def test_deduplication_works():
# 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]]
y = [0] * 6 + [1] * 2
X_test = [[-2, -1], [-1, -1], [-1, -2], [1, 1], [1, 2], [2, 1], [10, 5],
[5, -7]]
# Test LOF
clf = SkopeRules(random_state=rng, max_samples=1., max_depth_duplication=3)
clf.fit(X, y)
decision_func = clf.decision_function(X_test)
rules_vote = clf.rules_vote(X_test)
score_top_rules = clf.score_top_rules(X_test)
pred = clf.predict(X_test)
pred_score_top_rules = clf.predict_top_rules(X_test, 1)
def test_skope_rules_works():
# 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]]
y = [0] * 6 + [1] * 2
X_test = [[-2, -1], [-1, -1], [-1, -2], [1, 1], [1, 2], [2, 1], [10, 5],
[5, -7]]
# Test LOF
clf = SkopeRules(random_state=rng, max_samples=1.)
clf.fit(X, y)
decision_func = clf.decision_function(X_test)
rules_vote = clf.rules_vote(X_test)
score_top_rules = clf.score_top_rules(X_test)
pred = clf.predict(X_test)
pred_score_top_rules = clf.predict_top_rules(X_test, 1)
# assert detect outliers:
assert_greater(np.min(decision_func[-2:]), np.max(decision_func[:-2]))
assert_greater(np.min(rules_vote[-2:]), np.max(rules_vote[:-2]))
assert_greater(np.min(score_top_rules[-2:]), np.max(score_top_rules[:-2]))
assert_array_equal(pred, 6 * [0] + 2 * [1])
assert_array_equal(pred_score_top_rules, 6 * [0] + 2 * [1])
###############################################################################
# Extracting top rules
# ....................
#
# On the 4 following figures, the predict_top_rules method is used with
# several values of n_rules. n_rules = 2 means that the prediction is
# done using only the 2 best rules.
print('The 4 most precise rules are the following:')
for rule in clf.rules_[:4]:
print(rule[0])
fig, axes = plt.subplots(2, 2, figsize=(12, 5), sharex=True, sharey=True)
for i_ax, ax in enumerate(np.ravel(axes)):
Z = clf.predict_top_rules(np.c_[xx.ravel(), yy.ravel()], i_ax + 1)
Z = Z.reshape(xx.shape)
ax.set_title("Prediction with predict_top_rules, n_rules=" + str(i_ax + 1))
ax.contourf(xx, yy, Z, cmap=plt.cm.Blues)
a = ax.scatter(X_inliers[:, 0],
X_inliers[:, 1],
c='white',
s=20,
edgecolor='k')
b = ax.scatter(X_outliers[:, 0],
X_outliers[:, 1],
c='red',
s=20,
edgecolor='k')
ax.axis('tight')