def test_random_state(self):
np.random.seed(123)
n = 5000
d = 5
x_grid = np.linspace(-1, 1, 10)
X_test = np.hstack(
[x_grid.reshape(-1, 1),
np.random.normal(size=(10, d - 1))])
X = np.random.normal(0, 1, size=(n, d))
y = X[:, 0] + np.random.normal(0, .1, size=(n, ))
est = SubsampledHonestForest(n_estimators=100,
max_depth=5,
min_samples_leaf=10,
verbose=0,
random_state=12345)
est.fit(X, y)
point1 = est.predict(X_test)
est = SubsampledHonestForest(n_estimators=100,
max_depth=5,
min_samples_leaf=10,
verbose=0,
random_state=12345)
est.fit(X, y)
point2 = est.predict(X_test)
# Check that the point estimates are the same
np.testing.assert_equal(point1, point2)
def test_dishonest_y1d(self):
np.random.seed(123)
n = 5000
d = 1
x_grid = np.linspace(-1, 1, 10)
X_test = np.hstack(
[x_grid.reshape(-1, 1),
np.random.normal(size=(10, d - 1))])
for _ in range(3):
X = np.random.normal(0, 1, size=(n, d))
y = 1. * (X[:, 0] > 0) + np.random.normal(0, .1, size=(n, ))
est = SubsampledHonestForest(n_estimators=100,
honest=False,
max_depth=3,
min_samples_leaf=10,
verbose=0)
est.fit(X, y)
point = est.predict(X_test)
lb, ub = est.predict_interval(X_test, alpha=0.01)
np.testing.assert_allclose(point,
1 * (X_test[:, 0] > 0),
rtol=0,
atol=.2)
np.testing.assert_array_less(lb, 1 * (X_test[:, 0] > 0) + .05)
np.testing.assert_array_less(1 * (X_test[:, 0] > 0), ub + .05)
def test_y2d(self):
np.random.seed(123)
n = 5000
d = 5
x_grid = np.linspace(-1, 1, 10)
X_test = np.hstack(
[x_grid.reshape(-1, 1),
np.random.normal(size=(10, d - 1))])
for _ in range(3):
for criterion in ['mse', 'mae']:
X = np.random.normal(0, 1, size=(n, d))
y = X[:, [0, 0]] + np.random.normal(0, .1, size=(n, 2))
est = SubsampledHonestForest(n_estimators=100,
max_depth=5,
criterion=criterion,
min_samples_leaf=10,
verbose=0)
est.fit(X, y)
point = est.predict(X_test)
lb, ub = est.predict_interval(X_test, alpha=0.01)
np.testing.assert_allclose(point,
X_test[:, [0, 0]],
rtol=0,
atol=.2)
np.testing.assert_array_less(lb, X_test[:, [0, 0]] + .05)
np.testing.assert_array_less(X_test[:, [0, 0]], ub + .05)
def test_nonauto_subsample_fr(self):
np.random.seed(123)
n = 5000
d = 5
x_grid = np.linspace(-1, 1, 10)
X_test = np.hstack([x_grid.reshape(-1, 1), np.random.normal(size=(10, d - 1))])
X = np.random.normal(0, 1, size=(n, d))
y = X[:, 0] + np.random.normal(0, .1, size=(n,))
est = SubsampledHonestForest(n_estimators=100, subsample_fr=.8, max_depth=5, min_samples_leaf=10, verbose=0)
est.fit(X, y)
point = est.predict(X_test)
lb, ub = est.predict_interval(X_test, alpha=0.01)
np.testing.assert_allclose(point, X_test[:, 0], rtol=0, atol=.2)
np.testing.assert_array_less(lb, X_test[:, 0] + .05)
np.testing.assert_array_less(X_test[:, 0], ub + .05)
def monte_carlo():
n = 5000
d = 5
x_grid = np.linspace(-1, 1, 1000)
X_test = np.hstack(
[x_grid.reshape(-1, 1),
np.random.normal(size=(1000, d - 1))])
coverage = []
exp_dict = {'point': [], 'low': [], 'up': []}
for it in range(100):
print(it)
X = np.random.normal(0, 1, size=(n, d))
y = X[:, 0] + np.random.normal(size=(n, ))
est = SubsampledHonestForest(n_estimators=1000, verbose=1)
est.fit(X, y)
point = est.predict(X_test)
low, up = est.predict_interval(X_test, alpha=0.05)
coverage.append((low <= x_grid) & (x_grid <= up))
exp_dict['point'].append(point)
exp_dict['low'].append(low)
exp_dict['up'].append(up)
if not os.path.exists('figures'):
os.makedirs('figures')
if not os.path.exists(os.path.join("figures", 'honestforest')):
os.makedirs(os.path.join("figures", 'honestforest'))
plt.figure()
plt.plot(x_grid, np.mean(coverage, axis=0))
plt.savefig('figures/honestforest/coverage.png')
plt.figure()
plt.plot(x_grid,
np.sqrt(np.mean((np.array(exp_dict['point']) - x_grid)**2,
axis=0)),
label='RMSE')
plt.savefig('figures/honestforest/rmse.png')
plt.figure()
plt.plot(x_grid,
np.mean(np.array(exp_dict['up']) - np.array(exp_dict['low']),
axis=0),
label='length')
plt.savefig('figures/honestforest/length.png')
def __init__(self,
model_y, model_t,
discrete_treatment=False,
n_crossfit_splits=2,
n_estimators=100,
criterion="mse",
max_depth=None,
min_samples_split=2,
min_samples_leaf=1,
min_weight_fraction_leaf=0.,
max_features="auto",
max_leaf_nodes=None,
min_impurity_decrease=0.,
subsample_fr='auto',
honest=True,
n_jobs=None,
verbose=0,
random_state=None):
model_final = SubsampledHonestForest(n_estimators=n_estimators,
criterion=criterion,
max_depth=max_depth,
min_samples_split=min_samples_split,
min_samples_leaf=min_samples_leaf,
min_weight_fraction_leaf=min_weight_fraction_leaf,
max_features=max_features,
max_leaf_nodes=max_leaf_nodes,
min_impurity_decrease=min_impurity_decrease,
subsample_fr=subsample_fr,
honest=honest,
n_jobs=n_jobs,
random_state=random_state,
verbose=verbose)
super().__init__(model_y=model_y, model_t=model_t,
model_final=model_final, featurizer=None,
discrete_treatment=discrete_treatment,
n_splits=n_crossfit_splits, random_state=random_state)