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

Merge branch 'master' into unity

Browse Source 
Conflicts:
	src/learner/evaluation-inl.hpp
	wrapper/xgboost_R.cpp
	wrapper/xgboost_wrapper.cpp
	wrapper/xgboost_wrapper.h
This commit is contained in:
tqchen
2014-08-26 20:32:07 -07:00
parent 2623ab0a60 84e5fc285b
commit 414e7f27ff
21 changed files with 169 additions and 146 deletions
Download Patch File Download Diff File Expand all files Collapse all files

5
src/data.h
View File

@@ -12,6 +12,7 @@
#include <cstring>
#include <algorithm>
#include "utils/io.h"
#include "utils/omp.h"
#include "utils/utils.h"
#include "utils/iterator.h"
#include "utils/random.h"
@@ -370,9 +371,9 @@ class FMatrixS : public FMatrixInterface<FMatrixS>{
}
// sort columns
unsigned ncol = static_cast<unsigned>(this->NumCol());
bst_omp_uint ncol = static_cast<bst_omp_uint>(this->NumCol());
#pragma omp parallel for schedule(static)
for (unsigned i = 0; i < ncol; ++i) {
for (bst_omp_uint i = 0; i < ncol; ++i) {
std::sort(&col_data_[0] + col_ptr_[i],
&col_data_[0] + col_ptr_[i + 1], Entry::CmpValue);
}

14
src/gbm/gblinear-inl.hpp
View File

@@ -51,9 +51,9 @@ class GBLinear : public IGradBooster<FMatrix> {
// for all the output group
for (int gid = 0; gid < ngroup; ++gid) {
double sum_grad = 0.0, sum_hess = 0.0;
const unsigned ndata = static_cast<unsigned>(rowset.size());
const bst_omp_uint ndata = static_cast<bst_omp_uint>(rowset.size());
#pragma omp parallel for schedule(static) reduction(+: sum_grad, sum_hess)
for (unsigned i = 0; i < ndata; ++i) {
for (bst_omp_uint i = 0; i < ndata; ++i) {
bst_gpair &p = gpair[rowset[i] * ngroup + gid];
if (p.hess >= 0.0f) {
sum_grad += p.grad; sum_hess += p.hess;
@@ -65,7 +65,7 @@ class GBLinear : public IGradBooster<FMatrix> {
model.bias()[gid] += dw;
// update grad value
#pragma omp parallel for schedule(static)
for (unsigned i = 0; i < ndata; ++i) {
for (bst_omp_uint i = 0; i < ndata; ++i) {
bst_gpair &p = gpair[rowset[i] * ngroup + gid];
if (p.hess >= 0.0f) {
p.grad += p.hess * dw;
@@ -73,9 +73,9 @@ class GBLinear : public IGradBooster<FMatrix> {
}
}
// number of features
const unsigned nfeat = static_cast<unsigned>(feat_index.size());
const bst_omp_uint nfeat = static_cast<bst_omp_uint>(feat_index.size());
#pragma omp parallel for schedule(static)
for (unsigned i = 0; i < nfeat; ++i) {
for (bst_omp_uint i = 0; i < nfeat; ++i) {
const bst_uint fid = feat_index[i];
for (int gid = 0; gid < ngroup; ++gid) {
double sum_grad = 0.0, sum_hess = 0.0;
@@ -117,9 +117,9 @@ class GBLinear : public IGradBooster<FMatrix> {
// k is number of group
preds.resize(preds.size() + batch.size * ngroup);
// parallel over local batch
const unsigned nsize = static_cast<unsigned>(batch.size);
const bst_omp_uint nsize = static_cast<bst_omp_uint>(batch.size);
#pragma omp parallel for schedule(static)
for (unsigned i = 0; i < nsize; ++i) {
for (bst_omp_uint i = 0; i < nsize; ++i) {
const size_t ridx = batch.base_rowid + i;
// loop over output groups
for (int gid = 0; gid < ngroup; ++gid) {

