def test_performances():
X, y = make_blobs(n_samples=1000, random_state=0, centers=2)
# make labels imbalanced by remove all but 100 instances from class 1
indexes = np.ones(X.shape[0]).astype(bool)
ind = np.array([False] * 100 + list(((y == 1)[100:])))
indexes[ind] = 0
X = X[indexes]
y = y[indexes]
n_samples, n_features = X.shape
clf = SkopeRulesClassifier()
# fit
clf.fit(X, y)
# with lists
clf.fit(X.tolist(), y.tolist())
y_pred = clf.predict(X)
assert y_pred.shape == (n_samples, )
# training set performance
assert accuracy_score(y, y_pred) > 0.83
# decision_function agrees with predict
decision = -clf.decision_function(X)
assert decision.shape == (n_samples, )
dec_pred = (decision.ravel() < 0).astype(np.int)
assert_array_equal(dec_pred, y_pred)
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 = SkopeRulesClassifier(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)
assert True, 'deduplication works'
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 = SkopeRulesClassifier(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 np.min(decision_func[-2:]) > np.max(decision_func[:-2])
assert np.min(rules_vote[-2:]) > np.max(rules_vote[:-2])
assert 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])