def simulate_predictions(n=100, seed=None):
"""simulate classifier predictions for data size of n
"""
if seed is None:
seed = random_seed()
np.random.seed(seed % (2 ** 32))
probas = np.random.random(n)
classes = [discrete_sample({0: (1 - p), 1: p}) for p in probas]
return classes, probas
def simulate_predictions(n=100, seed=None):
"""simulate classifier predictions for data size of n
"""
if seed is None:
seed = random_seed()
np.random.seed(seed % (2 ** 32))
probas = np.random.random(n)
classes = [discrete_sample({0: (1 - p), 1: p}) for p in probas]
return classes, probas
def test_roc_simulated():
# Test Area under Receiver Operating Characteristic (ROC) curve
for _ in range(10):
y_true, probas_pred = simulate_predictions(1000, seed=random_seed())
rc = RocCurve.from_labels(y_true, probas_pred)
auc_expected1 = _auc(rc.fprs, rc.tprs)
auc_expected2 = auc_sklearn(y_true, probas_pred)
auc_actual = roc_auc_score(y_true, probas_pred)
assert_almost_equal(auc_expected1, auc_actual, 3)
assert_almost_equal(auc_expected2, auc_actual, 3)
def test_roc_simulated():
# Test Area under Receiver Operating Characteristic (ROC) curve
for _ in range(10):
y_true, probas_pred = simulate_predictions(1000, seed=random_seed())
rc = RocCurve.from_labels(y_true, probas_pred)
auc_expected1 = _auc(rc.fprs, rc.tprs)
auc_expected2 = auc_sklearn(y_true, probas_pred)
auc_actual = roc_auc_score(y_true, probas_pred)
assert_almost_equal(auc_expected1, auc_actual, 3)
assert_almost_equal(auc_expected2, auc_actual, 3)
