def test_classification_with_custom_objective():
tm._skip_if_no_sklearn()
from sklearn.datasets import load_digits
from sklearn.cross_validation import KFold
def logregobj(y_true, y_pred):
y_pred = 1.0 / (1.0 + np.exp(-y_pred))
grad = y_pred - y_true
hess = y_pred * (1.0 - y_pred)
return grad, hess
digits = load_digits(2)
y = digits['target']
X = digits['data']
kf = KFold(y.shape[0], n_folds=2, shuffle=True, random_state=rng)
for train_index, test_index in kf:
xgb_model = xgb.XGBClassifier(objective=logregobj)
xgb_model.fit(X[train_index], y[train_index])
preds = xgb_model.predict(X[test_index])
labels = y[test_index]
err = sum(1 for i in range(len(preds))
if int(preds[i] > 0.5) != labels[i]) / float(len(preds))
assert err < 0.1
# Test that the custom objective function is actually used
class XGBCustomObjectiveException(Exception):
pass
def dummy_objective(y_true, y_preds):
raise XGBCustomObjectiveException()
xgb_model = xgb.XGBClassifier(objective=dummy_objective)
np.testing.assert_raises(XGBCustomObjectiveException, xgb_model.fit, X, y)
def test_early_stopping_nonparallel(self):
tm._skip_if_no_sklearn()
from sklearn.datasets import load_digits
from sklearn.cross_validation import train_test_split
digits = load_digits(2)
X = digits['data']
y = digits['target']
X_train, X_test, y_train, y_test = train_test_split(X,
y,
random_state=0)
clf1 = xgb.XGBClassifier()
clf1.fit(X_train,
y_train,
early_stopping_rounds=5,
eval_metric="auc",
eval_set=[(X_test, y_test)])
clf2 = xgb.XGBClassifier()
clf2.fit(X_train,
y_train,
early_stopping_rounds=4,
eval_metric="auc",
eval_set=[(X_test, y_test)])
# should be the same
assert clf1.best_score == clf2.best_score
assert clf1.best_score != 1
# check overfit
clf3 = xgb.XGBClassifier()
clf3.fit(X_train,
y_train,
early_stopping_rounds=10,
eval_metric="auc",
eval_set=[(X_test, y_test)])
assert clf3.best_score == 1
def test_sklearn_plotting():
tm._skip_if_no_sklearn()
from sklearn.datasets import load_iris
iris = load_iris()
classifier = xgb.XGBClassifier()
classifier.fit(iris.data, iris.target)
import matplotlib
matplotlib.use('Agg')
from matplotlib.axes import Axes
from graphviz import Digraph
ax = xgb.plot_importance(classifier)
assert isinstance(ax, Axes)
assert ax.get_title() == 'Feature importance'
assert ax.get_xlabel() == 'F score'
assert ax.get_ylabel() == 'Features'
assert len(ax.patches) == 4
g = xgb.to_graphviz(classifier, num_trees=0)
assert isinstance(g, Digraph)
ax = xgb.plot_tree(classifier, num_trees=0)
assert isinstance(ax, Axes)
def test_split_value_histograms():
tm._skip_if_no_sklearn()
from sklearn.datasets import load_digits
digits_2class = load_digits(2)
X = digits_2class['data']
y = digits_2class['target']
dm = xgb.DMatrix(X, label=y)
params = {
'max_depth': 6,
'eta': 0.01,
'silent': 1,
'objective': 'binary:logistic'
}
gbdt = xgb.train(params, dm, num_boost_round=10)
assert gbdt.get_split_value_histogram("not_there",
as_pandas=True).shape[0] == 0
assert gbdt.get_split_value_histogram("not_there",
as_pandas=False).shape[0] == 0
assert gbdt.get_split_value_histogram("f28", bins=0).shape[0] == 1
assert gbdt.get_split_value_histogram("f28", bins=1).shape[0] == 1
assert gbdt.get_split_value_histogram("f28", bins=2).shape[0] == 2
assert gbdt.get_split_value_histogram("f28", bins=5).shape[0] == 2
assert gbdt.get_split_value_histogram("f28", bins=None).shape[0] == 2
def test_sklearn_nfolds_cv():
tm._skip_if_no_sklearn()
from sklearn.datasets import load_digits
from sklearn.cross_validation import StratifiedKFold
digits = load_digits(3)
X = digits['data']
y = digits['target']
dm = xgb.DMatrix(X, label=y)
params = {
'max_depth': 2,
