Hendrik/xgboost
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

Deprecate reg:linear' in favor of reg:squarederror'. (#4267)

Browse Source 
* Deprecate `reg:linear' in favor of `reg:squarederror'.
* Replace the use of `reg:linear'.
* Replace the use of `silent`.
This commit is contained in:
Jiaming Yuan
2019-03-17 17:55:04 +08:00
committed by GitHub
parent cf8d5b9b76
commit 29a1356669
34 changed files with 210 additions and 193 deletions
Download Patch File Download Diff File Expand all files Collapse all files

11
tests/python/regression_test_utilities.py
View File

@@ -132,15 +132,16 @@ def run_suite(param, num_rounds=10, select_datasets=None, scale_features=False):
Run the given parameters on a range of datasets. Objective and eval metric will be automatically set
"""
datasets = [
Dataset("Boston", get_boston, "reg:linear", "rmse"),
Dataset("Boston", get_boston, "reg:squarederror", "rmse"),
Dataset("Digits", get_digits, "multi:softmax", "merror"),
Dataset("Cancer", get_cancer, "binary:logistic", "error"),
Dataset("Sparse regression", get_sparse, "reg:linear", "rmse"),
Dataset("Sparse regression", get_sparse, "reg:squarederror", "rmse"),
Dataset("Sparse regression with weights", get_sparse_weights,
"reg:linear", "rmse", has_weights=True),
"reg:squarederror", "rmse", has_weights=True),
Dataset("Small weights regression", get_small_weights,
"reg:linear", "rmse", has_weights=True),
Dataset("Boston External Memory", get_boston, "reg:linear", "rmse",
"reg:squarederror", "rmse", has_weights=True),
Dataset("Boston External Memory", get_boston,
"reg:squarederror", "rmse",
use_external_memory=True)
]

14
tests/python/test_basic.py
View File

@@ -38,7 +38,7 @@ class TestBasic(unittest.TestCase):
def test_basic(self):
dtrain = xgb.DMatrix(dpath + 'agaricus.txt.train')
dtest = xgb.DMatrix(dpath + 'agaricus.txt.test')
param = {'max_depth': 2, 'eta': 1, 'silent': 1,
param = {'max_depth': 2, 'eta': 1, 'verbosity': 0,
'objective': 'binary:logistic'}
# specify validations set to watch performance
watchlist = [(dtest, 'eval'), (dtrain, 'train')]
@@ -85,7 +85,7 @@ class TestBasic(unittest.TestCase):
def test_record_results(self):
dtrain = xgb.DMatrix(dpath + 'agaricus.txt.train')
dtest = xgb.DMatrix(dpath + 'agaricus.txt.test')
param = {'max_depth': 2, 'eta': 1, 'silent': 1,
param = {'max_depth': 2, 'eta': 1, 'verbosity': 0,
'objective': 'binary:logistic'}
# specify validations set to watch performance
watchlist = [(dtest, 'eval'), (dtrain, 'train')]
@@ -102,7 +102,7 @@ class TestBasic(unittest.TestCase):
def test_multiclass(self):
dtrain = xgb.DMatrix(dpath + 'agaricus.txt.train')
dtest = xgb.DMatrix(dpath + 'agaricus.txt.test')
param = {'max_depth': 2, 'eta': 1, 'silent': 1, 'num_class': 2}
param = {'max_depth': 2, 'eta': 1, 'verbosity': 0, 'num_class': 2}
# specify validations set to watch performance
watchlist = [(dtest, 'eval'), (dtrain, 'train')]
num_round = 2
@@ -273,7 +273,7 @@ class TestBasic(unittest.TestCase):
def test_cv(self):
dm = xgb.DMatrix(dpath + 'agaricus.txt.train')
params = {'max_depth': 2, 'eta': 1, 'silent': 1,
params = {'max_depth': 2, 'eta': 1, 'verbosity': 0,
'objective': 'binary:logistic'}
# return np.ndarray
@@ -283,7 +283,7 @@ class TestBasic(unittest.TestCase):
def test_cv_no_shuffle(self):
dm = xgb.DMatrix(dpath + 'agaricus.txt.train')
params = {'max_depth': 2, 'eta': 1, 'silent': 1,
params = {'max_depth': 2, 'eta': 1, 'verbosity': 0,
'objective': 'binary:logistic'}
# return np.ndarray
@@ -294,7 +294,7 @@ class TestBasic(unittest.TestCase):
def test_cv_explicit_fold_indices(self):
dm = xgb.DMatrix(dpath + 'agaricus.txt.train')
params = {'max_depth': 2, 'eta': 1, 'silent': 1, 'objective':
params = {'max_depth': 2, 'eta': 1, 'verbosity': 0, 'objective':
'binary:logistic'}
folds = [
# Train Test
@@ -310,7 +310,7 @@ class TestBasic(unittest.TestCase):
def test_cv_explicit_fold_indices_labels(self):
params = {'max_depth': 2, 'eta': 1, 'verbosity': 0, 'objective':
'reg:linear'}
'reg:squarederror'}
N = 100
F = 3
dm = xgb.DMatrix(data=np.random.randn(N, F), label=np.arange(N))