7
src/gbm/gbtree-inl.hpp
View File

@@ -94,8 +94,9 @@ class GBTree : public IGradBooster<FMatrix> {
"must have exactly ngroup*nrow gpairs");
std::vector<bst_gpair> tmp(gpair.size()/ngroup);
for (int gid = 0; gid < ngroup; ++gid) {
bst_omp_uint nsize = static_cast<bst_omp_uint>(tmp.size());
#pragma omp parallel for schedule(static)
for (size_t i = 0; i < tmp.size(); ++i) {
for (bst_omp_uint i = 0; i < nsize; ++i) {
tmp[i] = gpair[i * ngroup + gid];
}
this->BoostNewTrees(tmp, fmat, info, gid);
@@ -125,9 +126,9 @@ class GBTree : public IGradBooster<FMatrix> {
while (iter->Next()) {
const SparseBatch &batch = iter->Value();
// parallel over local batch
const unsigned nsize = static_cast<unsigned>(batch.size);
const bst_omp_uint nsize = static_cast<bst_omp_uint>(batch.size);
#pragma omp parallel for schedule(static)
for (unsigned i = 0; i < nsize; ++i) {
for (bst_omp_uint i = 0; i < nsize; ++i) {
const int tid = omp_get_thread_num();
tree::RegTree::FVec &feats = thread_temp[tid];
int64_t ridx = static_cast<int64_t>(batch.base_rowid + i);

21
src/learner/evaluation-inl.hpp
View File

@@ -27,10 +27,12 @@ struct EvalEWiseBase : public IEvaluator {
utils::Check(info.labels.size() != 0, "label set cannot be empty");
utils::Check(preds.size() % info.labels.size() == 0,
"label and prediction size not match");
const unsigned ndata = static_cast<unsigned>(info.labels.size());
const bst_omp_uint ndata = static_cast<bst_omp_uint>(info.labels.size());
float sum = 0.0, wsum = 0.0;
#pragma omp parallel for reduction(+: sum, wsum) schedule(static)
for (unsigned i = 0; i < ndata; ++i) {
for (bst_omp_uint i = 0; i < ndata; ++i) {
const float wt = info.GetWeight(i);
sum += Derived::EvalRow(info.labels[i], preds[i]) * wt;
wsum += wt;
@@ -149,12 +151,13 @@ struct EvalAMS : public IEvaluator {
}
virtual float Eval(const std::vector<float> &preds,
const MetaInfo &info) const {
const unsigned ndata = static_cast<unsigned>(info.labels.size());
const bst_omp_uint ndata = static_cast<bst_omp_uint>(info.labels.size());
utils::Check(info.weights.size() == ndata, "we need weight to evaluate ams");
std::vector< std::pair<float, unsigned> > rec(ndata);
#pragma omp parallel for schedule(static)
for (unsigned i = 0; i < ndata; ++i) {
for (bst_omp_uint i = 0; i < ndata; ++i) {
rec[i] = std::make_pair(preds[i], i);
}
std::sort(rec.begin(), rec.end(), CmpFirst);
@@ -163,7 +166,7 @@ struct EvalAMS : public IEvaluator {
const double br = 10.0;
unsigned thresindex = 0;
double s_tp = 0.0, b_fp = 0.0, tams = 0.0;
for (unsigned i = 0; i < ndata-1 && i < ntop; ++i) {
for (unsigned i = 0; i < static_cast<unsigned>(ndata-1) && i < ntop; ++i) {
const unsigned ridx = rec[i].second;
const float wt = info.weights[ridx];
if (info.labels[ridx] > 0.5f) {
@@ -257,7 +260,7 @@ struct EvalAuc : public IEvaluator {
const std::vector<unsigned> &gptr = info.group_ptr.size() == 0 ? tgptr : info.group_ptr;
utils::Check(gptr.back() == info.labels.size(),
"EvalAuc: group structure must match number of prediction");
const unsigned ngroup = static_cast<unsigned>(gptr.size() - 1);
const bst_omp_uint ngroup = static_cast<bst_omp_uint>(gptr.size() - 1);
// sum statictis
double sum_auc = 0.0f;
#pragma omp parallel reduction(+:sum_auc)
@@ -265,7 +268,7 @@ struct EvalAuc : public IEvaluator {
// each thread takes a local rec
std::vector< std::pair<float, unsigned> > rec;
#pragma omp for schedule(static)
for (unsigned k = 0; k < ngroup; ++k) {
for (bst_omp_uint k = 0; k < ngroup; ++k) {
rec.clear();
for (unsigned j = gptr[k]; j < gptr[k + 1]; ++j) {
rec.push_back(std::make_pair(preds[j], j));
@@ -315,7 +318,7 @@ struct EvalRankList : public IEvaluator {
utils::Assert(gptr.size() != 0, "must specify group when constructing rank file");
utils::Assert(gptr.back() == preds.size(),
"EvalRanklist: group structure must match number of prediction");
const unsigned ngroup = static_cast<unsigned>(gptr.size() - 1);
const bst_omp_uint ngroup = static_cast<bst_omp_uint>(gptr.size() - 1);
// sum statistics
double sum_metric = 0.0f;
#pragma omp parallel reduction(+:sum_metric)
@@ -323,7 +326,7 @@ struct EvalRankList : public IEvaluator {
// each thread takes a local rec
std::vector< std::pair<float, unsigned> > rec;
#pragma omp for schedule(static)
for (unsigned k = 0; k < ngroup; ++k) {
for (bst_omp_uint k = 0; k < ngroup; ++k) {
rec.clear();
for (unsigned j = gptr[k]; j < gptr[k + 1]; ++j) {
rec.push_back(std::make_pair(preds[j], static_cast<int>(info.labels[j])));

