def check_multioutput(name):
# Check estimators on multi-output problems.
X_train = [[-2, -1], [-1, -1], [-1, -2], [1, 1], [1, 2], [2, 1], [-2, 1],
[-1, 1], [-1, 2], [2, -1], [1, -1], [1, -2]]
y_train = [[-1, 0], [-1, 0], [-1, 0], [1, 1], [1, 1], [1, 1], [-1, 2],
[-1, 2], [-1, 2], [1, 3], [1, 3], [1, 3]]
X_test = [[-1, -1], [1, 1], [-1, 1], [1, -1]]
y_test = [[-1, 0], [1, 1], [-1, 2], [1, 3]]
est = FOREST_ESTIMATORS[name](random_state=0, bootstrap=False)
y_pred = est.fit(X_train, y_train).predict(X_test)
assert_array_almost_equal(y_pred, y_test)
if name in FOREST_CLASSIFIERS:
with np.errstate(divide="ignore"):
proba = est.predict_proba(X_test)
assert_equal(len(proba), 2)
assert_equal(proba[0].shape, (4, 2))
assert_equal(proba[1].shape, (4, 4))
log_proba = est.predict_log_proba(X_test)
assert_equal(len(log_proba), 2)
assert_equal(log_proba[0].shape, (4, 2))
assert_equal(log_proba[1].shape, (4, 4))
def check_boston(presort, loss, subsample):
# Check consistency on dataset boston house prices with least squares
# and least absolute deviation.
ones = np.ones(len(boston.target))
last_y_pred = None
for sample_weight in None, ones, 2 * ones:
clf = GradientBoostingRegressor(n_estimators=100,
loss=loss,
max_depth=4,
subsample=subsample,
min_samples_split=2,
random_state=1,
presort=presort)
assert_raises(ValueError, clf.predict, boston.data)
clf.fit(boston.data, boston.target, sample_weight=sample_weight)
leaves = clf.apply(boston.data)
assert_equal(leaves.shape, (506, 100))
y_pred = clf.predict(boston.data)
mse = mean_squared_error(boston.target, y_pred)
assert_less(mse, 6.0)
if last_y_pred is not None:
assert_array_almost_equal(last_y_pred, y_pred)
last_y_pred = y_pred
def test_compute_class_weight_invariance():
# Test that results with class_weight="balanced" is invariant wrt
# class imbalance if the number of samples is identical.
# The test uses a balanced two class dataset with 100 datapoints.
# It creates three versions, one where class 1 is duplicated
# resulting in 150 points of class 1 and 50 of class 0,
# one where there are 50 points in class 1 and 150 in class 0,
# and one where there are 100 points of each class (this one is balanced
# again).
# With balancing class weights, all three should give the same model.
X, y = make_blobs(centers=2, random_state=0)
# create dataset where class 1 is duplicated twice
X_1 = np.vstack([X] + [X[y == 1]] * 2)
y_1 = np.hstack([y] + [y[y == 1]] * 2)
# create dataset where class 0 is duplicated twice
X_0 = np.vstack([X] + [X[y == 0]] * 2)
y_0 = np.hstack([y] + [y[y == 0]] * 2)
# duplicate everything
X_ = np.vstack([X] * 2)
y_ = np.hstack([y] * 2)
# results should be identical
logreg1 = LogisticRegression(class_weight="balanced").fit(X_1, y_1)
logreg0 = LogisticRegression(class_weight="balanced").fit(X_0, y_0)
logreg = LogisticRegression(class_weight="balanced").fit(X_, y_)
assert_array_almost_equal(logreg1.coef_, logreg0.coef_)
assert_array_almost_equal(logreg.coef_, logreg0.coef_)
def test_logsumexp():
# Try to add some smallish numbers in logspace
x = np.array([1e-40] * 1000000)
logx = np.log(x)
assert_almost_equal(np.exp(logsumexp(logx)), x.sum())
X = np.vstack([x, x])
logX = np.vstack([logx, logx])
assert_array_almost_equal(np.exp(logsumexp(logX, axis=0)), X.sum(axis=0))
assert_array_almost_equal(np.exp(logsumexp(logX, axis=1)), X.sum(axis=1))
def test_logistic_sigmoid():
# Check correctness and robustness of logistic sigmoid implementation
def naive_log_logistic(x):
return np.log(1 / (1 + np.exp(-x)))
x = np.linspace(-2, 2, 50)
assert_array_almost_equal(log_logistic(x), naive_log_logistic(x))
extreme_x = np.array([-100., 100.])
