def test_score_samples():
X_train = [[1, 1], [1, 2], [2, 1]]
clf1 = IsolationForest(contamination=0.1).fit(X_train)
clf2 = IsolationForest().fit(X_train)
assert_array_equal(clf1.score_samples([[2., 2.]]),
clf1.decision_function([[2., 2.]]) + clf1.offset_)
assert_array_equal(clf2.score_samples([[2., 2.]]),
clf2.decision_function([[2., 2.]]) + clf2.offset_)
assert_array_equal(clf1.score_samples([[2., 2.]]),
clf2.score_samples([[2., 2.]]))
def test_max_samples_attribute():
X = iris.data
clf = IsolationForest().fit(X)
assert clf.max_samples_ == X.shape[0]
clf = IsolationForest(max_samples=500)
assert_warns_message(UserWarning,
"max_samples will be set to n_samples for estimation",
clf.fit, X)
assert clf.max_samples_ == X.shape[0]
clf = IsolationForest(max_samples=0.4).fit(X)
assert clf.max_samples_ == 0.4*X.shape[0]
def test_iforest_error():
"""Test that it gives proper exception on deficient input."""
X = iris.data
# Test max_samples
assert_raises(ValueError,
IsolationForest(max_samples=-1).fit, X)
assert_raises(ValueError,
IsolationForest(max_samples=0.0).fit, X)
assert_raises(ValueError,
IsolationForest(max_samples=2.0).fit, X)
# The dataset has less than 256 samples, explicitly setting
# max_samples > n_samples should result in a warning. If not set
# explicitly there should be no warning
assert_warns_message(UserWarning,
"max_samples will be set to n_samples for estimation",
IsolationForest(max_samples=1000).fit, X)
# note that assert_no_warnings does not apply since it enables a
# PendingDeprecationWarning triggered by scipy.sparse's use of
# np.matrix. See issue #11251.
with pytest.warns(None) as record:
IsolationForest(max_samples='auto').fit(X)
user_warnings = [each for each in record
if issubclass(each.category, UserWarning)]
assert len(user_warnings) == 0
with pytest.warns(None) as record:
IsolationForest(max_samples=np.int64(2)).fit(X)
user_warnings = [each for each in record
if issubclass(each.category, UserWarning)]
assert len(user_warnings) == 0
assert_raises(ValueError, IsolationForest(max_samples='foobar').fit, X)
assert_raises(ValueError, IsolationForest(max_samples=1.5).fit, X)
# test X_test n_features match X_train one:
assert_raises(ValueError, IsolationForest().fit(X).predict, X[:, 1:])
# test that behaviour='old' will raise an error
msg = "The old behaviour of IsolationForest is not implemented anymore."
with pytest.raises(NotImplementedError, match=msg):
IsolationForest(behaviour='old').fit(X)
def test_iforest_sparse():
"""Check IForest for various parameter settings on sparse input."""
rng = check_random_state(0)
X_train, X_test, y_train, y_test = train_test_split(boston.data[:50],
boston.target[:50],
random_state=rng)
grid = ParameterGrid({"max_samples": [0.5, 1.0],
"bootstrap": [True, False]})
for sparse_format in [csc_matrix, csr_matrix]:
X_train_sparse = sparse_format(X_train)
X_test_sparse = sparse_format(X_test)
for params in grid:
# Trained on sparse format
sparse_classifier = IsolationForest(
n_estimators=10, random_state=1, **params).fit(X_train_sparse)
sparse_results = sparse_classifier.predict(X_test_sparse)
# Trained on dense format
dense_classifier = IsolationForest(
n_estimators=10, random_state=1, **params).fit(X_train)
dense_results = dense_classifier.predict(X_test)
assert_array_equal(sparse_results, dense_results)
def test_iforest():
"""Check Isolation Forest for various parameter settings."""
