def test_convert(self):
X = numpy.arange(8).astype(numpy.float64).reshape((-1, 2))
y = ((X[:, 0] + X[:, 1] * 2) > 10).astype(numpy.int64)
y2 = y.copy()
y2[0] = 2
tree = DecisionTreeClassifier(max_depth=2)
tree.fit(X, y2)
self.assertRaise(
lambda: NeuralTreeNet.create_from_tree(tree), RuntimeError)
tree = DecisionTreeClassifier(max_depth=2)
tree.fit(X, y)
root = NeuralTreeNet.create_from_tree(tree, 10)
self.assertNotEmpty(root)
exp = tree.predict_proba(X)
got = root.predict(X)
self.assertEqual(exp.shape[0], got.shape[0])
self.assertEqualArray(exp, got[:, -2:])
def test_neural_net_gradient(self):
X = numpy.arange(8).astype(numpy.float64).reshape((-1, 2))
y = ((X[:, 0] + X[:, 1] * 2) > 10).astype(numpy.int64)
ny = label_class_to_softmax_output(y)
tree = DecisionTreeClassifier(max_depth=2)
tree.fit(X, y)
root = NeuralTreeNet.create_from_tree(tree, 10)
_, out, err = self.capture(lambda: root.fit(X, ny, verbose=True))
self.assertIn("loss:", out)
self.assertEmpty(err)
def test_convert_compact(self):
X = numpy.arange(8).astype(numpy.float64).reshape((-1, 2))
y = ((X[:, 0] + X[:, 1] * 2) > 10).astype(numpy.int64)
y2 = y.copy()
y2[0] = 2
tree = DecisionTreeClassifier(max_depth=2)
tree.fit(X, y2)
self.assertRaise(
lambda: NeuralTreeNet.create_from_tree(tree, arch="k"), ValueError)
self.assertRaise(
lambda: NeuralTreeNet.create_from_tree(tree, arch="compact"),
RuntimeError)
tree = DecisionTreeClassifier(max_depth=2)
tree.fit(X, y)
root = NeuralTreeNet.create_from_tree(tree, 10, arch='compact')
self.assertNotEmpty(root)
exp = tree.predict_proba(X)
got = root.predict(X)
self.assertEqual(exp.shape[0], got.shape[0])
self.assertEqualArray(exp + 1e-8, got[:, -2:] + 1e-8)
dot = root.to_dot()
self.assertIn("s3a4:f4 -> s5a6:f6", dot)
def test_training_weights(self):
X = numpy.arange(8).astype(numpy.float64).reshape((-1, 2))
y = ((X[:, 0] + X[:, 1] * 2) > 10).astype(numpy.int64)
y2 = y.copy()
y2[0] = 2
tree = DecisionTreeClassifier(max_depth=2)
tree.fit(X, y)
root = NeuralTreeNet.create_from_tree(tree, 10)
v1 = root.predict(X[:1])
w = root.training_weights
self.assertEqual(w.shape, (11, ))
delta = numpy.arange(11) + 0.5
root.update_training_weights(delta)
v2 = root.predict(X[:1])
self.assertNotEqualArray(v1, v2)
def test_neural_net_gradient_fit(self):
X = numpy.arange(16).astype(numpy.float64).reshape((-1, 2))
y = ((X[:, 0] + X[:, 1] * 2) > 15).astype(numpy.int64)
ny = label_class_to_softmax_output(y)
tree = DecisionTreeClassifier(max_depth=2)
tree.fit(X, y)
root = NeuralTreeNet.create_from_tree(tree, 10)
loss1 = root.loss(X, ny).sum()
self.assertGreater(loss1, -1e-5)
self.assertLess(loss1, 1.)
_, out, err = self.capture(
lambda: root.fit(X, ny, verbose=True, max_iter=20))
self.assertEmpty(err)
self.assertNotEmpty(out)
loss2 = root.loss(X, ny).sum()
self.assertLess(loss2, loss1 + 1)
def test_convert_compact_fit(self):
X = numpy.arange(8).astype(numpy.float64).reshape((-1, 2))
y = ((X[:, 0] + X[:, 1] * 2) > 10).astype(numpy.int64)
y2 = y.copy()
y2[0] = 2
tree = DecisionTreeClassifier(max_depth=2)
tree.fit(X, y)
root = NeuralTreeNet.create_from_tree(tree, 10, arch='compact')
self.assertNotEmpty(root)
exp = tree.predict_proba(X)
got = root.predict(X)
self.assertEqual(exp.shape[0], got.shape[0])
self.assertEqualArray(exp + 1e-8, got[:, -2:] + 1e-8)
ny = label_class_to_softmax_output(y)
loss1 = root.loss(X, ny).sum()
_, out, err = self.capture(
lambda: root.fit(X, ny, verbose=True, max_iter=20))
self.assertEmpty(err)
self.assertNotEmpty(out)
loss2 = root.loss(X, ny).sum()
self.assertLess(loss2, loss1 + 1)
def test_dot(self):
data = load_iris()
X, y = data.data, data.target
y = y % 2
tree = DecisionTreeClassifier(max_depth=3, random_state=11)
tree.fit(X, y)
root = NeuralTreeNet.create_from_tree(tree)
dot = export_graphviz(tree)
self.assertIn("digraph", dot)
dot2 = root.to_dot()
self.assertIn("digraph", dot2)
x = X[:1].copy()
x[0, 3] = 1.
dot2 = root.to_dot(X=x.ravel())
self.assertIn("digraph", dot2)
exp = tree.predict_proba(X)[:, -1]
got = root.predict(X)[:, -1]
mat = numpy.empty((exp.shape[0], 2), dtype=exp.dtype)
mat[:, 0] = exp
mat[:, 1] = got
c = numpy.corrcoef(mat.T)
self.assertGreater(c[0, 1], 0.5)