assert_array_almost_equal(log_logistic(extreme_x), [-100, 0])
def test_oob_improvement():
# Test if oob improvement has correct shape and regression test.
clf = GradientBoostingClassifier(n_estimators=100,
random_state=1,
subsample=0.5)
clf.fit(X, y)
assert_equal(clf.oob_improvement_.shape[0], 100)
# hard-coded regression test - change if modification in OOB computation
assert_array_almost_equal(clf.oob_improvement_[:5],
np.array([0.19, 0.15, 0.12, -0.12, -0.11]),
decimal=2)
def test_warm_start_equal_n_estimators():
# Test if warm start with equal n_estimators does nothing
X, y = datasets.make_hastie_10_2(n_samples=100, random_state=1)
for Cls in [GradientBoostingRegressor, GradientBoostingClassifier]:
est = Cls(n_estimators=100, max_depth=1)
est.fit(X, y)
est2 = clone(est)
est2.set_params(n_estimators=est.n_estimators, warm_start=True)
est2.fit(X, y)
assert_array_almost_equal(est2.predict(X), est.predict(X))
def check_probability(name):
# Predict probabilities.
ForestClassifier = FOREST_CLASSIFIERS[name]
with np.errstate(divide="ignore"):
clf = ForestClassifier(n_estimators=10,
random_state=1,
max_features=1,
max_depth=1)
clf.fit(iris.data, iris.target)
assert_array_almost_equal(np.sum(clf.predict_proba(iris.data), axis=1),
np.ones(iris.data.shape[0]))
assert_array_almost_equal(clf.predict_proba(iris.data),
np.exp(clf.predict_log_proba(iris.data)))
def test_warm_start_n_estimators():
# Test if warm start equals fit - set n_estimators.
X, y = datasets.make_hastie_10_2(n_samples=100, random_state=1)
for Cls in [GradientBoostingRegressor, GradientBoostingClassifier]:
est = Cls(n_estimators=300, max_depth=1)
est.fit(X, y)
est_ws = Cls(n_estimators=100, max_depth=1, warm_start=True)
est_ws.fit(X, y)
est_ws.set_params(n_estimators=300)
est_ws.fit(X, y)
assert_array_almost_equal(est_ws.predict(X), est.predict(X))
def test_warm_start_clear():
# Test if fit clears state.
X, y = datasets.make_hastie_10_2(n_samples=100, random_state=1)
for Cls in [GradientBoostingRegressor, GradientBoostingClassifier]:
est = Cls(n_estimators=100, max_depth=1)
est.fit(X, y)
est_2 = Cls(n_estimators=100, max_depth=1, warm_start=True)
est_2.fit(X, y) # inits state
est_2.set_params(warm_start=False)
est_2.fit(X, y) # clears old state and equals est
assert_array_almost_equal(est_2.predict(X), est.predict(X))
def check_parallel(name, X, y):
"""Check parallel computations in classification"""
ForestEstimator = FOREST_ESTIMATORS[name]
forest = ForestEstimator(n_estimators=10, n_jobs=3, random_state=0)
forest.fit(X, y)
assert_equal(len(forest), 10)
forest.set_params(n_jobs=1)
y1 = forest.predict(X)
forest.set_params(n_jobs=2)
y2 = forest.predict(X)
assert_array_almost_equal(y1, y2, 3)
def test_compute_class_weight_auto_unordered():
# Test compute_class_weight when classes are unordered
classes = np.array([1, 0, 3])
y = np.asarray([1, 0, 0, 3, 3, 3])
cw = assert_warns(DeprecationWarning, compute_class_weight, "auto",
classes, y)
assert_almost_equal(cw.sum(), classes.shape)
assert_equal(len(cw), len(classes))
assert_array_almost_equal(cw, np.array([1.636, 0.818, 0.545]), decimal=3)
cw = compute_class_weight("balanced", classes, y)
class_counts = np.bincount(y)[classes]
assert_almost_equal(np.dot(cw, class_counts), y.shape[0])
assert_array_almost_equal(cw, [2., 1., 2. / 3])
def test_compute_class_weight_auto_negative():