'eta': 1,
'silent': 1,
'objective': 'multi:softprob',
'num_class': 3
}
seed = 2016
nfolds = 5
skf = StratifiedKFold(y, n_folds=nfolds, shuffle=True, random_state=seed)
cv1 = xgb.cv(params, dm, num_boost_round=10, nfold=nfolds, seed=seed)
cv2 = xgb.cv(params, dm, num_boost_round=10, folds=skf, seed=seed)
cv3 = xgb.cv(params,
dm,
num_boost_round=10,
nfold=nfolds,
stratified=True,
seed=seed)
assert cv1.shape[0] == cv2.shape[0] and cv2.shape[0] == cv3.shape[0]
assert cv2.iloc[-1, 0] == cv3.iloc[-1, 0]
def test_feature_importances():
tm._skip_if_no_sklearn()
from sklearn.datasets import load_digits
digits = load_digits(2)
y = digits['target']
X = digits['data']
xgb_model = xgb.XGBClassifier(seed=0).fit(X, y)
exp = np.array([
0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0.00833333, 0., 0., 0., 0., 0.,
0., 0., 0., 0.025, 0.14166667, 0., 0., 0., 0., 0., 0., 0.00833333,
0.25833333, 0., 0., 0., 0., 0.03333334, 0.03333334, 0., 0.32499999, 0.,
0., 0., 0., 0.05, 0.06666667, 0., 0., 0., 0., 0., 0., 0., 0.04166667,
0., 0., 0., 0., 0., 0., 0., 0.00833333, 0., 0., 0., 0., 0.
],
dtype=np.float32)
np.testing.assert_almost_equal(xgb_model.feature_importances_, exp)
# numeric columns
import pandas as pd
y = pd.Series(digits['target'])
X = pd.DataFrame(digits['data'])
xgb_model = xgb.XGBClassifier(seed=0).fit(X, y)
np.testing.assert_almost_equal(xgb_model.feature_importances_, exp)
# string columns, the feature order must be kept
chars = list('abcdefghijklmnopqrstuvwxyz')
X.columns = ["".join(random.sample(chars, 5)) for x in range(64)]
xgb_model = xgb.XGBClassifier(seed=0).fit(X, y)
np.testing.assert_almost_equal(xgb_model.feature_importances_, exp)
def test_multiclass_classification():
tm._skip_if_no_sklearn()
from sklearn.datasets import load_iris
from sklearn.cross_validation import KFold
def check_pred(preds, labels):
err = sum(1 for i in range(len(preds))
if int(preds[i] > 0.5) != labels[i]) / float(len(preds))
assert err < 0.4
iris = load_iris()
y = iris['target']
X = iris['data']
kf = KFold(y.shape[0], n_folds=2, shuffle=True, random_state=rng)
for train_index, test_index in kf:
xgb_model = xgb.XGBClassifier().fit(X[train_index], y[train_index])
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)
check_pred(preds2, labels)
check_pred(preds3, labels)
check_pred(preds4, labels)
def evalerror_04(self, preds, dtrain):
tm._skip_if_no_sklearn()
from sklearn.metrics import mean_squared_error
labels = dtrain.get_label()
return [('error', float(sum(labels != (preds > 0.0))) / len(labels)),
('rmse', mean_squared_error(labels, preds))]
def test_cv_early_stopping(self):
tm._skip_if_no_sklearn()
from sklearn.datasets import load_digits
digits = load_digits(2)
X = digits['data']
y = digits['target']
dm = xgb.DMatrix(X, label=y)
params = {'max_depth': 2, 'eta': 1, 'silent': 1, 'objective': 'binary:logistic'}
cv = xgb.cv(params, dm, num_boost_round=10, nfold=10, early_stopping_rounds=10)
assert cv.shape[0] == 10
cv = xgb.cv(params, dm, num_boost_round=10, nfold=10, early_stopping_rounds=5)
assert cv.shape[0] == 3
cv = xgb.cv(params, dm, num_boost_round=10, nfold=10, early_stopping_rounds=1)
assert cv.shape[0] == 1
cv = xgb.cv(params, dm, num_boost_round=10, nfold=10, feval=self.evalerror,
early_stopping_rounds=10)
assert cv.shape[0] == 10
cv = xgb.cv(params, dm, num_boost_round=10, nfold=10, feval=self.evalerror,
early_stopping_rounds=1)
assert cv.shape[0] == 5
cv = xgb.cv(params, dm, num_boost_round=10, nfold=10, feval=self.evalerror,
maximize=True, early_stopping_rounds=1)
assert cv.shape[0] == 1
def test_multiclass_classification():
tm._skip_if_no_sklearn()