23
tests/python/test_basic_models.py
View File

@@ -11,7 +11,7 @@ rng = np.random.RandomState(1994)
class TestModels(unittest.TestCase):
def test_glm(self):
param = {'silent': 1, 'objective': 'binary:logistic',
param = {'verbosity': 0, 'objective': 'binary:logistic',
'booster': 'gblinear', 'alpha': 0.0001, 'lambda': 1, 'nthread': 1}
watchlist = [(dtest, 'eval'), (dtrain, 'train')]
num_round = 4
@@ -26,7 +26,7 @@ class TestModels(unittest.TestCase):
def test_dart(self):
dtrain = xgb.DMatrix(dpath + 'agaricus.txt.train')
dtest = xgb.DMatrix(dpath + 'agaricus.txt.test')
param = {'max_depth': 5, 'objective': 'binary:logistic', 'booster': 'dart', 'silent': False}
param = {'max_depth': 5, 'objective': 'binary:logistic', 'booster': 'dart', 'verbosity': 1}
# specify validations set to watch performance
watchlist = [(dtest, 'eval'), (dtrain, 'train')]
num_round = 2
@@ -51,7 +51,7 @@ class TestModels(unittest.TestCase):
# check whether sample_type and normalize_type work
num_round = 50
param['silent'] = True
param['verbosity'] = 0
param['learning_rate'] = 0.1
param['rate_drop'] = 0.1
preds_list = []
@@ -74,7 +74,8 @@ class TestModels(unittest.TestCase):
# learning_rates as a list
# init eta with 0 to check whether learning_rates work
param = {'max_depth': 2, 'eta': 0, 'silent': 1, 'objective': 'binary:logistic'}
param = {'max_depth': 2, 'eta': 0, 'verbosity': 0,
'objective': 'binary:logistic'}
evals_result = {}
bst = xgb.train(param, dtrain, num_round, watchlist, learning_rates=[0.8, 0.7, 0.6, 0.5],
evals_result=evals_result)
@@ -84,7 +85,8 @@ class TestModels(unittest.TestCase):
assert eval_errors[0] > eval_errors[-1]
# init learning_rate with 0 to check whether learning_rates work
param = {'max_depth': 2, 'learning_rate': 0, 'silent': 1, 'objective': 'binary:logistic'}
param = {'max_depth': 2, 'learning_rate': 0, 'verbosity': 0,
'objective': 'binary:logistic'}
evals_result = {}
bst = xgb.train(param, dtrain, num_round, watchlist, learning_rates=[0.8, 0.7, 0.6, 0.5],
evals_result=evals_result)
@@ -94,7 +96,7 @@ class TestModels(unittest.TestCase):
assert eval_errors[0] > eval_errors[-1]
# check if learning_rates override default value of eta/learning_rate
param = {'max_depth': 2, 'silent': 1, 'objective': 'binary:logistic'}
param = {'max_depth': 2, 'verbosity': 0, 'objective': 'binary:logistic'}
evals_result = {}
bst = xgb.train(param, dtrain, num_round, watchlist, learning_rates=[0, 0, 0, 0],
evals_result=evals_result)
@@ -111,7 +113,7 @@ class TestModels(unittest.TestCase):
assert isinstance(bst, xgb.core.Booster)
def test_custom_objective(self):
param = {'max_depth': 2, 'eta': 1, 'silent': 1}
param = {'max_depth': 2, 'eta': 1, 'verbosity': 0}
watchlist = [(dtest, 'eval'), (dtrain, 'train')]
num_round = 2
@@ -152,7 +154,8 @@ class TestModels(unittest.TestCase):
def test_multi_eval_metric(self):
watchlist = [(dtest, 'eval'), (dtrain, 'train')]
param = {'max_depth': 2, 'eta': 0.2, 'silent': 1, 'objective': 'binary:logistic'}
param = {'max_depth': 2, 'eta': 0.2, 'verbosity': 0,
'objective': 'binary:logistic'}
param['eval_metric'] = ["auc", "logloss", 'error']
evals_result = {}
bst = xgb.train(param, dtrain, 4, watchlist, evals_result=evals_result)
@@ -161,7 +164,7 @@ class TestModels(unittest.TestCase):
assert set(evals_result['eval'].keys()) == {'auc', 'error', 'logloss'}
def test_fpreproc(self):
param = {'max_depth': 2, 'eta': 1, 'silent': 1,
param = {'max_depth': 2, 'eta': 1, 'verbosity': 0,
'objective': 'binary:logistic'}
num_round = 2
@@ -175,7 +178,7 @@ class TestModels(unittest.TestCase):
metrics={'auc'}, seed=0, fpreproc=fpreproc)
def test_show_stdv(self):
param = {'max_depth': 2, 'eta': 1, 'silent': 1,
param = {'max_depth': 2, 'eta': 1, 'verbosity': 0,
'objective': 'binary:logistic'}
num_round = 2
xgb.cv(param, dtrain, num_round, nfold=5,