# Test compute_class_weight when labels are negative
# Test with balanced class labels.
classes = np.array([-2, -1, 0])
y = np.asarray([-1, -1, 0, 0, -2, -2])
cw = assert_warns(DeprecationWarning, compute_class_weight, "auto",
classes, y)
assert_almost_equal(cw.sum(), classes.shape)
assert_equal(len(cw), len(classes))
assert_array_almost_equal(cw, np.array([1., 1., 1.]))
cw = compute_class_weight("balanced", classes, y)
assert_equal(len(cw), len(classes))
assert_array_almost_equal(cw, np.array([1., 1., 1.]))
# Test with unbalanced class labels.
y = np.asarray([-1, 0, 0, -2, -2, -2])
cw = assert_warns(DeprecationWarning, compute_class_weight, "auto",
classes, y)
assert_almost_equal(cw.sum(), classes.shape)
assert_equal(len(cw), len(classes))
assert_array_almost_equal(cw, np.array([0.545, 1.636, 0.818]), decimal=3)
cw = compute_class_weight("balanced", classes, y)
assert_equal(len(cw), len(classes))
class_counts = np.bincount(y + 2)
assert_almost_equal(np.dot(cw, class_counts), y.shape[0])
assert_array_almost_equal(cw, [2. / 3, 2., 1.])
def test_random_weights():
# set this up so that each row should have a weighted mode of 6,
# with a score that is easily reproduced
mode_result = 6
rng = np.random.RandomState(0)
x = rng.randint(mode_result, size=(100, 10))
w = rng.random_sample(x.shape)
x[:, :5] = mode_result
w[:, :5] += 1
mode, score = weighted_mode(x, w, axis=1)
assert_array_equal(mode, mode_result)
assert_array_almost_equal(score.ravel(), w[:, :5].sum(1))
def test_parallel_train():
rng = check_random_state(12321)
n_samples, n_features = 80, 30
X_train = rng.randn(n_samples, n_features)
y_train = rng.randint(0, 2, n_samples)
clfs = [
RandomForestClassifier(n_estimators=20,
n_jobs=n_jobs,
random_state=12345).fit(X_train, y_train)
for n_jobs in [1, 2, 3, 8, 16, 32]
]
X_test = rng.randn(n_samples, n_features)
probas = [clf.predict_proba(X_test) for clf in clfs]
for proba1, proba2 in zip(probas, probas[1:]):
assert_array_almost_equal(proba1, proba2)
def test_warm_start_oob():
# Test if warm start OOB equals fit.
X, y = datasets.make_hastie_10_2(n_samples=100, random_state=1)
for Cls in [GradientBoostingRegressor, GradientBoostingClassifier]:
est = Cls(n_estimators=200, max_depth=1, subsample=0.5, random_state=1)
est.fit(X, y)
est_ws = Cls(n_estimators=100,
max_depth=1,
subsample=0.5,
random_state=1,
warm_start=True)
est_ws.fit(X, y)
est_ws.set_params(n_estimators=200)
est_ws.fit(X, y)
assert_array_almost_equal(est_ws.oob_improvement_[:100],
est.oob_improvement_[:100])
def check_warm_start_clear(name):
# Test if fit clears state and grows a new forest when warm_start==False.
X, y = hastie_X, hastie_y
ForestEstimator = FOREST_ESTIMATORS[name]
clf = ForestEstimator(n_estimators=5,
max_depth=1,
warm_start=False,
random_state=1)
clf.fit(X, y)
clf_2 = ForestEstimator(n_estimators=5,
max_depth=1,
warm_start=True,
random_state=2)
clf_2.fit(X, y) # inits state
clf_2.set_params(warm_start=False, random_state=1)
clf_2.fit(X, y) # clears old state and equals clf
assert_array_almost_equal(clf_2.apply(X), clf.apply(X))
def test_quantile_loss():