from sklearn.datasets import load_iris
from sklearn.cross_validation import KFold
def check_pred(preds, labels):
err = sum(1 for i in range(len(preds))
if int(preds[i] > 0.5) != labels[i]) / float(len(preds))
assert err < 0.4
iris = load_iris()
y = iris['target']
X = iris['data']
kf = KFold(y.shape[0], n_folds=2, shuffle=True, random_state=rng)
for train_index, test_index in kf:
xgb_model = xgb.XGBClassifier().fit(X[train_index], y[train_index])
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)
check_pred(preds2, labels)
check_pred(preds3, labels)
check_pred(preds4, labels)
def test_regression_with_custom_objective():
tm._skip_if_no_sklearn()
from sklearn.metrics import mean_squared_error
from sklearn.datasets import load_boston
from sklearn.cross_validation import KFold
def objective_ls(y_true, y_pred):
grad = (y_pred - y_true)
hess = np.ones(len(y_true))
return grad, hess
boston = load_boston()
y = boston['target']
X = boston['data']
kf = KFold(y.shape[0], n_folds=2, shuffle=True, random_state=rng)
for train_index, test_index in kf:
xgb_model = xgb.XGBRegressor(objective=objective_ls).fit(
X[train_index], y[train_index])
preds = xgb_model.predict(X[test_index])
labels = y[test_index]
assert mean_squared_error(preds, labels) < 25
# Test that the custom objective function is actually used
class XGBCustomObjectiveException(Exception):
pass
def dummy_objective(y_true, y_pred):
raise XGBCustomObjectiveException()
xgb_model = xgb.XGBRegressor(objective=dummy_objective)
np.testing.assert_raises(XGBCustomObjectiveException, xgb_model.fit, X, y)
def test_sklearn_nfolds_cv():
tm._skip_if_no_sklearn()
from sklearn.datasets import load_digits
from sklearn.cross_validation import StratifiedKFold
digits = load_digits(3)
X = digits['data']
y = digits['target']
dm = xgb.DMatrix(X, label=y)
params = {
'max_depth': 2,
'eta': 1,
'silent': 1,
'objective':
'multi:softprob',
'num_class': 3
}
seed = 2016
nfolds = 5
skf = StratifiedKFold(y, n_folds=nfolds, shuffle=True, random_state=seed)
cv1 = xgb.cv(params, dm, num_boost_round=10, nfold=nfolds, seed=seed)
cv2 = xgb.cv(params, dm, num_boost_round=10, folds=skf, seed=seed)
cv3 = xgb.cv(params, dm, num_boost_round=10, nfold=nfolds, stratified=True, seed=seed)
assert cv1.shape[0] == cv2.shape[0] and cv2.shape[0] == cv3.shape[0]
assert cv2.iloc[-1, 0] == cv3.iloc[-1, 0]
def test_regression_with_custom_objective():
tm._skip_if_no_sklearn()
from sklearn.metrics import mean_squared_error
from sklearn.datasets import load_boston
from sklearn.cross_validation import KFold
def objective_ls(y_true, y_pred):
grad = (y_pred - y_true)
hess = np.ones(len(y_true))
return grad, hess
boston = load_boston()
y = boston['target']
X = boston['data']
kf = KFold(y.shape[0], n_folds=2, shuffle=True, random_state=rng)
for train_index, test_index in kf:
xgb_model = xgb.XGBRegressor(objective=objective_ls).fit(
X[train_index], y[train_index]
)
preds = xgb_model.predict(X[test_index])
labels = y[test_index]
assert mean_squared_error(preds, labels) < 25
# Test that the custom objective function is actually used
class XGBCustomObjectiveException(Exception):
pass
def dummy_objective(y_true, y_pred):
raise XGBCustomObjectiveException()
xgb_model = xgb.XGBRegressor(objective=dummy_objective)
np.testing.assert_raises(XGBCustomObjectiveException, xgb_model.fit, X, y)
def test_sklearn_plotting():
tm._skip_if_no_sklearn()
from sklearn.datasets import load_iris
iris = load_iris()
classifier = xgb.XGBClassifier()
classifier.fit(iris.data, iris.target)
import matplotlib
matplotlib.use('Agg')
from matplotlib.axes import Axes
from graphviz import Digraph
ax = xgb.plot_importance(classifier)