2
tests/python/test_early_stopping.py
View File

@@ -52,7 +52,7 @@ class TestEarlyStopping(unittest.TestCase):
X = digits['data']
y = digits['target']
dm = xgb.DMatrix(X, label=y)
params = {'max_depth': 2, 'eta': 1, 'silent': 1,
params = {'max_depth': 2, 'eta': 1, 'verbosity': 0,
'objective': 'binary:logistic'}
cv = xgb.cv(params, dm, num_boost_round=10, nfold=10,

8
tests/python/test_eval_metrics.py
View File

@@ -9,25 +9,25 @@ rng = np.random.RandomState(1337)
class TestEvalMetrics(unittest.TestCase):
xgb_params_01 = {
'silent': 1,
'verbosity': 0,
'nthread': 1,
'eval_metric': 'error'
}
xgb_params_02 = {
'silent': 1,
'verbosity': 0,
'nthread': 1,
'eval_metric': ['error']
}
xgb_params_03 = {
'silent': 1,
'verbosity': 0,
'nthread': 1,
'eval_metric': ['rmse', 'error']
}
xgb_params_04 = {
'silent': 1,
'verbosity': 0,
'nthread': 1,
'eval_metric': ['error', 'rmse']
}

2
tests/python/test_interaction_constraints.py
View File

@@ -18,7 +18,7 @@ class TestInteractionConstraints(unittest.TestCase):
X = np.column_stack((x1, x2, x3))
dtrain = xgboost.DMatrix(X, label=y)
params = {'max_depth': 3, 'eta': 0.1, 'nthread': 2, 'silent': 1,
params = {'max_depth': 3, 'eta': 0.1, 'nthread': 2, 'verbosity': 0,
'interaction_constraints': '[[0, 1]]'}
num_boost_round = 100
# Fit a model that only allows interaction between x1 and x2

