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 = SkopeRules()
# fit
clf.fit(X, y)
# with lists
clf.fit(X.tolist(), y.tolist())
y_pred = clf.predict(X)
assert_equal(y_pred.shape, (n_samples, ))
# training set performance
assert_greater(accuracy_score(y, y_pred), 0.83)
# decision_function agrees with predict
decision = -clf.decision_function(X)
assert_equal(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 = 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)
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])
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 SkopeRules estimator...')
model = SkopeRules(n_estimators=5, max_depth=5, n_jobs=-1)
tstart = time()
model.fit(X_train, y_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)
O = 0.5 * rng.randn(n_outliers, 2)
X_outliers = O # np.r_[O, O + [2, -2]]
X_train = np.r_[X_inliers, X_outliers]
y_train = [0] * n_inliers + [1] * n_outliers
###############################################################################
# Training the SkopeRules classifier
# ..................................
# fit the model
clf = SkopeRules(random_state=rng, n_estimators=10)
clf.fit(X_train, y_train)
# 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("Skope Rules, value of the decision_function method")
plt.contourf(xx, yy, Z, cmap=plt.cm.Blues)
a = plt.scatter(X_inliers[:, 0],
X_inliers[:, 1],
c='white',
s=20,
edgecolor='k')
b = plt.scatter(X_outliers[:, 0],
X_outliers[:, 1],
c='red',
s=20,
edgecolor='k')