assert isinstance(ax, Axes)
assert ax.get_title() == 'Feature importance'
assert ax.get_xlabel() == 'F score'
assert ax.get_ylabel() == 'Features'
assert len(ax.patches) == 4
g = xgb.to_graphviz(classifier, num_trees=0)
assert isinstance(g, Digraph)
ax = xgb.plot_tree(classifier, num_trees=0)
assert isinstance(ax, Axes)
def test_feature_importances():
tm._skip_if_no_sklearn()
from sklearn.datasets import load_digits
digits = load_digits(2)
y = digits['target']
X = digits['data']
xgb_model = xgb.XGBClassifier(seed=0).fit(X, y)
exp = np.array([0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0.00833333, 0.,
0., 0., 0., 0., 0., 0., 0., 0.025, 0.14166667, 0., 0., 0.,
0., 0., 0., 0.00833333, 0.25833333, 0., 0., 0., 0.,
0.03333334, 0.03333334, 0., 0.32499999, 0., 0., 0., 0.,
0.05, 0.06666667, 0., 0., 0., 0., 0., 0., 0., 0.04166667,
0., 0., 0., 0., 0., 0., 0., 0.00833333, 0., 0., 0., 0.,
0.], dtype=np.float32)
np.testing.assert_almost_equal(xgb_model.feature_importances_, exp)
# numeric columns
import pandas as pd
y = pd.Series(digits['target'])
X = pd.DataFrame(digits['data'])
xgb_model = xgb.XGBClassifier(seed=0).fit(X, y)
np.testing.assert_almost_equal(xgb_model.feature_importances_, exp)
# string columns, the feature order must be kept
chars = list('abcdefghijklmnopqrstuvwxyz')
X.columns = ["".join(random.sample(chars, 5)) for x in range(64)]
xgb_model = xgb.XGBClassifier(seed=0).fit(X, y)
np.testing.assert_almost_equal(xgb_model.feature_importances_, exp)
def test_boston_housing_regression():
tm._skip_if_no_sklearn()
from sklearn.metrics import mean_squared_error
from sklearn.datasets import load_boston
from sklearn.cross_validation import KFold
boston = load_boston()
y = boston['target']
X = boston['data']
kf = KFold(y.shape[0], n_folds=2, shuffle=True, random_state=rng)
for train_index, test_index in kf:
xgb_model = xgb.XGBRegressor().fit(X[train_index], y[train_index])
preds = xgb_model.predict(X[test_index])
# test other params in XGBRegressor().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]
assert mean_squared_error(preds, labels) < 25
assert mean_squared_error(preds2, labels) < 350
assert mean_squared_error(preds3, labels) < 25
assert mean_squared_error(preds4, labels) < 350
def test_cv_early_stopping(self):
tm._skip_if_no_sklearn()
from sklearn.datasets import load_digits
digits = load_digits(2)
X = digits['data']
y = digits['target']
dm = xgb.DMatrix(X, label=y)
params = {
'max_depth': 2,
'eta': 1,
'silent': 1,
'objective': 'binary:logistic'
}
cv = xgb.cv(params,
dm,
num_boost_round=10,
nfold=10,
early_stopping_rounds=10)
assert cv.shape[0] == 10
cv = xgb.cv(params,
dm,
num_boost_round=10,
nfold=10,
early_stopping_rounds=5)
assert cv.shape[0] == 3
cv = xgb.cv(params,
dm,
num_boost_round=10,
nfold=10,
early_stopping_rounds=1)
assert cv.shape[0] == 1
cv = xgb.cv(params,
dm,
num_boost_round=10,
nfold=10,
feval=self.evalerror,
early_stopping_rounds=10)
assert cv.shape[0] == 10
cv = xgb.cv(params,
dm,
num_boost_round=10,
nfold=10,
feval=self.evalerror,
early_stopping_rounds=1)
assert cv.shape[0] == 5
cv = xgb.cv(params,
dm,
num_boost_round=10,
nfold=10,
feval=self.evalerror,
maximize=True,
early_stopping_rounds=1)
assert cv.shape[0] == 1
def test_parameter_tuning():
tm._skip_if_no_sklearn()
from sklearn.grid_search import GridSearchCV
from sklearn.datasets import load_boston
boston = load_boston()
y = boston['target']
X = boston['data']
xgb_model = xgb.XGBRegressor()
clf = GridSearchCV(xgb_model, {'max_depth': [2, 4, 6],
'n_estimators': [50, 100, 200]}, verbose=1)
clf.fit(X, y)
assert clf.best_score_ < 0.7
assert clf.best_params_ == {'n_estimators': 100, 'max_depth': 4}
