def test_node_weights():
"""
Test the implementation of node_weights.
"""
rng = np.random.RandomState(0)
boston = load_boston()
X, y = boston.data, boston.target
n_train = 100
n_test = 100
X_train, y_train = X[:n_train], y[:n_train]
X_test, y_test = X[-n_test:], y[-n_test:]
minmax = MinMaxScaler()
X_train = minmax.fit_transform(X_train)
X_test = minmax.transform(X_test)
# Test that when all samples are in the training data all weights
# should be concentrated at the leaf.
mtr = MondrianTreeRegressor(random_state=0)
mtr.fit(X_train, y_train)
leaf_nodes = mtr.apply(X_train)
weights_sparse = mtr.weighted_decision_path(X_train)
assert_array_equal(weights_sparse.data, np.ones(X_train.shape[0]))
assert_array_equal(weights_sparse.indices, leaf_nodes)
assert_array_equal(weights_sparse.indptr, np.arange(n_train + 1))
# Test prediction using the node_weights function gives similar results
# to that using the prediction method.
weights = mtr.weighted_decision_path(X_test)
node_means = mtr.tree_.mean
node_variances = mtr.tree_.variance
variances1 = []
means1 = []
for startptr, endptr in zip(weights.indptr[:-1], weights.indptr[1:]):
curr_nodes = weights.indices[startptr:endptr]
curr_weights = weights.data[startptr:endptr]
curr_means = node_means[curr_nodes]
curr_var = node_variances[curr_nodes]
means1.append(np.sum(curr_weights * curr_means))
variances1.append(np.sum(curr_weights * (curr_var + curr_means**2)))
means1 = np.array(means1)
variances1 = np.array(variances1)
variances1 -= means1**2
means2, std2 = mtr.predict(X_test, return_std=True)
assert_array_almost_equal(means1, means2, 5)
assert_array_almost_equal(variances1, std2**2, 3)
def test_weighted_decision_path_test_regression():
X_train, X_test, y_train, y_test = load_scaled_boston()
n_train = X_train.shape[0]
mtr = MondrianTreeRegressor(random_state=0)
mtr.fit(X_train, y_train)
weights = mtr.weighted_decision_path(X_test)
node_means = mtr.tree_.mean
node_variances = mtr.tree_.variance
variances1 = []
means1 = []
for startptr, endptr in zip(weights.indptr[:-1], weights.indptr[1:]):
curr_nodes = weights.indices[startptr:endptr]
curr_weights = weights.data[startptr:endptr]
curr_means = node_means[curr_nodes]
curr_var = node_variances[curr_nodes]
means1.append(np.sum(curr_weights * curr_means))
variances1.append(np.sum(curr_weights * (curr_var + curr_means**2)))
means1 = np.array(means1)
variances1 = np.array(variances1)
variances1 -= means1**2
means2, std2 = mtr.predict(X_test, return_std=True)
assert_array_almost_equal(means1, means2, 5)
assert_array_almost_equal(variances1, std2**2, 3)