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

SHAP values for feature contributions (#2438)

Browse Source 
* SHAP values for feature contributions

* Fix commenting error

* New polynomial time SHAP value estimation algorithm

* Update API to support SHAP values

* Fix merge conflicts with updates in master

* Correct submodule hashes

* Fix variable sized stack allocation

* Make lint happy

* Add docs

* Fix typo

* Adjust tolerances

* Remove unneeded def

* Fixed cpp test setup

* Updated R API and cleaned up

* Fixed test typo
This commit is contained in:
Scott Lundberg
2017-10-12 12:35:51 -07:00
committed by GitHub
parent ff9180cd73
commit 78c4188cec
16 changed files with 369 additions and 143 deletions
Download Patch File Download Diff File Expand all files Collapse all files

22
src/predictor/cpu_predictor.cc
View File

@@ -206,9 +206,9 @@ class CPUPredictor : public Predictor {
}
}
void PredictContribution(DMatrix* p_fmat,
std::vector<bst_float>* out_contribs,
const gbm::GBTreeModel& model, unsigned ntree_limit) override {
void PredictContribution(DMatrix* p_fmat, std::vector<bst_float>* out_contribs,
const gbm::GBTreeModel& model, unsigned ntree_limit,
bool approximate) override {
const int nthread = omp_get_max_threads();
InitThreadTemp(nthread, model.param.num_feature);
const MetaInfo& info = p_fmat->info();
@@ -225,10 +225,12 @@ class CPUPredictor : public Predictor {
// make sure contributions is zeroed, we could be reusing a previously
// allocated one
std::fill(contribs.begin(), contribs.end(), 0);
// initialize tree node mean values
#pragma omp parallel for schedule(static)
for (bst_omp_uint i = 0; i < ntree_limit; ++i) {
model.trees[i]->FillNodeMeanValues();
if (approximate) {
// initialize tree node mean values
#pragma omp parallel for schedule(static)
for (bst_omp_uint i = 0; i < ntree_limit; ++i) {
model.trees[i]->FillNodeMeanValues();
}
}
// start collecting the contributions
dmlc::DataIter<RowBatch>* iter = p_fmat->RowIterator();
@@ -253,7 +255,11 @@ class CPUPredictor : public Predictor {
if (model.tree_info[j] != gid) {
continue;
}
model.trees[j]->CalculateContributions(feats, root_id, p_contribs);
if (!approximate) {
model.trees[j]->CalculateContributions(feats, root_id, p_contribs);
} else {
model.trees[j]->CalculateContributionsApprox(feats, root_id, p_contribs);
}
}
feats.Drop(batch[i]);
// add base margin to BIAS