def test_sklearn_api():
tm._skip_if_no_sklearn()
from sklearn.datasets import load_iris
from sklearn.cross_validation import train_test_split
iris = load_iris()
tr_d, te_d, tr_l, te_l = train_test_split(iris.data, iris.target, train_size=120)
classifier = xgb.XGBClassifier()
classifier.fit(tr_d, tr_l)
preds = classifier.predict(te_d)
labels = te_l
err = sum([1 for p, l in zip(preds, labels) if p != l]) / len(te_l)
assert err < 0.2
def test_binary_classification():
tm._skip_if_no_sklearn()
from sklearn.datasets import load_digits
from sklearn.cross_validation import KFold
digits = load_digits(2)
y = digits['target']
X = digits['data']
kf = KFold(y.shape[0], n_folds=2, shuffle=True, random_state=rng)
for train_index, test_index in kf:
xgb_model = xgb.XGBClassifier().fit(X[train_index], y[train_index])
preds = xgb_model.predict(X[test_index])
labels = y[test_index]
err = sum(1 for i in range(len(preds))
if int(preds[i] > 0.5) != labels[i]) / float(len(preds))
assert err < 0.1
def test_binary_classification():
tm._skip_if_no_sklearn()
from sklearn.datasets import load_digits
from sklearn.cross_validation import KFold
digits = load_digits(2)
y = digits['target']
X = digits['data']
kf = KFold(y.shape[0], n_folds=2, shuffle=True, random_state=rng)
for train_index, test_index in kf:
xgb_model = xgb.XGBClassifier().fit(X[train_index], y[train_index])
preds = xgb_model.predict(X[test_index])
labels = y[test_index]
err = sum(1 for i in range(len(preds))
if int(preds[i] > 0.5) != labels[i]) / float(len(preds))
assert err < 0.1
def test_sklearn_api():
tm._skip_if_no_sklearn()
from sklearn.datasets import load_iris
from sklearn.cross_validation import train_test_split
iris = load_iris()
tr_d, te_d, tr_l, te_l = train_test_split(iris.data,
iris.target,
train_size=120)
classifier = xgb.XGBClassifier()
classifier.fit(tr_d, tr_l)
preds = classifier.predict(te_d)
labels = te_l
err = sum([1 for p, l in zip(preds, labels) if p != l]) / len(te_l)
assert err < 0.2
def test_parameter_tuning():
tm._skip_if_no_sklearn()
from sklearn.grid_search import GridSearchCV
from sklearn.datasets import load_boston
boston = load_boston()
y = boston['target']
X = boston['data']
xgb_model = xgb.XGBRegressor()
clf = GridSearchCV(xgb_model, {
'max_depth': [2, 4, 6],
'n_estimators': [50, 100, 200]
},
verbose=1)
clf.fit(X, y)
assert clf.best_score_ < 0.7
assert clf.best_params_ == {'n_estimators': 100, 'max_depth': 4}
def test_eval_metrics(self):
tm._skip_if_no_sklearn()
from sklearn.cross_validation import train_test_split
from sklearn.datasets import load_digits
digits = load_digits(2)
X = digits['data']
y = digits['target']
Xt, Xv, yt, yv = train_test_split(X, y, test_size=0.2, random_state=0)
dtrain = xgb.DMatrix(Xt, label=yt)
dvalid = xgb.DMatrix(Xv, label=yv)
watchlist = [(dtrain, 'train'), (dvalid, 'val')]
gbdt_01 = xgb.train(self.xgb_params_01, dtrain, num_boost_round=10)
gbdt_02 = xgb.train(self.xgb_params_02, dtrain, num_boost_round=10)
gbdt_03 = xgb.train(self.xgb_params_03, dtrain, num_boost_round=10)
assert gbdt_01.predict(dvalid)[0] == gbdt_02.predict(dvalid)[0]
assert gbdt_01.predict(dvalid)[0] == gbdt_03.predict(dvalid)[0]
gbdt_01 = xgb.train(self.xgb_params_01, dtrain, 10, watchlist,
early_stopping_rounds=2)
gbdt_02 = xgb.train(self.xgb_params_02, dtrain, 10, watchlist,
early_stopping_rounds=2)
gbdt_03 = xgb.train(self.xgb_params_03, dtrain, 10, watchlist,
early_stopping_rounds=2)
gbdt_04 = xgb.train(self.xgb_params_04, dtrain, 10, watchlist,
early_stopping_rounds=2)
assert gbdt_01.predict(dvalid)[0] == gbdt_02.predict(dvalid)[0]
assert gbdt_01.predict(dvalid)[0] == gbdt_03.predict(dvalid)[0]
