def test_min_variance():
rng = np.random.RandomState(0)
X = rng.normal(size=(1000, 1))
y = np.ones(1000)
rf = RandomForestRegressor(min_variance=0.1)
rf.fit(X, y)
mean, std = rf.predict(X, return_std=True)
assert_array_almost_equal(mean, y)
assert_array_almost_equal(std, np.sqrt(0.1 * np.ones(1000)))
def test_min_variance():
rng = np.random.RandomState(0)
X = rng.normal(size=(1000, 1))
y = np.ones(1000)
rf = RandomForestRegressor(min_variance=0.1)
rf.fit(X, y)
mean, std = rf.predict(X, return_std=True)
assert_array_almost_equal(mean, y)
assert_array_almost_equal(std, np.sqrt(0.1*np.ones(1000)))
def rfbo_cycle(ndim,
space,
target_f,
n_iters=10,
acq_function=ei,
n_samples=int(1.0e+5),
model=None,
show_progress=True):
xrange = (lambda title, n: tqdm_notebook(range(n), postfix=title)
) if show_progress else (lambda title, n: range(n))
space = np.array(space)
if model is None:
model = RandomForestRegressor(n_estimators=200,
n_jobs=20,
min_variance=1.0e-3,
random_state=1234)
known_points = []
known_values = []
cost = []
for i in xrange('BO iteration', n_iters):
acq = acq_function(model, known_points, known_values)
candidates = np.random.uniform(size=(
n_samples,
ndim,
))
f = acq(candidates)
best = np.argmin(f)
suggestion = reverse_transform(candidates[best].reshape(1, -1),
space)[0, :]
point_cost, observed = target_f(suggestion)
known_points.append(suggestion)
known_values.append(observed)
cost.append(point_cost)
model.fit(transform(np.array(known_points), space),
np.array(known_values))
yield model, acq, space, known_points, known_values, cost
def test_random_forest():
# toy sample
X = [[-2, -1], [-1, -1], [-1, -2], [1, 1], [1, 2], [2, 1]]
y = [-1, -1, -1, 1, 1, 1]
T = [[-1, -1], [2, 2], [3, 2]]
true_result = [-1, 1, 1]
clf = RandomForestRegressor(n_estimators=10, random_state=1)
clf.fit(X, y)
assert_array_equal(clf.predict(T), true_result)
assert 10 == len(clf)
clf = RandomForestRegressor(n_estimators=10,
min_impurity_decrease=0.1,
random_state=1)
clf.fit(X, y)
assert_array_equal(clf.predict(T), true_result)
assert 10 == len(clf)
clf = RandomForestRegressor(n_estimators=10,
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.,
bootstrap=True,
oob_score=False,
n_jobs=1,
random_state=1,
verbose=0,
warm_start=False)
clf.fit(X, y)
assert_array_equal(clf.predict(T), true_result)
assert 10 == len(clf)
clf = RandomForestRegressor(n_estimators=10,
max_features=1,
random_state=1)
clf.fit(X, y)
assert_array_equal(clf.predict(T), true_result)
assert 10 == len(clf)
# also test apply
leaf_indices = clf.apply(X)
assert leaf_indices.shape == (len(X), clf.n_estimators)