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

Support configuring constraints by feature names (#6783)

Browse Source 
Co-authored-by: fis <jm.yuan@outlook.com>
This commit is contained in:
giladmaya
2021-04-04 01:53:33 +03:00
committed by GitHub
parent 7e06c81894
commit aa0d8f20c1
3 changed files with 124 additions and 7 deletions
Download Patch File Download Diff File Expand all files Collapse all files

40
tests/python/test_monotone_constraints.py
View File

@@ -14,7 +14,7 @@ def is_decreasing(y):
return np.count_nonzero(np.diff(y) > 0.0) == 0
def is_correctly_constrained(learner):
def is_correctly_constrained(learner, feature_names=None):
n = 100
variable_x = np.linspace(0, 1, n).reshape((n, 1))
fixed_xs_values = np.linspace(0, 1, n)
@@ -22,13 +22,15 @@ def is_correctly_constrained(learner):
for i in range(n):
fixed_x = fixed_xs_values[i] * np.ones((n, 1))
monotonically_increasing_x = np.column_stack((variable_x, fixed_x))
monotonically_increasing_dset = xgb.DMatrix(monotonically_increasing_x)
monotonically_increasing_dset = xgb.DMatrix(monotonically_increasing_x,
feature_names=feature_names)
monotonically_increasing_y = learner.predict(
monotonically_increasing_dset
)
monotonically_decreasing_x = np.column_stack((fixed_x, variable_x))
monotonically_decreasing_dset = xgb.DMatrix(monotonically_decreasing_x)
monotonically_decreasing_dset = xgb.DMatrix(monotonically_decreasing_x,
feature_names=feature_names)
monotonically_decreasing_y = learner.predict(
monotonically_decreasing_dset
)
@@ -101,6 +103,38 @@ class TestMonotoneConstraints:
assert is_correctly_constrained(constrained_hist_method)
@pytest.mark.parametrize('format', [dict, list])
def test_monotone_constraints_feature_names(self, format):
# next check monotonicity when initializing monotone_constraints by feature names
params = {
'tree_method': 'hist', 'verbosity': 1,
'grow_policy': 'lossguide',
'monotone_constraints': {'feature_0': 1, 'feature_1': -1}
}
if format == list:
params = list(params.items())
with pytest.raises(ValueError):
xgb.train(params, training_dset)
feature_names =[ 'feature_0', 'feature_2']
training_dset_w_feature_names = xgb.DMatrix(x, label=y, feature_names=feature_names)
with pytest.raises(ValueError):
xgb.train(params, training_dset_w_feature_names)
feature_names =[ 'feature_0', 'feature_1']
training_dset_w_feature_names = xgb.DMatrix(x, label=y, feature_names=feature_names)
constrained_learner = xgb.train(
params, training_dset_w_feature_names
)
assert is_correctly_constrained(constrained_learner, feature_names)
@pytest.mark.skipif(**tm.no_sklearn())
def test_training_accuracy(self):
from sklearn.metrics import accuracy_score