Start refactoring of classifiers

tests/classifiers/test_counting.py

@@ -12,7 +12,27 @@ E = 0.1
 
 def test_counting():
     clf = CountingClassifier()
-    clf.fit(np.zeros((8, 25)), [0.0, 0.0, 0.0, 1.0, 1.0, 1.0, 1.0, 1.0])
-    expected_proba = np.array([[0.375, 0.625], [0.375, 0.625]])
-    actual_proba = clf.predict_proba(np.zeros((2, 25)))
-    assert norm(actual_proba - expected_proba) < E
+    n_features = 25
+    x_train = np.zeros((8, n_features))
+    y_train = np.array(
+        [
+            [True, False, False],
+            [True, False, False],
+            [False, True, False],
+            [True, False, False],
+            [False, True, False],
+            [False, True, False],
+            [False, True, False],
+            [False, False, True],
+        ]
+    )
+    x_test = np.zeros((2, n_features))
+    y_expected = np.array(
+        [
+            [3 / 8.0, 4 / 8.0, 1 / 8.0],
+            [3 / 8.0, 4 / 8.0, 1 / 8.0],
+        ]
+    )
+    clf.fit(x_train, y_train)
+    y_actual = clf.predict_proba(x_test)
+    assert norm(y_actual - y_expected) < E

tests/classifiers/test_cv.py

@@ -7,20 +7,37 @@ from numpy.linalg import norm
 from sklearn.preprocessing import StandardScaler
 from sklearn.svm import SVC
 
+from miplearn.classifiers import ScikitLearnClassifier
 from miplearn.classifiers.cv import CrossValidatedClassifier
 
 E = 0.1
 
 
-def test_cv():
+def test_cv() -> None:
     # Training set: label is true if point is inside a 2D circle
-    x_train = np.array([[x1, x2] for x1 in range(-10, 11) for x2 in range(-10, 11)])
+    x_train = np.array(
+        [
+            [
+                x1,
+                x2,
+            ]
+            for x1 in range(-10, 11)
+            for x2 in range(-10, 11)
+        ]
+    )
     x_train = StandardScaler().fit_transform(x_train)
     n_samples = x_train.shape[0]
-
     y_train = np.array(
         [
-            1.0 if x1 * x1 + x2 * x2 <= 100 else 0.0
+            [
+                False,
+                True,
+            ]
+            if x1 * x1 + x2 * x2 <= 100
+            else [
+                True,
+                False,
+            ]
             for x1 in range(-10, 11)
             for x2 in range(-10, 11)
         ]
@@ -29,24 +46,39 @@ def test_cv():
     # Support vector machines with linear kernels do not perform well on this
     # data set, so predictor should return the given constant.
     clf = CrossValidatedClassifier(
-        classifier=SVC(probability=True, random_state=42),
+        classifier=lambda: ScikitLearnClassifier(
+            SVC(
+                probability=True,
+                random_state=42,
+            )
+        ),
         threshold=0.90,
-        constant=0.0,
+        constant=[True, False],
         cv=30,
     )
     clf.fit(x_train, y_train)
     proba = clf.predict_proba(x_train)
+    assert isinstance(proba, np.ndarray)
+    assert proba.shape == (n_samples, 2)
+
     y_pred = (proba[:, 1] > 0.5).astype(float)
     assert norm(np.zeros(n_samples) - y_pred) < E
 
     # Support vector machines with quadratic kernels perform almost perfectly
     # on this data set, so predictor should return their prediction.
     clf = CrossValidatedClassifier(
-        classifier=SVC(probability=True, kernel="poly", degree=2, random_state=42),
+        classifier=lambda: ScikitLearnClassifier(
+            SVC(
+                probability=True,
+                kernel="poly",
+                degree=2,
+                random_state=42,
+            )
+        ),
         threshold=0.90,
         cv=30,
     )
     clf.fit(x_train, y_train)
     proba = clf.predict_proba(x_train)
     y_pred = (proba[:, 1] > 0.5).astype(float)
-    assert norm(y_train - y_pred) < E
+    assert norm(y_train[:, 1] - y_pred) < E