def test_get_nb_skl_base_estimators(self):
X, y = random_binary_classification(40, 4)
rf = RandomForestClassifier(max_depth=2, n_estimators=4)
rf.fit(X, y)
n1 = get_nb_skl_base_estimators(rf, fitted=False)
n2 = get_nb_skl_base_estimators(rf, fitted=True)
self.assertEqual(n1, 2)
self.assertEqual(n2, 5)
def __init__(self, dim=None, **opts):
# Models are fitted here. Every not measured
# should take place here.
assert dim is not None
BenchPerfTest.__init__(self, **opts)
self.model1 = SGDClassifier()
self.model2 = make_pipeline(PolynomialFeatures(), SGDClassifier())
self.model3 = make_pipeline(
ExtendedFeatures(kind='poly'), SGDClassifier())
self.model4 = make_pipeline(ExtendedFeatures(
kind='poly-slow'), SGDClassifier())
X, y = random_binary_classification(10000, dim)
self.model1.fit(PolynomialFeatures().fit_transform(X), y)
self.model2.fit(X, y)
self.model3.fit(X, y)
self.model4.fit(X, y)
def data(self, N=None, dim=None, **opts):
# The benchmark requires a new datasets each time.
assert N is not None
assert dim is not None
return random_binary_classification(N, dim)
def test_random_binary_classification(self):
X, y = random_binary_classification(40, 4)
self.assertEqual(X.shape, (40, 4))
self.assertEqual(y.shape, (40, ))
self.assertEqual(len(set(y)), 2)
self.assertIn(y.dtype, (numpy.int32, numpy.int64))