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_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_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
# 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],
X_outliers[:, 1],
c='red',
s=20,
edgecolor='k')
plt.axis('tight')
plt.xlim((-5, 5))
plt.ylim((-5, 5))
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")
# Show ROC Curves
predict_time = time() - tstart
fpr, tpr, thresholds = roc_curve(y_test, scoring)