X_train = np.array([[0, 1], [1, 2]])
X_test = np.array([[2, 1], [1, 1]])
grid = ParameterGrid({"n_estimators": [3],
"max_samples": [0.5, 1.0, 3],
"bootstrap": [True, False]})
with ignore_warnings():
for params in grid:
IsolationForest(random_state=rng,
**params).fit(X_train).predict(X_test)
def test_iforest_performance():
"""Test Isolation Forest performs well"""
# Generate train/test data
rng = check_random_state(2)
X = 0.3 * rng.randn(120, 2)
X_train = np.r_[X + 2, X - 2]
X_train = X[:100]
# Generate some abnormal novel observations
X_outliers = rng.uniform(low=-4, high=4, size=(20, 2))
X_test = np.r_[X[100:], X_outliers]
y_test = np.array([0] * 20 + [1] * 20)
# fit the model
clf = IsolationForest(max_samples=100, random_state=rng).fit(X_train)
# predict scores (the lower, the more normal)
y_pred = - clf.decision_function(X_test)
# check that there is at most 6 errors (false positive or false negative)
assert roc_auc_score(y_test, y_pred) > 0.98
def test_iforest_subsampled_features():
# It tests non-regression for #5732 which failed at predict.
rng = check_random_state(0)
X_train, X_test, y_train, y_test = train_test_split(boston.data[:50],
boston.target[:50],
random_state=rng)
clf = IsolationForest(max_features=0.8)
clf.fit(X_train, y_train)
clf.predict(X_test)
def test_iforest_warm_start():
"""Test iterative addition of iTrees to an iForest """
rng = check_random_state(0)
X = rng.randn(20, 2)
# fit first 10 trees
clf = IsolationForest(n_estimators=10, max_samples=20,
random_state=rng, warm_start=True)
clf.fit(X)
# remember the 1st tree
tree_1 = clf.estimators_[0]
# fit another 10 trees
clf.set_params(n_estimators=20)
clf.fit(X)
# expecting 20 fitted trees and no overwritten trees
assert len(clf.estimators_) == 20
assert clf.estimators_[0] is tree_1
def test_iforest_works(contamination):
# toy sample (the last two samples are outliers)
X = [[-2, -1], [-1, -1], [-1, -2], [1, 1], [1, 2], [2, 1], [6, 3], [-4, 7]]
# Test IsolationForest
clf = IsolationForest(random_state=rng, contamination=contamination)
clf.fit(X)
decision_func = -clf.decision_function(X)
pred = clf.predict(X)
# assert detect outliers:
assert np.min(decision_func[-2:]) > np.max(decision_func[:-2])
assert_array_equal(pred, 6 * [1] + 2 * [-1])
def test_iforest_with_uniform_data():
"""Test whether iforest predicts inliers when using uniform data"""
# 2-d array of all 1s
X = np.ones((100, 10))
iforest = IsolationForest()
iforest.fit(X)
rng = np.random.RandomState(0)
assert all(iforest.predict(X) == 1)
assert all(iforest.predict(rng.randn(100, 10)) == 1)
assert all(iforest.predict(X + 1) == 1)
assert all(iforest.predict(X - 1) == 1)
# 2-d array where columns contain the same value across rows
X = np.repeat(rng.randn(1, 10), 100, 0)
iforest = IsolationForest()
iforest.fit(X)
assert all(iforest.predict(X) == 1)
assert all(iforest.predict(rng.randn(100, 10)) == 1)
assert all(iforest.predict(np.ones((100, 10))) == 1)
# Single row
X = rng.randn(1, 10)
iforest = IsolationForest()
iforest.fit(X)
assert all(iforest.predict(X) == 1)
assert all(iforest.predict(rng.randn(100, 10)) == 1)
assert all(iforest.predict(np.ones((100, 10))) == 1)
def test_iforest_deprecation():
iforest = IsolationForest(behaviour='new')
warn_msg = "'behaviour' is deprecated in 0.22 and will be removed in 0.24"
with pytest.warns(DeprecationWarning, match=warn_msg):
iforest.fit(iris.data)
import matplotlib.pyplot as plt
from mrex.ensemble import IsolationForest
rng = np.random.RandomState(42)
# Generate train data
X = 0.3 * rng.randn(100, 2)
X_train = np.r_[X + 2, X - 2]
# Generate some regular novel observations
X = 0.3 * rng.randn(20, 2)
X_test = np.r_[X + 2, X - 2]
# Generate some abnormal novel observations
X_outliers = rng.uniform(low=-4, high=4, size=(20, 2))
# fit the model
clf = IsolationForest(max_samples=100, random_state=rng)
clf.fit(X_train)
y_pred_train = clf.predict(X_train)
y_pred_test = clf.predict(X_test)
y_pred_outliers = clf.predict(X_outliers)
# plot the line, the samples, and the nearest vectors to the plane
xx, yy = np.meshgrid(np.linspace(-5, 5, 50), np.linspace(-5, 5, 50))
Z = clf.decision_function(np.c_[xx.ravel(), yy.ravel()])
Z = Z.reshape(xx.shape)
plt.title("IsolationForest")
plt.contourf(xx, yy, Z, cmap=plt.cm.Blues_r)
b1 = plt.scatter(X_train[:, 0], X_train[:, 1], c='white', s=20, edgecolor='k')
b2 = plt.scatter(X_test[:, 0], X_test[:, 1], c='green', s=20, edgecolor='k')
def test_iforest_parallel_regression():
"""Check parallel regression."""
