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_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_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_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)
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')
c = plt.scatter(X_outliers[:, 0],
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")
ax[2].hist(scoring[y_test == 1], bins, color='r', label='outliers')
ax[2].legend(loc="lower right")