# Check if quantile loss with alpha=0.5 equals lad.
clf_quantile = GradientBoostingRegressor(n_estimators=100,
loss='quantile',
max_depth=4,
alpha=0.5,
random_state=7)
clf_quantile.fit(boston.data, boston.target)
y_quantile = clf_quantile.predict(boston.data)
clf_lad = GradientBoostingRegressor(n_estimators=100,
loss='lad',
max_depth=4,
random_state=7)
clf_lad.fit(boston.data, boston.target)
y_lad = clf_lad.predict(boston.data)
assert_array_almost_equal(y_quantile, y_lad, decimal=4)
def test_compute_class_weight_dict():
classes = np.arange(3)
class_weights = {0: 1.0, 1: 2.0, 2: 3.0}
y = np.asarray([0, 0, 1, 2])
cw = compute_class_weight(class_weights, classes, y)
# When the user specifies class weights, compute_class_weights should just
# return them.
assert_array_almost_equal(np.asarray([1.0, 2.0, 3.0]), cw)
# When a class weight is specified that isn't in classes, a ValueError
# should get raised
msg = 'Class label 4 not present.'
class_weights = {0: 1.0, 1: 2.0, 2: 3.0, 4: 1.5}
assert_raise_message(ValueError, msg, compute_class_weight, class_weights,
classes, y)
msg = 'Class label -1 not present.'
class_weights = {-1: 5.0, 0: 1.0, 1: 2.0, 2: 3.0}
assert_raise_message(ValueError, msg, compute_class_weight, class_weights,
classes, y)
def test_probability_exponential():
# Predict probabilities.
clf = GradientBoostingClassifier(loss='exponential',
n_estimators=100,
random_state=1)
assert_raises(ValueError, clf.predict_proba, T)
clf.fit(X, y)
assert_array_equal(clf.predict(T), true_result)
# check if probabilities are in [0, 1].
y_proba = clf.predict_proba(T)
assert_true(np.all(y_proba >= 0.0))
assert_true(np.all(y_proba <= 1.0))
score = clf.decision_function(T).ravel()
assert_array_almost_equal(y_proba[:, 1], 1.0 / (1.0 + np.exp(-2 * score)))
# derive predictions from probabilities
y_pred = clf.classes_.take(y_proba.argmax(axis=1), axis=0)
assert_array_equal(y_pred, true_result)
def check_importances(name, criterion, X, y):
ForestEstimator = FOREST_ESTIMATORS[name]
est = ForestEstimator(n_estimators=20, criterion=criterion, random_state=0)
est.fit(X, y)
importances = est.feature_importances_
n_important = np.sum(importances > 0.1)
assert_equal(importances.shape[0], 10)
assert_equal(n_important, 3)
# XXX: Remove this test in 0.19 after transform support to estimators
# is removed.
X_new = assert_warns(DeprecationWarning,
est.transform,
X,
threshold="mean")
assert_less(0 < X_new.shape[1], X.shape[1])
# Check with parallel
importances = est.feature_importances_
est.set_params(n_jobs=2)
importances_parrallel = est.feature_importances_
assert_array_almost_equal(importances, importances_parrallel)
# Check with sample weights
sample_weight = check_random_state(0).randint(1, 10, len(X))
est = ForestEstimator(n_estimators=20, random_state=0, criterion=criterion)
est.fit(X, y, sample_weight=sample_weight)
importances = est.feature_importances_
assert_true(np.all(importances >= 0.0))
for scale in [0.5, 10, 100]:
est = ForestEstimator(n_estimators=20,
random_state=0,
criterion=criterion)
est.fit(X, y, sample_weight=scale * sample_weight)
importances_bis = est.feature_importances_
assert_less(np.abs(importances - importances_bis).mean(), 0.001)
def test_newton_cg():
# Test that newton_cg gives same result as scipy's fmin_ncg
rng = np.random.RandomState(0)
A = rng.normal(size=(10, 10))
x0 = np.ones(10)
def func(x):
Ax = A.dot(x)
return .5 * (Ax).dot(Ax)
def grad(x):
return A.T.dot(A.dot(x))
def hess(x, p):
return p.dot(A.T.dot(A.dot(x.all())))
def grad_hess(x):
return grad(x), lambda x: A.T.dot(A.dot(x))
assert_array_almost_equal(
newton_cg(grad_hess, func, grad, x0, tol=1e-10)[0],
fmin_ncg(f=func, x0=x0, fprime=grad, fhess_p=hess))
def test_feature_importances():
X = np.array(boston.data, dtype=np.float32)
y = np.array(boston.target, dtype=np.float32)
for presort in True, False:
clf = GradientBoostingRegressor(n_estimators=100,
max_depth=5,
min_samples_split=2,
random_state=1,
presort=presort)
clf.fit(X, y)
assert_true(hasattr(clf, 'feature_importances_'))