assert gbdt_03.predict(dvalid)[0] != gbdt_04.predict(dvalid)[0]
gbdt_01 = xgb.train(self.xgb_params_01, dtrain, 10, watchlist,
early_stopping_rounds=2, feval=self.evalerror_01)
gbdt_02 = xgb.train(self.xgb_params_02, dtrain, 10, watchlist,
early_stopping_rounds=2, feval=self.evalerror_02)
gbdt_03 = xgb.train(self.xgb_params_03, dtrain, 10, watchlist,
early_stopping_rounds=2, feval=self.evalerror_03)
gbdt_04 = xgb.train(self.xgb_params_04, dtrain, 10, watchlist,
early_stopping_rounds=2, feval=self.evalerror_04)
assert gbdt_01.predict(dvalid)[0] == gbdt_02.predict(dvalid)[0]
assert gbdt_01.predict(dvalid)[0] == gbdt_03.predict(dvalid)[0]
assert gbdt_03.predict(dvalid)[0] != gbdt_04.predict(dvalid)[0]
def test_split_value_histograms():
tm._skip_if_no_sklearn()
from sklearn.datasets import load_digits
digits_2class = load_digits(2)
X = digits_2class['data']
y = digits_2class['target']
dm = xgb.DMatrix(X, label=y)
params = {'max_depth': 6, 'eta': 0.01, 'silent': 1, 'objective': 'binary:logistic'}
gbdt = xgb.train(params, dm, num_boost_round=10)
assert gbdt.get_split_value_histogram("not_there", as_pandas=True).shape[0] == 0
assert gbdt.get_split_value_histogram("not_there", as_pandas=False).shape[0] == 0
assert gbdt.get_split_value_histogram("f28", bins=0).shape[0] == 1
assert gbdt.get_split_value_histogram("f28", bins=1).shape[0] == 1
assert gbdt.get_split_value_histogram("f28", bins=2).shape[0] == 2
assert gbdt.get_split_value_histogram("f28", bins=5).shape[0] == 2
assert gbdt.get_split_value_histogram("f28", bins=None).shape[0] == 2
def test_early_stopping_nonparallel(self):
tm._skip_if_no_sklearn()
from sklearn.datasets import load_digits
from sklearn.cross_validation import train_test_split
digits = load_digits(2)
X = digits['data']
y = digits['target']
X_train, X_test, y_train, y_test = train_test_split(X, y, random_state=0)
clf1 = xgb.XGBClassifier()
clf1.fit(X_train, y_train, early_stopping_rounds=5, eval_metric="auc",
eval_set=[(X_test, y_test)])
clf2 = xgb.XGBClassifier()
clf2.fit(X_train, y_train, early_stopping_rounds=4, eval_metric="auc",
eval_set=[(X_test, y_test)])
# should be the same
assert clf1.best_score == clf2.best_score
assert clf1.best_score != 1
# check overfit
clf3 = xgb.XGBClassifier()
clf3.fit(X_train, y_train, early_stopping_rounds=10, eval_metric="auc",
eval_set=[(X_test, y_test)])
assert clf3.best_score == 1
def test_classification_with_custom_objective():
tm._skip_if_no_sklearn()
from sklearn.datasets import load_digits
from sklearn.cross_validation import KFold
def logregobj(y_true, y_pred):
y_pred = 1.0 / (1.0 + np.exp(-y_pred))
grad = y_pred - y_true
hess = y_pred * (1.0 - y_pred)
return grad, hess
digits = load_digits(2)
y = digits['target']
X = digits['data']
kf = KFold(y.shape[0], n_folds=2, shuffle=True, random_state=rng)
for train_index, test_index in kf:
xgb_model = xgb.XGBClassifier(objective=logregobj)
xgb_model.fit(X[train_index], y[train_index])
preds = xgb_model.predict(X[test_index])
labels = y[test_index]
err = sum(1 for i in range(len(preds))
if int(preds[i] > 0.5) != labels[i]) / float(len(preds))
assert err < 0.1
# Test that the custom objective function is actually used
class XGBCustomObjectiveException(Exception):
pass
def dummy_objective(y_true, y_preds):
raise XGBCustomObjectiveException()
xgb_model = xgb.XGBClassifier(objective=dummy_objective)
np.testing.assert_raises(
XGBCustomObjectiveException,
xgb_model.fit,
X, y
)
def test_boston_housing_regression():
tm._skip_if_no_sklearn()
from sklearn.metrics import mean_squared_error
from sklearn.datasets import load_boston
