def test_var(self,):
# test that the estimator calcualtes var correctly
config = self._get_base_config()
config['honest'] = True
config['max_depth'] = 0
config['inference'] = True
config['n_estimators'] = 1000
config['subforest_size'] = 2
config['max_samples'] = .5
config['n_jobs'] = 1
n_features = 2
# test api
n = 100
random_state = 123
X, y, truth = self._get_regression_data(n, n_features, random_state)
forest = RegressionForest(**config).fit(X, y)
alpha = .1
mean, var = forest.predict_and_var(X)
lb = scipy.stats.norm.ppf(alpha / 2, loc=mean[:, 0], scale=np.sqrt(var[:, 0, 0])).reshape(-1, 1)
ub = scipy.stats.norm.ppf(1 - alpha / 2, loc=mean[:, 0], scale=np.sqrt(var[:, 0, 0])).reshape(-1, 1)
np.testing.assert_allclose(var, forest.predict_var(X))
lbtest, ubtest = forest.predict_interval(X, alpha=alpha)
np.testing.assert_allclose(lb, lbtest)
np.testing.assert_allclose(ub, ubtest)
meantest, lbtest, ubtest = forest.predict(X, interval=True, alpha=alpha)
np.testing.assert_allclose(mean, meantest)
np.testing.assert_allclose(lb, lbtest)
np.testing.assert_allclose(ub, ubtest)
np.testing.assert_allclose(np.sqrt(var[:, 0, 0]), forest.prediction_stderr(X)[:, 0])
# test accuracy
for n in [10, 100, 1000, 10000]:
random_state = 123
X, y, truth = self._get_regression_data(n, n_features, random_state)
forest = RegressionForest(**config).fit(X, y)
our_mean, our_var = forest.predict_and_var(X[:1])
true_mean, true_var = np.mean(y), np.var(y) / y.shape[0]
np.testing.assert_allclose(our_mean, true_mean, atol=0.05)
np.testing.assert_allclose(our_var, true_var, atol=0.05, rtol=.1)
for n, our_thr, true_thr in [(1000, .5, .25), (10000, .05, .05)]:
random_state = 123
config['max_depth'] = 1
X, y, truth = self._get_step_regression_data(n, n_features, random_state)
forest = RegressionForest(**config).fit(X, y)
posX = X[X[:, 0] > our_thr]
negX = X[X[:, 0] < -our_thr]
our_pos_mean, our_pos_var = forest.predict_and_var(posX)
our_neg_mean, our_neg_var = forest.predict_and_var(negX)
pos = X[:, 0] > true_thr
true_pos_mean, true_pos_var = np.mean(y[pos]), np.var(y[pos]) / y[pos].shape[0]
neg = X[:, 0] < -true_thr
true_neg_mean, true_neg_var = np.mean(y[neg]), np.var(y[neg]) / y[neg].shape[0]
np.testing.assert_allclose(our_pos_mean, true_pos_mean, atol=0.07)
np.testing.assert_allclose(our_pos_var, true_pos_var, atol=0.0, rtol=.25)
np.testing.assert_allclose(our_neg_mean, true_neg_mean, atol=0.07)
np.testing.assert_allclose(our_neg_var, true_neg_var, atol=0.0, rtol=.25)
return
def test_projection(self, ):
# test the projection functionality of forests
# test that the estimator calcualtes var correctly
np.set_printoptions(precision=10, suppress=True)
config = self._get_base_config()
config['honest'] = True
config['max_depth'] = 0
config['inference'] = True
config['n_estimators'] = 100
config['subforest_size'] = 2
config['max_samples'] = .5
config['n_jobs'] = 1
n_features = 2
# test api
n = 100
random_state = 123
X, y, truth = self._get_regression_data(n, n_features, random_state)
forest = RegressionForest(**config).fit(X, y)
mean, var = forest.predict_and_var(X)
mean = mean.flatten()
var = var.flatten()
y = np.hstack([y, y])
truth = np.hstack([truth, truth])
forest = RegressionForest(**config).fit(X, y)
projector = np.ones((X.shape[0], 2)) / 2.0
mean_proj, var_proj = forest.predict_projection_and_var(X, projector)
np.testing.assert_array_equal(mean_proj, mean)
np.testing.assert_array_equal(var_proj, var)
np.testing.assert_array_equal(
var_proj, forest.predict_projection_var(X, projector))
np.testing.assert_array_equal(mean_proj,
forest.predict_projection(X, projector))
return