13
src/learner/learner-inl.hpp
View File

@@ -79,6 +79,11 @@ class BoostLearner {
* \param val value of the parameter
*/
inline void SetParam(const char *name, const char *val) {
// in this version, bst: prefix is no longer required
if (strncmp(name, "bst:", 4) != 0) {
std::string n = "bst:"; n += name;
this->SetParam(n.c_str(), val);
}
if (!strcmp(name, "silent")) silent = atoi(val);
if (!strcmp(name, "prob_buffer_row")) prob_buffer_row = static_cast<float>(atof(val));
if (!strcmp(name, "eval_metric")) evaluator_.AddEval(val);
@@ -91,7 +96,7 @@ class BoostLearner {
if (!strcmp(name, "objective")) name_obj_ = val;
if (!strcmp(name, "booster")) name_gbm_ = val;
mparam.SetParam(name, val);
}
}
if (gbm_ != NULL) gbm_->SetParam(name, val);
if (obj_ != NULL) obj_->SetParam(name, val);
if (gbm_ == NULL || obj_ == NULL) {
@@ -248,17 +253,17 @@ class BoostLearner {
data.info.info, out_preds);
// add base margin
std::vector<float> &preds = *out_preds;
const unsigned ndata = static_cast<unsigned>(preds.size());
const bst_omp_uint ndata = static_cast<bst_omp_uint>(preds.size());
if (data.info.base_margin.size() != 0) {
utils::Check(preds.size() == data.info.base_margin.size(),
"base_margin.size does not match with prediction size");
#pragma omp parallel for schedule(static)
for (unsigned j = 0; j < ndata; ++j) {
for (bst_omp_uint j = 0; j < ndata; ++j) {
preds[j] += data.info.base_margin[j];
}
} else {
#pragma omp parallel for schedule(static)
for (unsigned j = 0; j < ndata; ++j) {
for (bst_omp_uint j = 0; j < ndata; ++j) {
preds[j] += mparam.base_score;
}
}

