model.fit(X_train, y_train)
+    with pytest.raises(AttributeError):
+        LdaCounterfactual(model)
+    with pytest.raises(AttributeError):
+        generate_counterfactual(model, x_orig, 0)
diff --git a/tests/sklearn/test_sklearn_qda.py b/tests/sklearn/test_sklearn_qda.py
@@ -34,6 +34,10 @@ def test_qda():
     assert y_cf == 0
     assert model.predict(np.array([x_cf])) == 0
 
+    cf = generate_counterfactual(model, x_orig, 0, features_whitelist=features_whitelist, regularization="l1", optimizer="mp", return_as_dict=True)
+    assert cf["y_cf"] == 0
+    assert model.predict(np.array([cf["x_cf"]])) == 0
+
     x_cf, y_cf, delta = generate_counterfactual(model, x_orig, 0, features_whitelist=features_whitelist, regularization="l2", optimizer="mp", return_as_dict=False)
     assert y_cf == 0
     assert model.predict(np.array([x_cf])) == 0
@@ -103,6 +107,10 @@ def test_qda():
     assert y_cf == 1
     assert model.predict(np.array([x_cf])) == 1
 
+    cf = generate_counterfactual(model, x_orig, y_target=1, features_whitelist=features_whitelist, optimizer="mp", return_as_dict=True)
+    assert cf["y_cf"] == 1
+    assert model.predict(np.array([cf["x_cf"]])) == 1
+
     x_orig = X_test[0,:]
     assert model.predict([x_orig]) == 1
 
@@ -113,4 +121,11 @@ def test_qda():
     # Other stuff
     from ceml.sklearn import QdaCounterfactual
     with pytest.raises(TypeError):
-        QdaCounterfactual(sklearn.linear_model.LogisticRegression())
+        QdaCounterfactual(sklearn.linear_model.LogisticRegression())
+
+    model = QuadraticDiscriminantAnalysis()
+    model.fit(X_train, y_train)
+    with pytest.raises(AttributeError):
+        QdaCounterfactual(model)
+    with pytest.raises(AttributeError):
+        generate_counterfactual(model, x_orig, 0)