def test_iterator_and_str(self):
"""Check preorder iterator"""
expected = [
"root feaures=(0, 1, 2) impurity=1.0000 counts=(array([0, 1]), "
"array([750, 750]))",
"root - Down(2), <cgaf> - Leaf class=0 belief= 0.928297 impurity="
"0.3722 counts=(array([0, 1]), array([725, 56]))",
"root - Up(2) feaures=(0, 1, 2) impurity=0.2178 counts=(array([0, "
"1]), array([ 25, 694]))",
"root - Up(2) - Down(3) feaures=(0, 1, 2) impurity=0.8454 counts="
"(array([0, 1]), array([8, 3]))",
"root - Up(2) - Down(3) - Down(4), <pure> - Leaf class=0 belief= "
"1.000000 impurity=0.0000 counts=(array([0]), array([7]))",
"root - Up(2) - Down(3) - Up(4), <cgaf> - Leaf class=1 belief= "
"0.750000 impurity=0.8113 counts=(array([0, 1]), array([1, 3]))",
"root - Up(2) - Up(3), <cgaf> - Leaf class=1 belief= 0.975989 "
"impurity=0.1634 counts=(array([0, 1]), array([ 17, 691]))",
]
computed = []
expected_string = ""
clf = Stree(
kernel="liblinear",
multiclass_strategy="ovr",
random_state=self._random_state,
)
clf.fit(*load_dataset(self._random_state))
for node in iter(clf):
computed.append(str(node))
expected_string += str(node) + "\n"
self.assertListEqual(expected, computed)
self.assertEqual(expected_string, str(clf))
def test_min_samples_split(self):
dataset = [[1], [2], [3]], [1, 1, 0]
tcl_split = Stree(min_samples_split=3).fit(*dataset)
self.assertIsNotNone(tcl_split.tree_.get_down())
self.assertIsNotNone(tcl_split.tree_.get_up())
tcl_nosplit = Stree(min_samples_split=4).fit(*dataset)
self.assertIsNone(tcl_nosplit.tree_.get_down())
self.assertIsNone(tcl_nosplit.tree_.get_up())
def __init__(self, *args, **kwargs):
self._random_state = 1
self._clf = Stree(
random_state=self._random_state,
kernel="liblinear",
multiclass_strategy="ovr",
)
self._clf.fit(*load_dataset(self._random_state))
super().__init__(*args, **kwargs)
def test_single_prediction(self):
X, y = load_dataset(self._random_state)
for kernel in self._kernels:
clf = Stree(
kernel=kernel,
multiclass_strategy="ovr" if kernel == "liblinear" else "ovo",
random_state=self._random_state,
)
yp = clf.fit(X, y).predict((X[0, :].reshape(-1, X.shape[1])))
self.assertEqual(yp[0], y[0])
def test_score_max_features(self):
X, y = load_dataset(self._random_state)
clf = Stree(
kernel="liblinear",
multiclass_strategy="ovr",
random_state=self._random_state,
max_features=2,
)
clf.fit(X, y)
self.assertAlmostEqual(0.9453333333333334, clf.score(X, y))
def test_muticlass_dataset(self):
warnings.filterwarnings("ignore", category=ConvergenceWarning)
warnings.filterwarnings("ignore", category=RuntimeWarning)
datasets = {
"Synt": load_dataset(random_state=self._random_state, n_classes=3),
"Iris": load_wine(return_X_y=True),
}
outcomes = {
"Synt": {
"max_samples liblinear": 0.9493333333333334,
"max_samples linear": 0.9426666666666667,
"max_samples rbf": 0.9606666666666667,
"max_samples poly": 0.9373333333333334,
"max_samples sigmoid": 0.824,
"impurity liblinear": 0.9493333333333334,
"impurity linear": 0.9426666666666667,
"impurity rbf": 0.9606666666666667,
"impurity poly": 0.9373333333333334,
"impurity sigmoid": 0.824,
},
"Iris": {
"max_samples liblinear": 0.9550561797752809,
"max_samples linear": 1.0,
"max_samples rbf": 0.6685393258426966,
"max_samples poly": 0.6853932584269663,
