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)
separate_rules_score = clf.separate_rules_score(X_test)
pred = clf.predict(X_test)
# 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(separate_rules_score[-2:]),
np.max(separate_rules_score[:-2]))
assert_array_equal(pred, 6 * [0] + 2 * [1])
# This part shows how SkopeRules can be fitted to detect credit defaults.
# Performances are compared with the random forest model previously trained.
# fit the model
clf = SkopeRules(
similarity_thres=.9, max_depth=3, max_features=0.5,
max_samples_features=0.5, random_state=rng, n_estimators=30,
feature_names=feature_names, recall_min=0.02, precision_min=0.6
)
clf.fit(X_train, y_train)
# in the separate_rules_score method, a score of k means that rule number k
# vote positively, but not rules 1, ..., k-1. It will allow us to plot
# performance of each rule separately on ROC and PR plots.
scoring = clf.separate_rules_score(X_test)
print(str(len(clf.rules_)) + ' rules have been built.')
print('The most precise rules are the following:')
print(clf.rules_[:5])
curves = [roc_curve, precision_recall_curve]
xlabels = ['False Positive Rate', 'Recall (True Positive Rate)']
ylabels = ['True Positive Rate (Recall)', 'Precision']
fig, axes = plt.subplots(1, 2, figsize=(12, 5),
sharex=True, sharey=True)
ax = axes[0]
fpr, tpr, _ = roc_curve(y_test, scoring)