4
tests/python/test_linear.py
View File

@@ -30,7 +30,7 @@ def xgb_get_weights(bst):
def assert_regression_result(results, tol):
regression_results = [r for r in results if
r["param"]["objective"] == "reg:linear"]
r["param"]["objective"] == "reg:squarederror"]
for res in regression_results:
X = scale(res["dataset"].X,
with_mean=isinstance(res["dataset"].X, np.ndarray))
@@ -52,7 +52,7 @@ def assert_regression_result(results, tol):
# TODO: More robust classification tests
def assert_classification_result(results):
classification_results = [r for r in results if
r["param"]["objective"] != "reg:linear"]
r["param"]["objective"] != "reg:squarederror"]
for res in classification_results:
# Check accuracy is reasonable
assert res["eval"][-1] < 0.5, (res["dataset"].name, res["eval"][-1])

3
tests/python/test_parse_tree.py
View File

@@ -16,7 +16,8 @@ class TestTreesToDataFrame(unittest.TestCase):
def build_model(self, max_depth, num_round):
dtrain = xgb.DMatrix(dpath + 'agaricus.txt.train')
param = {'max_depth': max_depth, 'objective': 'binary:logistic', 'silent': False}
param = {'max_depth': max_depth, 'objective': 'binary:logistic',
'verbosity': 1}
num_round = num_round
bst = xgb.train(param, dtrain, num_round)
return bst

2
tests/python/test_shap.py
View File

@@ -51,7 +51,7 @@ class TestSHAP(unittest.TestCase):
def fn(max_depth, num_rounds):
# train
params = {'max_depth': max_depth, 'eta': 1, 'silent': 1}
params = {'max_depth': max_depth, 'eta': 1, 'verbosity': 0}
bst = xgb.train(params, dtrain, num_boost_round=num_rounds)
# predict

2
tests/python/test_sparse_dmatrix.py
View File

@@ -4,7 +4,7 @@ from scipy.sparse import rand
rng = np.random.RandomState(1)
param = {'max_depth': 3, 'objective': 'binary:logistic', 'silent': 1}
param = {'max_depth': 3, 'objective': 'binary:logistic', 'verbosity': 0}
def test_sparse_dmatrix_csr():

6
tests/python/test_training_continuation.py
View File

@@ -11,18 +11,18 @@ class TestTrainingContinuation(unittest.TestCase):
num_parallel_tree = 3
xgb_params_01 = {
'silent': 1,
'verbosity': 0,
'nthread': 1,
}
xgb_params_02 = {
'silent': 1,
'verbosity': 0,
'nthread': 1,
'num_parallel_tree': num_parallel_tree
}
xgb_params_03 = {
'silent': 1,
'verbosity': 0,
'nthread': 1,
'num_class': 5,
'num_parallel_tree': num_parallel_tree

9
tests/python/test_tree_regularization.py
View File

@@ -10,7 +10,8 @@ train_data = xgb.DMatrix(np.array([[1]]), label=np.array([1]))
class TestTreeRegularization(unittest.TestCase):
def test_alpha(self):
params = {
'tree_method': 'exact', 'silent': 1, 'objective': 'reg:linear',
'tree_method': 'exact', 'verbosity': 0,
'objective': 'reg:squarederror',
'eta': 1,
'lambda': 0,
'alpha': 0.1
@@ -27,7 +28,8 @@ class TestTreeRegularization(unittest.TestCase):
def test_lambda(self):
params = {
'tree_method': 'exact', 'silent': 1, 'objective': 'reg:linear',
'tree_method': 'exact', 'verbosity': 0,
'objective': 'reg:squarederror',
'eta': 1,
'lambda': 1,
'alpha': 0
@@ -44,7 +46,8 @@ class TestTreeRegularization(unittest.TestCase):
def test_alpha_and_lambda(self):
params = {
'tree_method': 'exact', 'silent': 1, 'objective': 'reg:linear',
'tree_method': 'exact', 'verbosity': 1,
'objective': 'reg:squarederror',
'eta': 1,
'lambda': 1,
'alpha': 0.1

