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

Validate weights are positive values. (#6115)

Browse Source
This commit is contained in:
Jiaming Yuan 2020-09-15 09:03:55 +08:00 committed by GitHub
parent c6f2b8c841
commit b5f52f0b1b
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
6 changed files with 15 additions and 9 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
R-package/tests/testthat/test_dmatrix.R
View File

@ -64,8 +64,8 @@ test_that("xgb.DMatrix: getinfo & setinfo", {
expect_true(setinfo(dtest, 'group', c(50, 50)))
expect_error(setinfo(dtest, 'group', test_label))
# providing character values will give a warning
expect_warning(setinfo(dtest, 'weight', rep('a', nrow(test_data))))
# providing character values will give an error
expect_error(setinfo(dtest, 'weight', rep('a', nrow(test_data))))
# any other label should error
expect_error(setinfo(dtest, 'asdf', test_label))

2
demo/guide-python/data_iterator.py
View File

@ -39,7 +39,7 @@ class IterForDMatrixDemo(xgboost.core.DataIter):
rng = cupy.random.RandomState(1994)
self._data = [rng.randn(self.rows, self.cols)] * BATCHES
self._labels = [rng.randn(self.rows)] * BATCHES
self._weights = [rng.randn(self.rows)] * BATCHES
self._weights = [rng.uniform(size=self.rows)] * BATCHES
self.it = 0 # set iterator to 0
super().__init__()

3
src/data/data.cc
View File

@ -359,6 +359,9 @@ void MetaInfo::SetInfo(const char* key, const void* dptr, DataType dtype, size_t
weights.resize(num);
DISPATCH_CONST_PTR(dtype, dptr, cast_dptr,
std::copy(cast_dptr, cast_dptr + num, weights.begin()));
auto valid = std::all_of(weights.cbegin(), weights.cend(),
[](float w) { return w >= 0; });
CHECK(valid) << "Weights must be positive values.";
} else if (!std::strcmp(key, "base_margin")) {
auto& base_margin = base_margin_.HostVector();
base_margin.resize(num);

11
src/data/data.cu
View File

@ -86,6 +86,10 @@ void MetaInfo::SetInfo(const char * c_key, std::string const& interface_str) {
CopyInfoImpl(array_interface, &labels_);
} else if (key == "weight") {
CopyInfoImpl(array_interface, &weights_);
auto ptr = weights_.ConstDevicePointer();
auto valid =
thrust::all_of(thrust::device, ptr, ptr + weights_.Size(), AllOfOp{});
CHECK(valid) << "Weights must be positive values.";
} else if (key == "base_margin") {
CopyInfoImpl(array_interface, &base_margin_);
} else if (key == "group") {
@ -100,10 +104,9 @@ void MetaInfo::SetInfo(const char * c_key, std::string const& interface_str) {
} else if (key == "feature_weights") {
CopyInfoImpl(array_interface, &feature_weigths);
auto d_feature_weights = feature_weigths.ConstDeviceSpan();
auto valid =
thrust::all_of(thrust::device, d_feature_weights.data(),
d_feature_weights.data() + d_feature_weights.size(),
AllOfOp{});
auto valid = thrust::all_of(
thrust::device, d_feature_weights.data(),
d_feature_weights.data() + d_feature_weights.size(), AllOfOp{});
CHECK(valid) << "Feature weight must be greater than 0.";
return;
} else {

2
tests/python/test_with_modin.py
View File

@ -135,7 +135,7 @@ class TestModin(unittest.TestCase):
X = np.random.randn(kRows, kCols)
y = np.random.randn(kRows)
w = np.random.randn(kRows).astype(np.float32)
w = np.random.uniform(size=kRows).astype(np.float32)
w_pd = md.DataFrame(w)
data = xgb.DMatrix(X, y, w_pd)

2
tests/python/test_with_pandas.py
View File

@ -151,7 +151,7 @@ class TestPandas(unittest.TestCase):
X = np.random.randn(kRows, kCols)
y = np.random.randn(kRows)
w = np.random.randn(kRows).astype(np.float32)
w = np.random.uniform(size=kRows).astype(np.float32)
w_pd = pd.DataFrame(w)
data = xgb.DMatrix(X, y, w_pd)