20
src/learner/objective-inl.hpp
View File

@@ -116,9 +116,9 @@ class RegLossObj : public IObjFunction{
gpair.resize(preds.size());
// start calculating gradient
const unsigned nstep = static_cast<unsigned>(info.labels.size());
const unsigned ndata = static_cast<unsigned>(preds.size());
const bst_omp_uint ndata = static_cast<bst_omp_uint>(preds.size());
#pragma omp parallel for schedule(static)
for (unsigned i = 0; i < ndata; ++i) {
for (bst_omp_uint i = 0; i < ndata; ++i) {
const unsigned j = i % nstep;
float p = loss.PredTransform(preds[i]);
float w = info.GetWeight(j);
@@ -132,9 +132,9 @@ class RegLossObj : public IObjFunction{
}
virtual void PredTransform(std::vector<float> *io_preds) {
std::vector<float> &preds = *io_preds;
const unsigned ndata = static_cast<unsigned>(preds.size());
const bst_omp_uint ndata = static_cast<bst_omp_uint>(preds.size());
#pragma omp parallel for schedule(static)
for (unsigned j = 0; j < ndata; ++j) {
for (bst_omp_uint j = 0; j < ndata; ++j) {
preds[j] = loss.PredTransform(preds[j]);
}
}
@@ -169,12 +169,12 @@ class SoftmaxMultiClassObj : public IObjFunction {
std::vector<bst_gpair> &gpair = *out_gpair;
gpair.resize(preds.size());
const unsigned nstep = static_cast<unsigned>(info.labels.size() * nclass);
const unsigned ndata = static_cast<unsigned>(preds.size() / nclass);
const bst_omp_uint ndata = static_cast<bst_omp_uint>(preds.size() / nclass);
#pragma omp parallel
{
std::vector<float> rec(nclass);
#pragma omp for schedule(static)
for (unsigned i = 0; i < ndata; ++i) {
for (bst_omp_uint i = 0; i < ndata; ++i) {
for (int k = 0; k < nclass; ++k) {
rec[k] = preds[i * nclass + k];
}
@@ -210,13 +210,13 @@ class SoftmaxMultiClassObj : public IObjFunction {
utils::Check(nclass != 0, "must set num_class to use softmax");
std::vector<float> &preds = *io_preds;
std::vector<float> tmp;
const unsigned ndata = static_cast<unsigned>(preds.size()/nclass);
const bst_omp_uint ndata = static_cast<bst_omp_uint>(preds.size()/nclass);
if (prob == 0) tmp.resize(ndata);
#pragma omp parallel
{
std::vector<float> rec(nclass);
#pragma omp for schedule(static)
for (unsigned j = 0; j < ndata; ++j) {
for (bst_omp_uint j = 0; j < ndata; ++j) {
for (int k = 0; k < nclass; ++k) {
rec[k] = preds[j * nclass + k];
}
@@ -263,7 +263,7 @@ class LambdaRankObj : public IObjFunction {
const std::vector<unsigned> &gptr = info.group_ptr.size() == 0 ? tgptr : info.group_ptr;
utils::Check(gptr.size() != 0 && gptr.back() == info.labels.size(),
"group structure not consistent with #rows");
const unsigned ngroup = static_cast<unsigned>(gptr.size() - 1);
const bst_omp_uint ngroup = static_cast<bst_omp_uint>(gptr.size() - 1);
#pragma omp parallel
{
// parall construct, declare random number generator here, so that each
@@ -273,7 +273,7 @@ class LambdaRankObj : public IObjFunction {
std::vector<ListEntry> lst;
std::vector< std::pair<float, unsigned> > rec;
#pragma omp for schedule(static)
for (unsigned k = 0; k < ngroup; ++k) {
for (bst_omp_uint k = 0; k < ngroup; ++k) {
lst.clear(); pairs.clear();
for (unsigned j = gptr[k]; j < gptr[k+1]; ++j) {
lst.push_back(ListEntry(preds[j], info.labels[j], j));