rng = check_random_state(0)
X_train, X_test, y_train, y_test = train_test_split(boston.data,
boston.target,
random_state=rng)
ensemble = IsolationForest(n_jobs=3,
random_state=0).fit(X_train)
ensemble.set_params(n_jobs=1)
y1 = ensemble.predict(X_test)
ensemble.set_params(n_jobs=2)
y2 = ensemble.predict(X_test)
assert_array_almost_equal(y1, y2)
ensemble = IsolationForest(n_jobs=1,
random_state=0).fit(X_train)
y3 = ensemble.predict(X_test)
assert_array_almost_equal(y1, y3)
def test_recalculate_max_depth():
"""Check max_depth recalculation when max_samples is reset to n_samples"""
X = iris.data
clf = IsolationForest().fit(X)
for est in clf.estimators_:
assert est.max_depth == int(np.ceil(np.log2(X.shape[0])))
# Example settings
n_samples = 300
outliers_fraction = 0.15
n_outliers = int(outliers_fraction * n_samples)
n_inliers = n_samples - n_outliers
# define outlier/anomaly detection methods to be compared
anomaly_algorithms = [("Robust covariance",
EllipticEnvelope(contamination=outliers_fraction)),
("One-Class SVM",
svm.OneClassSVM(nu=outliers_fraction,
kernel="rbf",
gamma=0.1)),
("Isolation Forest",
IsolationForest(contamination=outliers_fraction,
random_state=42)),
("Local Outlier Factor",
LocalOutlierFactor(n_neighbors=35,
contamination=outliers_fraction))]
# Define datasets
blobs_params = dict(random_state=0, n_samples=n_inliers, n_features=2)
datasets = [
make_blobs(centers=[[0, 0], [0, 0]], cluster_std=0.5, **blobs_params)[0],
make_blobs(centers=[[2, 2], [-2, -2]],
cluster_std=[0.5, 0.5],
**blobs_params)[0],
make_blobs(centers=[[2, 2], [-2, -2]],
cluster_std=[1.5, .3],
**blobs_params)[0],
4. * (make_moons(n_samples=n_samples, noise=.05, random_state=0)[0] -
def test_max_samples_consistency():
# Make sure validated max_samples in iforest and BaseBagging are identical
X = iris.data
clf = IsolationForest().fit(X)
assert clf.max_samples_ == clf._max_samples
if dat in ('http', 'smtp'):
y = (y != b'normal.').astype(int)
print_outlier_ratio(y)
n_samples, n_features = X.shape
n_samples_train = n_samples // 2
X = X.astype(float)
X_train = X[:n_samples_train, :]
X_test = X[n_samples_train:, :]
y_train = y[:n_samples_train]
y_test = y[n_samples_train:]
print('--- Fitting the IsolationForest estimator...')
model = IsolationForest(n_jobs=-1, random_state=random_state)
tstart = time()
model.fit(X_train)
fit_time = time() - tstart
tstart = time()
scoring = -model.decision_function(X_test) # the lower, the more abnormal
print("--- Preparing the plot elements...")
if with_decision_function_histograms:
fig, ax = plt.subplots(3, sharex=True, sharey=True)
bins = np.linspace(-0.5, 0.5, 200)
ax[0].hist(scoring, bins, color='black')
ax[0].set_title('Decision function for %s dataset' % dat)
ax[1].hist(scoring[y_test == 0], bins, color='b', label='normal data')
ax[1].legend(loc="lower right")