"max_samples sigmoid": 0.6404494382022472,
"impurity liblinear": 0.9550561797752809,
"impurity linear": 1.0,
"impurity rbf": 0.6685393258426966,
"impurity poly": 0.6853932584269663,
"impurity sigmoid": 0.6404494382022472,
},
}
for name, dataset in datasets.items():
px, py = dataset
for criteria in ["max_samples", "impurity"]:
for kernel in self._kernels:
clf = Stree(
max_iter=1e4,
multiclass_strategy="ovr"
if kernel == "liblinear" else "ovo",
kernel=kernel,
random_state=self._random_state,
)
clf.fit(px, py)
outcome = outcomes[name][f"{criteria} {kernel}"]
# print(f'"{criteria} {kernel}": {clf.score(px, py)},')
self.assertAlmostEqual(
outcome,
clf.score(px, py),
5,
f"{name} - {criteria} - {kernel}",
)
def test_build_tree(self):
"""Check if the tree is built the same way as predictions of models"""
warnings.filterwarnings("ignore")
for kernel in self._kernels:
clf = Stree(
kernel="sigmoid",
multiclass_strategy="ovr" if kernel == "liblinear" else "ovo",
random_state=self._random_state,
)
clf.fit(*load_dataset(self._random_state))
self._check_tree(clf.tree_)
def test_check_max_depth(self):
depths = (3, 4)
for depth in depths:
tcl = Stree(
kernel="liblinear",
multiclass_strategy="ovr",
random_state=self._random_state,
max_depth=depth,
)
tcl.fit(*load_dataset(self._random_state))
self.assertEqual(depth, tcl.depth_)
def test_multiple_prediction(self):
# First 27 elements the predictions are the same as the truth
num = 27
X, y = load_dataset(self._random_state)
for kernel in ["liblinear", "linear", "rbf", "poly"]:
clf = Stree(
kernel=kernel,
multiclass_strategy="ovr" if kernel == "liblinear" else "ovo",
random_state=self._random_state,
)
yp = clf.fit(X, y).predict(X[:num, :])
self.assertListEqual(y[:num].tolist(), yp.tolist())
def test_score_multiclass_linear(self):
warnings.filterwarnings("ignore", category=ConvergenceWarning)
warnings.filterwarnings("ignore", category=RuntimeWarning)
X, y = load_dataset(
random_state=self._random_state,
n_classes=3,
n_features=5,
n_samples=1500,
)
clf = Stree(
kernel="liblinear",
multiclass_strategy="ovr",
random_state=self._random_state,
)
self.assertEqual(0.9533333333333334, clf.fit(X, y).score(X, y))
# Check with context based standardization
clf2 = Stree(
kernel="liblinear",
multiclass_strategy="ovr",
random_state=self._random_state,
normalize=True,
)
self.assertEqual(0.9526666666666667, clf2.fit(X, y).score(X, y))
X, y = load_wine(return_X_y=True)
self.assertEqual(0.9831460674157303, clf.fit(X, y).score(X, y))
self.assertEqual(1.0, clf2.fit(X, y).score(X, y))
def test_multiclass_classifier_integrity(self):
"""Checks if the multiclass operation is done right"""
X, y = load_iris(return_X_y=True)
clf = Stree(kernel="liblinear",
multiclass_strategy="ovr",
random_state=0)
clf.fit(X, y)
score = clf.score(X, y)
# Check accuracy of the whole model
self.assertAlmostEquals(0.98, score, 5)
svm = LinearSVC(random_state=0)
svm.fit(X, y)
self.assertAlmostEquals(0.9666666666666667, svm.score(X, y), 5)
data = svm.decision_function(X)
expected = [
0.4444444444444444,
0.35777777777777775,
0.4569777777777778,
]
ty = data.copy()
ty[data <= 0] = 0
ty[data > 0] = 1
ty = ty.astype(int)
for i in range(3):
self.assertAlmostEquals(
expected[i],
clf.splitter_._gini(ty[:, i]),
)
