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

[R] Fix global feature importance and predict with 1 sample. (#7394)

Browse Source 
* [R] Fix global feature importance.

* Add implementation for tree index.  The parameter is not documented in C API since we
should work on porting the model slicing to R instead of supporting more use of tree
index.

* Fix the difference between "gain" and "total_gain".

* debug.

* Fix prediction.
This commit is contained in:
Jiaming Yuan
2021-11-05 10:07:00 +08:00
committed by GitHub
parent 48aff0eabd
commit c968217ca8
11 changed files with 119 additions and 49 deletions
Download Patch File Download Diff File Expand all files Collapse all files

12
src/c_api/c_api.cc
View File

@@ -1159,9 +1159,17 @@ XGB_DLL int XGBoosterFeatureScore(BoosterHandle handle, char const *json_config,
custom_feature_names = get<Array const>(config["feature_names"]);
}
auto& scores = learner->GetThreadLocal().ret_vec_float;
std::vector<int32_t> tree_idx;
if (!IsA<Null>(config["tree_idx"])) {
auto j_tree_idx = get<Array const>(config["tree_idx"]);
for (auto const &idx : j_tree_idx) {
tree_idx.push_back(get<Integer const>(idx));
}
}
auto &scores = learner->GetThreadLocal().ret_vec_float;
std::vector<bst_feature_t> features;
learner->CalcFeatureScore(importance, &features, &scores);
learner->CalcFeatureScore(importance, common::Span<int32_t const>(tree_idx), &features, &scores);
auto n_features = learner->GetNumFeature();
GenerateFeatureMap(learner, custom_feature_names, n_features, &feature_map);

2
src/gbm/gblinear.cc
View File

@@ -232,9 +232,11 @@ class GBLinear : public GradientBooster {
}
void FeatureScore(std::string const &importance_type,
common::Span<int32_t const> trees,
std::vector<bst_feature_t> *out_features,
std::vector<float> *out_scores) const override {
CHECK(!model_.weight.empty()) << "Model is not initialized";
CHECK(trees.empty()) << "gblinear doesn't support number of trees for feature importance.";
CHECK_EQ(importance_type, "weight")
<< "gblinear only has `weight` defined for feature importance.";
out_features->resize(this->learner_model_param_->num_feature, 0);

20
src/gbm/gbtree.h
View File

@@ -300,18 +300,28 @@ class GBTree : public GradientBooster {
}
}
void FeatureScore(std::string const &importance_type,
std::vector<bst_feature_t> *features,
std::vector<float> *scores) const override {
void FeatureScore(std::string const& importance_type, common::Span<int32_t const> trees,
std::vector<bst_feature_t>* features,
std::vector<float>* scores) const override {
// Because feature with no importance doesn't appear in the return value so
// we need to set up another pair of vectors to store the values during
// computation.
std::vector<size_t> split_counts(this->model_.learner_model_param->num_feature, 0);
std::vector<float> gain_map(this->model_.learner_model_param->num_feature, 0);
std::vector<int32_t> tree_idx;
if (trees.empty()) {
tree_idx.resize(this->model_.trees.size());
std::iota(tree_idx.begin(), tree_idx.end(), 0);
trees = common::Span<int32_t const>(tree_idx);
}
auto total_n_trees = model_.trees.size();
auto add_score = [&](auto fn) {
for (auto const &p_tree : model_.trees) {
for (auto idx : trees) {
CHECK_LE(idx, total_n_trees) << "Invalid tree index.";
auto const& p_tree = model_.trees[idx];
p_tree->WalkTree([&](bst_node_t nidx) {
auto const &node = (*p_tree)[nidx];
auto const& node = (*p_tree)[nidx];
if (!node.IsLeaf()) {
split_counts[node.SplitIndex()]++;
fn(p_tree, nidx, node.SplitIndex());

7
src/learner.cc
View File

@@ -1212,11 +1212,10 @@ class LearnerImpl : public LearnerIO {
*out_preds = &out_predictions.predictions;
}
void CalcFeatureScore(std::string const &importance_type,
std::vector<bst_feature_t> *features,
std::vector<float> *scores) override {
void CalcFeatureScore(std::string const& importance_type, common::Span<int32_t const> trees,
std::vector<bst_feature_t>* features, std::vector<float>* scores) override {
this->Configure();
gbm_->FeatureScore(importance_type, features, scores);
gbm_->FeatureScore(importance_type, trees, features, scores);
}
const std::map<std::string, std::string>& GetConfigurationArguments() const override {