from sklearn.cross_validation import KFold
boston = load_boston()
y = boston['target']
X = boston['data']
kf = KFold(y.shape[0], n_folds=2, shuffle=True, random_state=rng)
for train_index, test_index in kf:
xgb_model = xgb.XGBRegressor().fit(X[train_index], y[train_index])
preds = xgb_model.predict(X[test_index])
# test other params in XGBRegressor().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]
assert mean_squared_error(preds, labels) < 25
assert mean_squared_error(preds2, labels) < 350
assert mean_squared_error(preds3, labels) < 25
assert mean_squared_error(preds4, labels) < 350
def test_training_continuation(self):
tm._skip_if_no_sklearn()
from sklearn.datasets import load_digits
from sklearn.metrics import mean_squared_error
digits_2class = load_digits(2)
digits_5class = load_digits(5)
X_2class = digits_2class['data']
y_2class = digits_2class['target']
X_5class = digits_5class['data']
y_5class = digits_5class['target']
dtrain_2class = xgb.DMatrix(X_2class, label=y_2class)
dtrain_5class = xgb.DMatrix(X_5class, label=y_5class)
gbdt_01 = xgb.train(self.xgb_params_01, dtrain_2class, num_boost_round=10)
ntrees_01 = len(gbdt_01.get_dump())
assert ntrees_01 == 10
gbdt_02 = xgb.train(self.xgb_params_01, dtrain_2class, num_boost_round=0)
gbdt_02.save_model('xgb_tc.model')
gbdt_02a = xgb.train(self.xgb_params_01, dtrain_2class, num_boost_round=10, xgb_model=gbdt_02)
gbdt_02b = xgb.train(self.xgb_params_01, dtrain_2class, num_boost_round=10, xgb_model="xgb_tc.model")
ntrees_02a = len(gbdt_02a.get_dump())
ntrees_02b = len(gbdt_02b.get_dump())
assert ntrees_02a == 10
assert ntrees_02b == 10
res1 = mean_squared_error(y_2class, gbdt_01.predict(dtrain_2class))
res2 = mean_squared_error(y_2class, gbdt_02a.predict(dtrain_2class))
assert res1 == res2
res1 = mean_squared_error(y_2class, gbdt_01.predict(dtrain_2class))
res2 = mean_squared_error(y_2class, gbdt_02b.predict(dtrain_2class))
assert res1 == res2
gbdt_03 = xgb.train(self.xgb_params_01, dtrain_2class, num_boost_round=3)
gbdt_03.save_model('xgb_tc.model')
gbdt_03a = xgb.train(self.xgb_params_01, dtrain_2class, num_boost_round=7, xgb_model=gbdt_03)
gbdt_03b = xgb.train(self.xgb_params_01, dtrain_2class, num_boost_round=7, xgb_model="xgb_tc.model")
ntrees_03a = len(gbdt_03a.get_dump())
ntrees_03b = len(gbdt_03b.get_dump())
assert ntrees_03a == 10
assert ntrees_03b == 10
res1 = mean_squared_error(y_2class, gbdt_03a.predict(dtrain_2class))
res2 = mean_squared_error(y_2class, gbdt_03b.predict(dtrain_2class))
assert res1 == res2
gbdt_04 = xgb.train(self.xgb_params_02, dtrain_2class, num_boost_round=3)
assert gbdt_04.best_ntree_limit == (gbdt_04.best_iteration + 1) * self.num_parallel_tree
res1 = mean_squared_error(y_2class, gbdt_04.predict(dtrain_2class))
res2 = mean_squared_error(y_2class, gbdt_04.predict(dtrain_2class, ntree_limit=gbdt_04.best_ntree_limit))
assert res1 == res2
gbdt_04 = xgb.train(self.xgb_params_02, dtrain_2class, num_boost_round=7, xgb_model=gbdt_04)
assert gbdt_04.best_ntree_limit == (gbdt_04.best_iteration + 1) * self.num_parallel_tree
res1 = mean_squared_error(y_2class, gbdt_04.predict(dtrain_2class))
res2 = mean_squared_error(y_2class, gbdt_04.predict(dtrain_2class, ntree_limit=gbdt_04.best_ntree_limit))
assert res1 == res2
gbdt_05 = xgb.train(self.xgb_params_03, dtrain_5class, num_boost_round=7)
assert gbdt_05.best_ntree_limit == (gbdt_05.best_iteration + 1) * self.num_parallel_tree
gbdt_05 = xgb.train(self.xgb_params_03, dtrain_5class, num_boost_round=3, xgb_model=gbdt_05)
assert gbdt_05.best_ntree_limit == (gbdt_05.best_iteration + 1) * self.num_parallel_tree
res1 = gbdt_05.predict(dtrain_5class)