# 1st Branch
# up has to have 50 samples of class 0
# down should have 100 [50, 50]
up = data[:, 2] > 0
resup = np.unique(y[up], return_counts=True)
resdn = np.unique(y[~up], return_counts=True)
self.assertListEqual([1, 2], resup[0].tolist())
self.assertListEqual([3, 50], resup[1].tolist())
self.assertListEqual([0, 1], resdn[0].tolist())
self.assertListEqual([50, 47], resdn[1].tolist())
# 2nd Branch
# up should have 53 samples of classes [1, 2] [3, 50]
# down shoud have 47 samples of class 1
node_up = clf.tree_.get_down().get_up()
node_dn = clf.tree_.get_down().get_down()
resup = np.unique(node_up._y, return_counts=True)
resdn = np.unique(node_dn._y, return_counts=True)
self.assertListEqual([1, 2], resup[0].tolist())
self.assertListEqual([3, 50], resup[1].tolist())
self.assertListEqual([1], resdn[0].tolist())
self.assertListEqual([47], resdn[1].tolist())
def test_incompatible_hyperparameters(self):
X, y = load_wine(return_X_y=True)
clf = Stree(kernel="liblinear", multiclass_strategy="ovo")
with self.assertRaises(ValueError):
clf.fit(X, y)
clf = Stree(multiclass_strategy="ovo", split_criteria="max_samples")
with self.assertRaises(ValueError):
clf.fit(X, y)
def test_check_max_depth_is_positive_or_None(self):
tcl = Stree()
self.assertIsNone(tcl.max_depth)
tcl = Stree(max_depth=1)
self.assertGreaterEqual(1, tcl.max_depth)
with self.assertRaises(ValueError):
tcl = Stree(max_depth=-1)
tcl.fit(*load_dataset(self._random_state))
def test_nodes_coefs(self):
"""Check if the nodes of the tree have the right attributes filled"""
def run_tree(node: Snode):
if node._belief < 1:
# only exclude pure leaves
self.assertIsNotNone(node._clf)
self.assertIsNotNone(node._clf.coef_)
if node.is_leaf():
return
run_tree(node.get_up())
run_tree(node.get_down())
model = Stree(self._random_state)
model.fit(*load_dataset(self._random_state, 3, 4))
run_tree(model.tree_)
def test_nodes_leaves_artificial(self):
n1 = Snode(None, [1, 2, 3, 4], [1, 0, 1, 1], [], 0.0, "test1")
n2 = Snode(None, [1, 2, 3, 4], [1, 0, 1, 1], [], 0.0, "test2")
n3 = Snode(None, [1, 2, 3, 4], [1, 0, 1, 1], [], 0.0, "test3")
n4 = Snode(None, [1, 2, 3, 4], [1, 0, 1, 1], [], 0.0, "test4")
n5 = Snode(None, [1, 2, 3, 4], [1, 0, 1, 1], [], 0.0, "test5")
n6 = Snode(None, [1, 2, 3, 4], [1, 0, 1, 1], [], 0.0, "test6")
n1.set_up(n2)
n2.set_up(n3)
n2.set_down(n4)
n3.set_up(n5)
n4.set_down(n6)
clf = Stree(random_state=self._random_state)
clf.tree_ = n1
nodes, leaves = clf.nodes_leaves()
self.assertEqual(6, nodes)
self.assertEqual(2, leaves)
def test_nodes_leaves(self):
X, y = load_dataset(
random_state=self._random_state,
n_classes=3,
n_features=5,
n_samples=1500,
)
clf = Stree(random_state=self._random_state)
clf.fit(X, y)
nodes, leaves = clf.nodes_leaves()
self.assertEqual(31, nodes)
self.assertEqual(16, leaves)
X, y = load_wine(return_X_y=True)
clf = Stree(random_state=self._random_state)
clf.fit(X, y)
nodes, leaves = clf.nodes_leaves()
self.assertEqual(11, nodes)
self.assertEqual(6, leaves)
def test_copy_node(self):
px = [1, 2, 3, 4]
py = [1]
test = Snode(Stree(), px, py, [], 0.0, "test")
computed = Snode.copy(test)
self.assertListEqual(computed._X, px)
self.assertListEqual(computed._y, py)
self.assertEqual("test", computed._title)
self.assertIsInstance(computed._clf, Stree)
