def test_multiclass_classification(objective):
from sklearn.datasets import load_iris
from sklearn.model_selection import KFold
def check_pred(preds, labels, output_margin):
if output_margin:
err = sum(1 for i in range(len(preds))
if preds[i].argmax() != labels[i]) / float(len(preds))
else:
err = sum(1 for i in range(len(preds))
if preds[i] != labels[i]) / float(len(preds))
assert err < 0.4
iris = load_iris()
y = iris['target']
X = iris['data']
kf = KFold(n_splits=2, shuffle=True, random_state=rng)
for train_index, test_index in kf.split(X, y):
xgb_model = xgb.XGBClassifier(objective=objective).fit(
X[train_index], y[train_index])
assert (xgb_model.get_booster().num_boosted_rounds() ==
xgb_model.n_estimators)
preds = xgb_model.predict(X[test_index])
# test other params in XGBClassifier().fit
preds2 = xgb_model.predict(X[test_index],
output_margin=True,
ntree_limit=3)
preds3 = xgb_model.predict(X[test_index],
output_margin=True,
ntree_limit=0)
preds4 = xgb_model.predict(X[test_index],
output_margin=False,
ntree_limit=3)
labels = y[test_index]
check_pred(preds, labels, output_margin=False)
check_pred(preds2, labels, output_margin=True)
check_pred(preds3, labels, output_margin=True)
check_pred(preds4, labels, output_margin=False)
cls = xgb.XGBClassifier(n_estimators=4).fit(X, y)
assert cls.n_classes_ == 3
proba = cls.predict_proba(X)
assert proba.shape[0] == X.shape[0]
assert proba.shape[1] == cls.n_classes_
# custom objective, the default is multi:softprob so no transformation is required.
cls = xgb.XGBClassifier(n_estimators=4,
objective=tm.softprob_obj(3)).fit(X, y)
proba = cls.predict_proba(X)
assert proba.shape[0] == X.shape[0]
assert proba.shape[1] == cls.n_classes_
def test_evaluation_metric():
from sklearn.datasets import load_diabetes, load_digits
from sklearn.metrics import mean_absolute_error
X, y = load_diabetes(return_X_y=True)
n_estimators = 16
with tm.captured_output() as (out, err):
reg = xgb.XGBRegressor(
tree_method="hist",
eval_metric=mean_absolute_error,
n_estimators=n_estimators,
)
reg.fit(X, y, eval_set=[(X, y)])
lines = out.getvalue().strip().split('\n')
assert len(lines) == n_estimators
for line in lines:
assert line.find("mean_absolute_error") != -1
def metric(predt: np.ndarray, Xy: xgb.DMatrix):
y = Xy.get_label()
return "m", np.abs(predt - y).sum()
with pytest.warns(UserWarning):
reg = xgb.XGBRegressor(
tree_method="hist",
n_estimators=1,
)
reg.fit(X, y, eval_set=[(X, y)], eval_metric=metric)
def merror(y_true: np.ndarray, predt: np.ndarray):
n_samples = y_true.shape[0]
assert n_samples == predt.size
errors = np.zeros(y_true.shape[0])
errors[y != predt] = 1.0
return np.sum(errors) / n_samples
X, y = load_digits(n_class=10, return_X_y=True)
clf = xgb.XGBClassifier(use_label_encoder=False,
tree_method="hist",
eval_metric=merror,
n_estimators=16,
objective="multi:softmax")
clf.fit(X, y, eval_set=[(X, y)])
custom = clf.evals_result()
clf = xgb.XGBClassifier(use_label_encoder=False,
tree_method="hist",
eval_metric="merror",
n_estimators=16,
objective="multi:softmax")
clf.fit(X, y, eval_set=[(X, y)])
internal = clf.evals_result()
np.testing.assert_allclose(custom["validation_0"]["merror"],
internal["validation_0"]["merror"],
atol=1e-6)
clf = xgb.XGBRFClassifier(
use_label_encoder=False,
tree_method="hist",
n_estimators=16,
objective=tm.softprob_obj(10),
eval_metric=merror,
)
with pytest.raises(AssertionError):
# shape check inside the `merror` function
clf.fit(X, y, eval_set=[(X, y)])