res2 = gbdt_05.predict(dtrain_5class, ntree_limit=gbdt_05.best_ntree_limit)
np.testing.assert_almost_equal(res1, res2)
def test_training_continuation(self):
tm._skip_if_no_sklearn()
from sklearn.datasets import load_digits
from sklearn.metrics import mean_squared_error
digits_2class = load_digits(2)
digits_5class = load_digits(5)
X_2class = digits_2class['data']
y_2class = digits_2class['target']
X_5class = digits_5class['data']
y_5class = digits_5class['target']
dtrain_2class = xgb.DMatrix(X_2class, label=y_2class)
dtrain_5class = xgb.DMatrix(X_5class, label=y_5class)
gbdt_01 = xgb.train(self.xgb_params_01,
dtrain_2class,
num_boost_round=10)
ntrees_01 = len(gbdt_01.get_dump())
assert ntrees_01 == 10
gbdt_02 = xgb.train(self.xgb_params_01,
dtrain_2class,
num_boost_round=0)
gbdt_02.save_model('xgb_tc.model')
gbdt_02a = xgb.train(self.xgb_params_01,
dtrain_2class,
num_boost_round=10,
xgb_model=gbdt_02)
gbdt_02b = xgb.train(self.xgb_params_01,
dtrain_2class,
num_boost_round=10,
xgb_model="xgb_tc.model")
ntrees_02a = len(gbdt_02a.get_dump())
ntrees_02b = len(gbdt_02b.get_dump())
assert ntrees_02a == 10
assert ntrees_02b == 10
res1 = mean_squared_error(y_2class, gbdt_01.predict(dtrain_2class))
res2 = mean_squared_error(y_2class, gbdt_02a.predict(dtrain_2class))
assert res1 == res2
res1 = mean_squared_error(y_2class, gbdt_01.predict(dtrain_2class))
res2 = mean_squared_error(y_2class, gbdt_02b.predict(dtrain_2class))
assert res1 == res2
gbdt_03 = xgb.train(self.xgb_params_01,
dtrain_2class,
num_boost_round=3)
gbdt_03.save_model('xgb_tc.model')
gbdt_03a = xgb.train(self.xgb_params_01,
dtrain_2class,
num_boost_round=7,
xgb_model=gbdt_03)
gbdt_03b = xgb.train(self.xgb_params_01,
dtrain_2class,
num_boost_round=7,
xgb_model="xgb_tc.model")
ntrees_03a = len(gbdt_03a.get_dump())
ntrees_03b = len(gbdt_03b.get_dump())
assert ntrees_03a == 10
assert ntrees_03b == 10
res1 = mean_squared_error(y_2class, gbdt_03a.predict(dtrain_2class))
res2 = mean_squared_error(y_2class, gbdt_03b.predict(dtrain_2class))
assert res1 == res2
gbdt_04 = xgb.train(self.xgb_params_02,
dtrain_2class,
num_boost_round=3)
assert gbdt_04.best_ntree_limit == (gbdt_04.best_iteration +
1) * self.num_parallel_tree
res1 = mean_squared_error(y_2class, gbdt_04.predict(dtrain_2class))
res2 = mean_squared_error(
y_2class,
gbdt_04.predict(dtrain_2class,
ntree_limit=gbdt_04.best_ntree_limit))
assert res1 == res2
gbdt_04 = xgb.train(self.xgb_params_02,
dtrain_2class,
num_boost_round=7,
xgb_model=gbdt_04)
assert gbdt_04.best_ntree_limit == (gbdt_04.best_iteration +
1) * self.num_parallel_tree
res1 = mean_squared_error(y_2class, gbdt_04.predict(dtrain_2class))
res2 = mean_squared_error(
y_2class,
gbdt_04.predict(dtrain_2class,
ntree_limit=gbdt_04.best_ntree_limit))
assert res1 == res2
gbdt_05 = xgb.train(self.xgb_params_03,
dtrain_5class,
num_boost_round=7)
assert gbdt_05.best_ntree_limit == (gbdt_05.best_iteration +
1) * self.num_parallel_tree
gbdt_05 = xgb.train(self.xgb_params_03,
dtrain_5class,
num_boost_round=3,
xgb_model=gbdt_05)
assert gbdt_05.best_ntree_limit == (gbdt_05.best_iteration +
1) * self.num_parallel_tree
res1 = gbdt_05.predict(dtrain_5class)
res2 = gbdt_05.predict(dtrain_5class,
ntree_limit=gbdt_05.best_ntree_limit)
np.testing.assert_almost_equal(res1, res2)
def evalerror(self, preds, dtrain):
tm._skip_if_no_sklearn()
from sklearn.metrics import mean_squared_error
labels = dtrain.get_label()
return 'rmse', mean_squared_error(labels, preds)
def evalerror(self, preds, dtrain):
tm._skip_if_no_sklearn()
from sklearn.metrics import mean_squared_error
labels = dtrain.get_label()
return 'rmse', mean_squared_error(labels, preds)