self.assertEqual(test._partition_column, computed._partition_column)
self.assertEqual(test._sample_weight, computed._sample_weight)
self.assertEqual(test._scaler, computed._scaler)
def test_depth(self):
X, y = load_dataset(
random_state=self._random_state,
n_classes=3,
n_features=5,
n_samples=1500,
)
clf = Stree(random_state=self._random_state)
clf.fit(X, y)
self.assertEqual(6, clf.depth_)
X, y = load_wine(return_X_y=True)
clf = Stree(random_state=self._random_state)
clf.fit(X, y)
self.assertEqual(4, clf.depth_)
def test_predict_feature_dimensions(self):
X = np.random.rand(10, 5)
y = np.random.randint(0, 2, 10)
clf = Stree()
clf.fit(X, y)
with self.assertRaises(ValueError):
clf.predict(X[:, :3])
def test_multiclass_strategy(self):
X, y = load_wine(return_X_y=True)
clf_o = Stree(multiclass_strategy="ovo")
clf_r = Stree(multiclass_strategy="ovr")
score_o = clf_o.fit(X, y).score(X, y)
score_r = clf_r.fit(X, y).score(X, y)
self.assertEqual(1.0, score_o)
self.assertEqual(0.9269662921348315, score_r)
def test_score_multiclass_rbf(self):
X, y = load_dataset(
random_state=self._random_state,
n_classes=3,
n_features=5,
n_samples=500,
)
clf = Stree(kernel="rbf", random_state=self._random_state)
clf2 = Stree(kernel="rbf",
random_state=self._random_state,
normalize=True)
self.assertEqual(0.966, clf.fit(X, y).score(X, y))
self.assertEqual(0.964, clf2.fit(X, y).score(X, y))
X, y = load_wine(return_X_y=True)
self.assertEqual(0.6685393258426966, clf.fit(X, y).score(X, y))
self.assertEqual(1.0, clf2.fit(X, y).score(X, y))
def test_max_features(self):
n_features = 16
expected_values = [
("auto", 4),
("log2", 4),
("sqrt", 4),
(0.5, 8),
(3, 3),
(None, 16),
]
clf = Stree()
clf.n_features_ = n_features
for max_features, expected in expected_values:
clf.set_params(**dict(max_features=max_features))
computed = clf._initialize_max_features()
self.assertEqual(expected, computed)
# Check bogus max_features
values = ["duck", -0.1, 0.0]
for max_features in values:
clf.set_params(**dict(max_features=max_features))
with self.assertRaises(ValueError):
_ = clf._initialize_max_features()
def test_score_multiclass_sigmoid(self):
X, y = load_dataset(
random_state=self._random_state,
n_classes=3,
n_features=5,
n_samples=500,
)
clf = Stree(kernel="sigmoid", random_state=self._random_state, C=10)
clf2 = Stree(
kernel="sigmoid",
random_state=self._random_state,
normalize=True,
C=10,
)
self.assertEqual(0.796, clf.fit(X, y).score(X, y))
self.assertEqual(0.952, clf2.fit(X, y).score(X, y))
X, y = load_wine(return_X_y=True)
self.assertEqual(0.6910112359550562, clf.fit(X, y).score(X, y))
self.assertEqual(0.9662921348314607, clf2.fit(X, y).score(X, y))
def test_simple_muticlass_dataset(self):
for kernel in self._kernels:
clf = Stree(
kernel=kernel,
multiclass_strategy="ovr" if kernel == "liblinear" else "ovo",
random_state=self._random_state,
)
px = [[1, 2], [5, 6], [9, 10]]
py = [0, 1, 2]
clf.fit(px, py)
self.assertEqual(1.0, clf.score(px, py))
self.assertListEqual(py, clf.predict(px).tolist())
self.assertListEqual(py, clf.classes_.tolist())
def test_mask_samples_weighted_zero(self):
X = np.array([
[1, 1],
[1, 1],
[1, 1],
[2, 2],
[2, 2],
[2, 2],
[3, 3],
[3, 3],
[3, 3],
])
y = np.array([1, 1, 1, 2, 2, 2, 5, 5, 5])
yw = np.array([1, 1, 1, 1, 1, 1, 5, 5, 5])