# XXX: Remove this test in 0.19 after transform support to estimators
# is removed.
X_new = assert_warns(DeprecationWarning,
clf.transform,
X,
threshold="mean")
assert_less(X_new.shape[1], X.shape[1])
feature_mask = (clf.feature_importances_ >
clf.feature_importances_.mean())
assert_array_almost_equal(X_new, X[:, feature_mask])
def check_decision_path(name):
X, y = hastie_X, hastie_y
n_samples = X.shape[0]
ForestEstimator = FOREST_ESTIMATORS[name]
est = ForestEstimator(n_estimators=5,
max_depth=1,
warm_start=False,
random_state=1)
est.fit(X, y)
indicator, n_nodes_ptr = est.decision_path(X)
assert_equal(indicator.shape[1], n_nodes_ptr[-1])
assert_equal(indicator.shape[0], n_samples)
assert_array_equal(np.diff(n_nodes_ptr),
[e.tree_.node_count for e in est.estimators_])
# Assert that leaves index are correct
leaves = est.apply(X)
for est_id in range(leaves.shape[1]):
leave_indicator = [
indicator[i, n_nodes_ptr[est_id] + j]
for i, j in enumerate(leaves[:, est_id])
]
assert_array_almost_equal(leave_indicator, np.ones(shape=n_samples))
def test_row_norms():
X = np.random.RandomState(42).randn(100, 100)
for dtype in (np.float32, np.float64):
if dtype is np.float32:
precision = 4
else:
precision = 5
X = X.astype(dtype)
sq_norm = (X**2).sum(axis=1)
assert_array_almost_equal(sq_norm, row_norms(X, squared=True),
precision)
assert_array_almost_equal(np.sqrt(sq_norm), row_norms(X), precision)
Xcsr = sparse.csr_matrix(X, dtype=dtype)
assert_array_almost_equal(sq_norm, row_norms(Xcsr, squared=True),
precision)
assert_array_almost_equal(np.sqrt(sq_norm), row_norms(Xcsr), precision)
def check_sparse_input(name, X, X_sparse, y):
ForestEstimator = FOREST_ESTIMATORS[name]
dense = ForestEstimator(random_state=0, max_depth=2).fit(X, y)
sparse = ForestEstimator(random_state=0, max_depth=2).fit(X_sparse, y)
assert_array_almost_equal(sparse.apply(X), dense.apply(X))
if name in FOREST_CLASSIFIERS or name in FOREST_REGRESSORS:
assert_array_almost_equal(sparse.predict(X), dense.predict(X))
assert_array_almost_equal(sparse.feature_importances_,
dense.feature_importances_)
if name in FOREST_CLASSIFIERS:
assert_array_almost_equal(sparse.predict_proba(X),
dense.predict_proba(X))
assert_array_almost_equal(sparse.predict_log_proba(X),
dense.predict_log_proba(X))
if name in FOREST_TRANSFORMERS:
assert_array_almost_equal(
sparse.transform(X).toarray(),
dense.transform(X).toarray())
assert_array_almost_equal(
sparse.fit_transform(X).toarray(),
dense.fit_transform(X).toarray())
def test_softmax():
rng = np.random.RandomState(0)
X = rng.randn(3, 5)
exp_X = np.exp(X)
sum_exp_X = np.sum(exp_X, axis=1).reshape((-1, 1))
assert_array_almost_equal(softmax(X), exp_X / sum_exp_X)
def test_compute_sample_weight_with_subsample():
# Test compute_sample_weight with subsamples specified.
# Test with balanced classes and all samples present
y = np.asarray([1, 1, 1, 2, 2, 2])
sample_weight = assert_warns(DeprecationWarning, compute_sample_weight,
"auto", y)
assert_array_almost_equal(sample_weight, [1., 1., 1., 1., 1., 1.])
sample_weight = compute_sample_weight("balanced", y, range(6))
assert_array_almost_equal(sample_weight, [1., 1., 1., 1., 1., 1.])
