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

[jvm-packages]add feature size for LabelPoint and DataBatch (#5303)

Browse Source 
* fix type error

* Validate number of features.

* resolve comments

* add feature size for LabelPoint and DataBatch

* pass the feature size to native

* move feature size validating tests into a separate suite

* resolve comments

Co-authored-by: fis <jm.yuan@outlook.com>
This commit is contained in:
Bobby Wang
2020-04-08 07:49:52 +08:00
committed by GitHub
parent 8bc595ea1e
commit ad826e913f
17 changed files with 193 additions and 75 deletions
Download Patch File Download Diff File Expand all files Collapse all files

16
src/learner.cc
View File

@@ -1063,19 +1063,9 @@ class LearnerImpl : public LearnerIO {
return tparam_.dsplit == DataSplitMode::kRow ||
tparam_.dsplit == DataSplitMode::kAuto;
};
bool const valid_features =
!row_based_split() ||
(learner_model_param_.num_feature == p_fmat->Info().num_col_);
std::string const msg {
"Number of columns does not match number of features in booster."
};
if (generic_parameters_.validate_features) {
CHECK_EQ(learner_model_param_.num_feature, p_fmat->Info().num_col_) << msg;
} else if (!valid_features) {
// Remove this and make the equality check fatal once spark can fix all failing tests.
LOG(WARNING) << msg << " "
<< "Columns: " << p_fmat->Info().num_col_ << " "
<< "Features: " << learner_model_param_.num_feature;
if (row_based_split()) {
CHECK_EQ(learner_model_param_.num_feature, p_fmat->Info().num_col_)
<< "Number of columns does not match number of features in booster.";
}
}