4
tests/python/test_updaters.py
View File

@@ -33,7 +33,7 @@ class TestUpdaters(unittest.TestCase):
'max_bin': [2, 256],
'grow_policy': ['depthwise', 'lossguide'],
'max_leaves': [64, 0],
'silent': [1]}
'verbosity': [0]}
for param in parameter_combinations(variable_param):
result = run_suite(param)
assert_results_non_increasing(result, 1e-2)
@@ -45,7 +45,7 @@ class TestUpdaters(unittest.TestCase):
ag_param = {'max_depth': 2,
'tree_method': 'hist',
'eta': 1,
'silent': 1,
'verbosity': 0,
'objective': 'binary:logistic',
'eval_metric': 'auc'}
hist_res = {}

14
tests/python/test_with_pandas.py
View File

@@ -120,7 +120,7 @@ class TestPandas(unittest.TestCase):
def test_cv_as_pandas(self):
dm = xgb.DMatrix(dpath + 'agaricus.txt.train')
params = {'max_depth': 2, 'eta': 1, 'silent': 1,
params = {'max_depth': 2, 'eta': 1, 'verbosity': 0,
'objective': 'binary:logistic'}
cv = xgb.cv(params, dm, num_boost_round=10, nfold=10)
@@ -143,19 +143,19 @@ class TestPandas(unittest.TestCase):
u'train-error-mean', u'train-error-std'])
assert cv.columns.equals(exp)
params = {'max_depth': 2, 'eta': 1, 'silent': 1,
params = {'max_depth': 2, 'eta': 1, 'verbosity': 0,
'objective': 'binary:logistic', 'eval_metric': 'auc'}
cv = xgb.cv(params, dm, num_boost_round=10, nfold=10, as_pandas=True)
assert 'eval_metric' in params
assert 'auc' in cv.columns[0]
params = {'max_depth': 2, 'eta': 1, 'silent': 1,
params = {'max_depth': 2, 'eta': 1, 'verbosity': 0,
'objective': 'binary:logistic', 'eval_metric': ['auc']}
cv = xgb.cv(params, dm, num_boost_round=10, nfold=10, as_pandas=True)
assert 'eval_metric' in params
assert 'auc' in cv.columns[0]
params = {'max_depth': 2, 'eta': 1, 'silent': 1,
params = {'max_depth': 2, 'eta': 1, 'verbosity': 0,
'objective': 'binary:logistic', 'eval_metric': ['auc']}
cv = xgb.cv(params, dm, num_boost_round=10, nfold=10,
as_pandas=True, early_stopping_rounds=1)
@@ -163,19 +163,19 @@ class TestPandas(unittest.TestCase):
assert 'auc' in cv.columns[0]
assert cv.shape[0] < 10
params = {'max_depth': 2, 'eta': 1, 'silent': 1,
params = {'max_depth': 2, 'eta': 1, 'verbosity': 0,
'objective': 'binary:logistic'}
cv = xgb.cv(params, dm, num_boost_round=10, nfold=10,
as_pandas=True, metrics='auc')
assert 'auc' in cv.columns[0]
params = {'max_depth': 2, 'eta': 1, 'silent': 1,
params = {'max_depth': 2, 'eta': 1, 'verbosity': 0,
'objective': 'binary:logistic'}
cv = xgb.cv(params, dm, num_boost_round=10, nfold=10,
as_pandas=True, metrics=['auc'])
assert 'auc' in cv.columns[0]
params = {'max_depth': 2, 'eta': 1, 'silent': 1,
params = {'max_depth': 2, 'eta': 1, 'verbosity': 0,
'objective': 'binary:logistic', 'eval_metric': ['auc']}
cv = xgb.cv(params, dm, num_boost_round=10, nfold=10,
as_pandas=True, metrics='error')

3
tests/python/test_with_sklearn.py
View File

@@ -603,7 +603,8 @@ def test_RFECV():
# Regression
X, y = load_boston(return_X_y=True)
bst = xgb.XGBClassifier(booster='gblinear', learning_rate=0.1,
n_estimators=10, n_jobs=1, objective='reg:linear',
n_estimators=10, n_jobs=1,
objective='reg:squarederror',
random_state=0, verbosity=0)
rfecv = RFECV(
estimator=bst, step=1, cv=3, scoring='neg_mean_squared_error')