w = [1, 1, 1, 0, 0, 0, 1, 1, 1]
model1 = Stree().fit(X, y)
model2 = Stree().fit(X, y, w)
predict1 = model1.predict(X)
predict2 = model2.predict(X)
self.assertListEqual(y.tolist(), predict1.tolist())
self.assertListEqual(yw.tolist(), predict2.tolist())
self.assertEqual(model1.score(X, y), 1)
self.assertAlmostEqual(model2.score(X, y), 0.66666667)
self.assertEqual(model2.score(X, y, w), 1)
def test_score_multiclass_poly(self):
X, y = load_dataset(
random_state=self._random_state,
n_classes=3,
n_features=5,
n_samples=500,
)
clf = Stree(kernel="poly",
random_state=self._random_state,
C=10,
degree=5)
clf2 = Stree(
kernel="poly",
random_state=self._random_state,
normalize=True,
)
self.assertEqual(0.946, clf.fit(X, y).score(X, y))
self.assertEqual(0.972, clf2.fit(X, y).score(X, y))
X, y = load_wine(return_X_y=True)
self.assertEqual(0.7808988764044944, clf.fit(X, y).score(X, y))
self.assertEqual(1.0, clf2.fit(X, y).score(X, y))
def test_score_multiclass_liblinear(self):
X, y = load_dataset(
random_state=self._random_state,
n_classes=3,
n_features=5,
n_samples=500,
)
clf = Stree(
kernel="liblinear",
multiclass_strategy="ovr",
random_state=self._random_state,
C=10,
)
clf2 = Stree(
kernel="liblinear",
multiclass_strategy="ovr",
random_state=self._random_state,
normalize=True,
)
self.assertEqual(0.968, clf.fit(X, y).score(X, y))
self.assertEqual(0.97, clf2.fit(X, y).score(X, y))
X, y = load_wine(return_X_y=True)
self.assertEqual(1.0, clf.fit(X, y).score(X, y))
self.assertEqual(1.0, clf2.fit(X, y).score(X, y))
def test_get_subspaces(self):
dataset = np.random.random((10, 16))
y = np.random.randint(0, 2, 10)
expected_values = [
("auto", 4),
("log2", 4),
("sqrt", 4),
(0.5, 8),
(3, 3),
(None, 16),
]
clf = Stree()
for max_features, expected in expected_values:
clf.set_params(**dict(max_features=max_features))
clf.fit(dataset, y)
computed, indices = clf.splitter_.get_subspace(
dataset, y, clf.max_features_)
self.assertListEqual(dataset[:, indices].tolist(),
computed.tolist())
self.assertEqual(expected, len(indices))
def test_single_vs_multiple_prediction(self):
"""Check if predicting sample by sample gives the same result as
predicting all samples at once
"""
X, y = load_dataset(self._random_state)
for kernel in self._kernels:
clf = Stree(
kernel=kernel,
multiclass_strategy="ovr" if kernel == "liblinear" else "ovo",
random_state=self._random_state,
)
clf.fit(X, y)
# Compute prediction line by line
yp_line = np.array([], dtype=int)
for xp in X:
yp_line = np.append(yp_line,
clf.predict(xp.reshape(-1, X.shape[1])))
# Compute prediction at once
yp_once = clf.predict(X)
self.assertListEqual(yp_line.tolist(), yp_once.tolist())
def test_score_binary(self):
X, y = load_dataset(self._random_state)
accuracies = [
0.9506666666666667,
0.9493333333333334,
0.9606666666666667,
0.9433333333333334,
0.9153333333333333,
]
for kernel, accuracy_expected in zip(self._kernels, accuracies):
clf = Stree(
random_state=self._random_state,
multiclass_strategy="ovr" if kernel == "liblinear" else "ovo",
kernel=kernel,
)
clf.fit(X, y)
accuracy_score = clf.score(X, y)
yp = clf.predict(X)
accuracy_computed = np.mean(yp == y)
self.assertEqual(accuracy_score, accuracy_computed)
self.assertAlmostEqual(accuracy_expected, accuracy_score)