def test_dimension_location():
"""
Test dimension and location of split.
"""
rng = np.random.RandomState(0)
X = rng.rand(100, 2)
X[:, 1] *= 100
y = rng.randn(100)
mtr = MondrianTreeRegressor(random_state=0, max_depth=1)
n = 1000
features = []
thresholds = []
for random_state in np.arange(1000):
mtr.set_params(random_state=random_state).fit(X, y)
features.append(mtr.tree_.feature[0])
thresholds.append(mtr.tree_.threshold[0])
# Check that this converges to the actual probability p of the bernoulli.
diff = np.max(X, axis=0) - np.min(X, axis=0)
p_act = diff / np.sum(diff)
features = np.array(features)
thresholds = np.array(thresholds)
counts = np.bincount(features)
p_sim = counts / np.sum(counts)
assert_array_almost_equal(p_act, p_sim, 2)
# Check that the split location converges to the (u + l) / 2 where
# u and l are the upper and lower bounds of the feature.
u = np.max(X, axis=0)[-1]
l = np.min(X, axis=0)[-1]
thresh_sim = np.mean(thresholds[features == 1])
thresh_act = (u + l) / 2.0
assert_array_almost_equal(thresh_act, thresh_sim, 2)
def test_tau():
"""
Test time of split for the root.
"""
X, y = make_regression(random_state=0, n_features=10)
rate = np.sum(np.max(X, axis=0) - np.min(X, axis=0))
mtr = MondrianTreeRegressor(random_state=0, max_depth=1)
taus = []
for random_state in np.arange(100):
mtr.set_params(random_state=random_state).fit(X, y)
taus.append(mtr.tree_.tau[0])
assert_almost_equal(np.mean(taus), 1.0 / rate, 2)