# Test with column vector of balanced classes and all samples present
y = np.asarray([[1], [1], [1], [2], [2], [2]])
sample_weight = assert_warns(DeprecationWarning, compute_sample_weight,
"auto", y)
assert_array_almost_equal(sample_weight, [1., 1., 1., 1., 1., 1.])
sample_weight = compute_sample_weight("balanced", y, range(6))
assert_array_almost_equal(sample_weight, [1., 1., 1., 1., 1., 1.])
# Test with a subsample
y = np.asarray([1, 1, 1, 2, 2, 2])
sample_weight = assert_warns(DeprecationWarning, compute_sample_weight,
"auto", y, range(4))
assert_array_almost_equal(sample_weight, [.5, .5, .5, 1.5, 1.5, 1.5])
sample_weight = compute_sample_weight("balanced", y, range(4))
assert_array_almost_equal(sample_weight,
[2. / 3, 2. / 3, 2. / 3, 2., 2., 2.])
# Test with a bootstrap subsample
y = np.asarray([1, 1, 1, 2, 2, 2])
sample_weight = assert_warns(DeprecationWarning, compute_sample_weight,
"auto", y, [0, 1, 1, 2, 2, 3])
expected_auto = np.asarray(
[1 / 3., 1 / 3., 1 / 3., 5 / 3., 5 / 3., 5 / 3.])
assert_array_almost_equal(sample_weight, expected_auto)
sample_weight = compute_sample_weight("balanced", y, [0, 1, 1, 2, 2, 3])
expected_balanced = np.asarray([0.6, 0.6, 0.6, 3., 3., 3.])
assert_array_almost_equal(sample_weight, expected_balanced)
# Test with a bootstrap subsample for multi-output
y = np.asarray([[1, 0], [1, 0], [1, 0], [2, 1], [2, 1], [2, 1]])
sample_weight = assert_warns(DeprecationWarning, compute_sample_weight,
"auto", y, [0, 1, 1, 2, 2, 3])
assert_array_almost_equal(sample_weight, expected_auto**2)
sample_weight = compute_sample_weight("balanced", y, [0, 1, 1, 2, 2, 3])
assert_array_almost_equal(sample_weight, expected_balanced**2)
# Test with a missing class
y = np.asarray([1, 1, 1, 2, 2, 2, 3])
sample_weight = assert_warns(DeprecationWarning, compute_sample_weight,
"auto", y, range(6))
assert_array_almost_equal(sample_weight, [1., 1., 1., 1., 1., 1., 0.])
sample_weight = compute_sample_weight("balanced", y, range(6))
assert_array_almost_equal(sample_weight, [1., 1., 1., 1., 1., 1., 0.])
# Test with a missing class for multi-output
y = np.asarray([[1, 0], [1, 0], [1, 0], [2, 1], [2, 1], [2, 1], [2, 2]])
sample_weight = assert_warns(DeprecationWarning, compute_sample_weight,
"auto", y, range(6))
assert_array_almost_equal(sample_weight, [1., 1., 1., 1., 1., 1., 0.])
sample_weight = compute_sample_weight("balanced", y, range(6))
assert_array_almost_equal(sample_weight, [1., 1., 1., 1., 1., 1., 0.])
def test_compute_sample_weight():
# Test (and demo) compute_sample_weight.
# Test with balanced classes
y = np.asarray([1, 1, 1, 2, 2, 2])
sample_weight = assert_warns(DeprecationWarning, compute_sample_weight,
"auto", y)
assert_array_almost_equal(sample_weight, [1., 1., 1., 1., 1., 1.])
sample_weight = compute_sample_weight("balanced", y)
assert_array_almost_equal(sample_weight, [1., 1., 1., 1., 1., 1.])
