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

Use DART tree weights when computing SHAPs (#5050)

Browse Source 
This PR fixes tree weights in dart being ignored when computing contributions.

* Fix ellpack page source link.
* Add tree weights to compute contribution.
This commit is contained in:
Kodi Arfer
2019-12-03 06:55:53 -05:00
committed by Jiaming Yuan
parent 64f4361b47
commit f2277e7106
12 changed files with 88 additions and 16 deletions
Download Patch File Download Diff File Expand all files Collapse all files

22
src/predictor/cpu_predictor.cc
View File

@@ -257,6 +257,7 @@ class CPUPredictor : public Predictor {
void PredictContribution(DMatrix* p_fmat, std::vector<bst_float>* out_contribs,
const gbm::GBTreeModel& model, unsigned ntree_limit,
std::vector<bst_float>* tree_weights,
bool approximate,
int condition,
unsigned condition_feature) override {
@@ -296,16 +297,23 @@ class CPUPredictor : public Predictor {
bst_float* p_contribs =
&contribs[(row_idx * ngroup + gid) * ncolumns];
feats.Fill(batch[i]);
std::vector<bst_float> this_tree_contribs;
this_tree_contribs.resize(ncolumns);
// calculate contributions
for (unsigned j = 0; j < ntree_limit; ++j) {
std::fill(this_tree_contribs.begin(), this_tree_contribs.end(), 0);
if (model.tree_info[j] != gid) {
continue;
}
if (!approximate) {
model.trees[j]->CalculateContributions(feats, root_id, p_contribs,
model.trees[j]->CalculateContributions(feats, root_id, &this_tree_contribs[0],
condition, condition_feature);
} else {
model.trees[j]->CalculateContributionsApprox(feats, root_id, p_contribs);
model.trees[j]->CalculateContributionsApprox(feats, root_id, &this_tree_contribs[0]);
}
for (int ci = 0 ; ci < ncolumns ; ++ci) {
p_contribs[ci] += this_tree_contribs[ci] *
(tree_weights == nullptr ? 1 : (*tree_weights)[j]);
}
}
feats.Drop(batch[i]);
@@ -322,6 +330,7 @@ class CPUPredictor : public Predictor {
void PredictInteractionContributions(DMatrix* p_fmat, std::vector<bst_float>* out_contribs,
const gbm::GBTreeModel& model, unsigned ntree_limit,
std::vector<bst_float>* tree_weights,
bool approximate) override {
const MetaInfo& info = p_fmat->Info();
const int ngroup = model.param.num_output_group;
@@ -340,10 +349,13 @@ class CPUPredictor : public Predictor {
// Compute the difference in effects when conditioning on each of the features on and off
// see: Axiomatic characterizations of probabilistic and
// cardinal-probabilistic interaction indices
PredictContribution(p_fmat, &contribs_diag, model, ntree_limit, approximate, 0, 0);
PredictContribution(p_fmat, &contribs_diag, model, ntree_limit,
tree_weights, approximate, 0, 0);
for (size_t i = 0; i < ncolumns + 1; ++i) {
PredictContribution(p_fmat, &contribs_off, model, ntree_limit, approximate, -1, i);
PredictContribution(p_fmat, &contribs_on, model, ntree_limit, approximate, 1, i);
PredictContribution(p_fmat, &contribs_off, model, ntree_limit,
tree_weights, approximate, -1, i);
PredictContribution(p_fmat, &contribs_on, model, ntree_limit,
tree_weights, approximate, 1, i);
for (size_t j = 0; j < info.num_row_; ++j) {
for (int l = 0; l < ngroup; ++l) {