def test_iforest_average_path_length():
# It tests non-regression for #8549 which used the wrong formula
# for average path length, strictly for the integer case
result_one = 2. * (np.log(4.) + euler_gamma) - 2. * 4. / 5.
result_two = 2. * (np.log(998.) + euler_gamma) - 2. * 998. / 999.
assert_almost_equal(_average_path_length(1), 1., decimal=10)
assert_almost_equal(_average_path_length(5), result_one, decimal=10)
assert_almost_equal(_average_path_length(999), result_two, decimal=10)
assert_array_almost_equal(_average_path_length(np.array([1, 5, 999])),
[1., result_one, result_two], decimal=10)
def test_iforest_average_path_length():
# It tests non-regression for #8549 which used the wrong formula
# for average path length, strictly for the integer case
result_one = 2. * (np.log(4.) + euler_gamma) - 2. * 4. / 5.
result_two = 2. * (np.log(998.) + euler_gamma) - 2. * 998. / 999.
assert_almost_equal(_average_path_length(1), 1., decimal=10)
assert_almost_equal(_average_path_length(5), result_one, decimal=10)
assert_almost_equal(_average_path_length(999), result_two, decimal=10)
assert_array_almost_equal(_average_path_length(np.array([1, 5, 999])),
[1., result_one, result_two], decimal=10)
def test_isolation_forest():
import shap
import numpy as np
from sklearn.ensemble import IsolationForest
from sklearn.ensemble.iforest import _average_path_length
X, y = shap.datasets.boston()
iso = IsolationForest(behaviour='new', contamination='auto')
iso.fit(X)
explainer = shap.TreeExplainer(iso)
shap_values = explainer.shap_values(X)
score_from_shap = -2**(
-(np.sum(shap_values, axis=1) + explainer.expected_value) /
_average_path_length(np.array([iso.max_samples_]))[0])
assert np.allclose(iso.score_samples(X), score_from_shap, atol=1e-7)
def test_iforest_average_path_length():
# It tests non-regression for #8549 which used the wrong formula
# for average path length, strictly for the integer case
# Updated to check average path length when input is <= 2 (issue #11839)
result_one = 2. * (np.log(4.) + np.euler_gamma) - 2. * 4. / 5.
result_two = 2. * (np.log(998.) + np.euler_gamma) - 2. * 998. / 999.
assert _average_path_length(0) == pytest.approx(0)
assert _average_path_length(1) == pytest.approx(0)
assert _average_path_length(2) == pytest.approx(1)
assert_allclose(_average_path_length(5), result_one)
assert_allclose(_average_path_length(999), result_two)
assert_allclose(_average_path_length(np.array([1, 2, 5, 999])),
[0., 1., result_one, result_two])
# _average_path_length is increasing
avg_path_length = _average_path_length(np.arange(5))
assert_array_equal(avg_path_length, np.sort(avg_path_length))
def test_iforest_average_path_length():
# It tests non-regression for #8549 which used the wrong formula
# for average path length, strictly for the integer case
# Updated to check average path length when input is <= 2 (issue #11839)
result_one = 2.0 * (np.log(4.0) + np.euler_gamma) - 2.0 * 4.0 / 5.0
result_two = 2.0 * (np.log(998.0) + np.euler_gamma) - 2.0 * 998.0 / 999.0
assert_allclose(_average_path_length([0]), [0.0])
assert_allclose(_average_path_length([1]), [0.0])
assert_allclose(_average_path_length([2]), [1.0])
assert_allclose(_average_path_length([5]), [result_one])
assert_allclose(_average_path_length([999]), [result_two])
assert_allclose(
_average_path_length(np.array([1, 2, 5, 999])),
[0.0, 1.0, result_one, result_two],
)
# _average_path_length is increasing
avg_path_length = _average_path_length(np.arange(5))
assert_array_equal(avg_path_length, np.sort(avg_path_length))
def test_iforest_average_path_length():
# It tests non-regression for #8549 which used the wrong formula
# for average path length, strictly for the integer case
# Updated to check average path length when input is <= 2 (issue #11839)
result_one = 2.0 * (np.log(4.0) + np.euler_gamma) - 2.0 * 4.0 / 5.0
result_two = 2.0 * (np.log(998.0) + np.euler_gamma) - 2.0 * 998.0 / 999.0
assert_allclose(_average_path_length([0]), [0.0])
assert_allclose(_average_path_length([1]), [0.0])
assert_allclose(_average_path_length([2]), [1.0])
assert_allclose(_average_path_length([5]), [result_one])
assert_allclose(_average_path_length([999]), [result_two])
assert_allclose(
_average_path_length(np.array([1, 2, 5, 999])),
[0.0, 1.0, result_one, result_two],
)
# _average_path_length is increasing
avg_path_length = _average_path_length(np.arange(5))
assert_array_equal(avg_path_length, np.sort(avg_path_length))
def test_pyod_isolation_forest():
import shap
import numpy as np
from pyod.models.iforest import IForest
from sklearn.ensemble.iforest import _average_path_length
X, _ = shap.datasets.boston()
for max_features in [1.0, 0.75]:
iso = IForest(max_features=max_features)
iso.fit(X)
explainer = shap.TreeExplainer(iso)
shap_values = explainer.shap_values(X)
score_from_shap = -2**(
-(np.sum(shap_values, axis=1) + explainer.expected_value) /
_average_path_length(np.array([iso.max_samples_]))[0])
assert np.allclose(iso.detector_.score_samples(X),
score_from_shap,
atol=1e-7)