# Test with user-defined weights
sample_weight = compute_sample_weight({1: 2, 2: 1}, y)
assert_array_almost_equal(sample_weight, [2., 2., 2., 1., 1., 1.])
# Test with column vector of balanced classes
y = np.asarray([[1], [1], [1], [2], [2], [2]])
sample_weight = assert_warns(DeprecationWarning, compute_sample_weight,
"auto", y)
assert_array_almost_equal(sample_weight, [1., 1., 1., 1., 1., 1.])
sample_weight = compute_sample_weight("balanced", y)
assert_array_almost_equal(sample_weight, [1., 1., 1., 1., 1., 1.])
# Test with unbalanced classes
y = np.asarray([1, 1, 1, 2, 2, 2, 3])
sample_weight = assert_warns(DeprecationWarning, compute_sample_weight,
"auto", y)
expected_auto = np.asarray([.6, .6, .6, .6, .6, .6, 1.8])
assert_array_almost_equal(sample_weight, expected_auto)
sample_weight = compute_sample_weight("balanced", y)
expected_balanced = np.array(
[0.7777, 0.7777, 0.7777, 0.7777, 0.7777, 0.7777, 2.3333])
assert_array_almost_equal(sample_weight, expected_balanced, decimal=4)
# Test with `None` weights
sample_weight = compute_sample_weight(None, y)
assert_array_almost_equal(sample_weight, [1., 1., 1., 1., 1., 1., 1.])
# Test with multi-output of balanced classes
y = np.asarray([[1, 0], [1, 0], [1, 0], [2, 1], [2, 1], [2, 1]])
sample_weight = assert_warns(DeprecationWarning, compute_sample_weight,
"auto", y)
assert_array_almost_equal(sample_weight, [1., 1., 1., 1., 1., 1.])
sample_weight = compute_sample_weight("balanced", y)
assert_array_almost_equal(sample_weight, [1., 1., 1., 1., 1., 1.])
# Test with multi-output with user-defined weights
y = np.asarray([[1, 0], [1, 0], [1, 0], [2, 1], [2, 1], [2, 1]])
sample_weight = compute_sample_weight([{1: 2, 2: 1}, {0: 1, 1: 2}], y)
assert_array_almost_equal(sample_weight, [2., 2., 2., 2., 2., 2.])
# Test with multi-output of unbalanced classes
y = np.asarray([[1, 0], [1, 0], [1, 0], [2, 1], [2, 1], [2, 1], [3, -1]])
sample_weight = assert_warns(DeprecationWarning, compute_sample_weight,
"auto", y)
assert_array_almost_equal(sample_weight, expected_auto**2)
sample_weight = compute_sample_weight("balanced", y)
assert_array_almost_equal(sample_weight, expected_balanced**2, decimal=3)
def check_sparse_input(EstimatorClass, X, X_sparse, y):
dense = EstimatorClass(n_estimators=10, random_state=0,
max_depth=2).fit(X, y)
sparse = EstimatorClass(n_estimators=10,
random_state=0,
max_depth=2,
presort=False).fit(X_sparse, y)
auto = EstimatorClass(n_estimators=10,
random_state=0,
max_depth=2,
presort='auto').fit(X_sparse, y)
assert_array_almost_equal(sparse.apply(X), dense.apply(X))
assert_array_almost_equal(sparse.predict(X), dense.predict(X))
assert_array_almost_equal(sparse.feature_importances_,
dense.feature_importances_)
assert_array_almost_equal(sparse.apply(X), auto.apply(X))
assert_array_almost_equal(sparse.predict(X), auto.predict(X))
assert_array_almost_equal(sparse.feature_importances_,
auto.feature_importances_)
if isinstance(EstimatorClass, GradientBoostingClassifier):
assert_array_almost_equal(sparse.predict_proba(X),
dense.predict_proba(X))
assert_array_almost_equal(sparse.predict_log_proba(X),
dense.predict_log_proba(X))
assert_array_almost_equal(sparse.predict_proba(X),
auto.predict_proba(X))
assert_array_almost_equal(sparse.predict_log_proba(X),
auto.predict_log_proba(X))