16
src/tree/updater_colmaker-inl.hpp
View File

@@ -186,9 +186,9 @@ class ColMaker: public IUpdater<FMatrix> {
}
const std::vector<bst_uint> &rowset = fmat.buffered_rowset();
// setup position
const unsigned ndata = static_cast<unsigned>(rowset.size());
const bst_omp_uint ndata = static_cast<bst_omp_uint>(rowset.size());
#pragma omp parallel for schedule(static)
for (unsigned i = 0; i < ndata; ++i) {
for (bst_omp_uint i = 0; i < ndata; ++i) {
const bst_uint ridx = rowset[i];
const int tid = omp_get_thread_num();
if (position[ridx] < 0) continue;
@@ -286,12 +286,12 @@ class ColMaker: public IUpdater<FMatrix> {
feat_set.resize(n);
}
// start enumeration
const unsigned nsize = static_cast<unsigned>(feat_set.size());
const bst_omp_uint nsize = static_cast<bst_omp_uint>(feat_set.size());
#if defined(_OPENMP)
const int batch_size = std::max(static_cast<int>(nsize / this->nthread / 32), 1);
#endif
#pragma omp parallel for schedule(dynamic, batch_size)
for (unsigned i = 0; i < nsize; ++i) {
for (bst_omp_uint i = 0; i < nsize; ++i) {
const unsigned fid = feat_set[i];
const int tid = omp_get_thread_num();
if (param.need_forward_search(fmat.GetColDensity(fid))) {
@@ -321,9 +321,9 @@ class ColMaker: public IUpdater<FMatrix> {
inline void ResetPosition(const std::vector<int> &qexpand, const FMatrix &fmat, const RegTree &tree) {
const std::vector<bst_uint> &rowset = fmat.buffered_rowset();
// step 1, set default direct nodes to default, and leaf nodes to -1
const unsigned ndata = static_cast<unsigned>(rowset.size());
const bst_omp_uint ndata = static_cast<bst_omp_uint>(rowset.size());
#pragma omp parallel for schedule(static)
for (unsigned i = 0; i < ndata; ++i) {
for (bst_omp_uint i = 0; i < ndata; ++i) {
const bst_uint ridx = rowset[i];
const int nid = position[ridx];
if (nid >= 0) {
@@ -344,9 +344,9 @@ class ColMaker: public IUpdater<FMatrix> {
std::sort(fsplits.begin(), fsplits.end());
fsplits.resize(std::unique(fsplits.begin(), fsplits.end()) - fsplits.begin());
// start put things into right place
const unsigned nfeats = static_cast<unsigned>(fsplits.size());
const bst_omp_uint nfeats = static_cast<bst_omp_uint>(fsplits.size());
#pragma omp parallel for schedule(dynamic, 1)
for (unsigned i = 0; i < nfeats; ++i) {
for (bst_omp_uint i = 0; i < nfeats; ++i) {
const unsigned fid = fsplits[i];
for (typename FMatrix::ColIter it = fmat.GetSortedCol(fid); it.Next();) {
const bst_uint ridx = it.rindex();

4
src/tree/updater_refresh-inl.hpp
View File

@@ -56,9 +56,9 @@ class TreeRefresher: public IUpdater<FMatrix> {
const SparseBatch &batch = iter->Value();
utils::Check(batch.size < std::numeric_limits<unsigned>::max(),
"too large batch size ");
const unsigned nbatch = static_cast<unsigned>(batch.size);
const bst_omp_uint nbatch = static_cast<bst_omp_uint>(batch.size);
#pragma omp parallel for schedule(static)
for (unsigned i = 0; i < nbatch; ++i) {
for (bst_omp_uint i = 0; i < nbatch; ++i) {
SparseBatch::Inst inst = batch[i];
const int tid = omp_get_thread_num();
const bst_uint ridx = static_cast<bst_uint>(batch.base_rowid + i);

12
src/utils/matrix_csr.h
View File

@@ -17,26 +17,26 @@ namespace utils {
* \tparam IndexType type of index used to store the index position, usually unsigned or size_t
* \tparam whether enabling the usage of aclist, this option must be enabled manually
*/
template<typename IndexType, bool UseAcList = false>
template<typename IndexType, bool UseAcList = false, typename SizeType = size_t>
struct SparseCSRMBuilder {
private:
/*! \brief dummy variable used in the indicator matrix construction */
std::vector<size_t> dummy_aclist;
/*! \brief pointer to each of the row */
std::vector<size_t> &rptr;
std::vector<SizeType> &rptr;
/*! \brief index of nonzero entries in each row */
std::vector<IndexType> &findex;
/*! \brief a list of active rows, used when many rows are empty */
std::vector<size_t> &aclist;
public:
SparseCSRMBuilder(std::vector<size_t> &p_rptr,
SparseCSRMBuilder(std::vector<SizeType> &p_rptr,
std::vector<IndexType> &p_findex)
:rptr(p_rptr), findex(p_findex), aclist(dummy_aclist) {
Assert(!UseAcList, "enabling bug");
}
/*! \brief use with caution! rptr must be cleaned before use */
SparseCSRMBuilder(std::vector<size_t> &p_rptr,
SparseCSRMBuilder(std::vector<SizeType> &p_rptr,
std::vector<IndexType> &p_findex,
std::vector<size_t> &p_aclist)
:rptr(p_rptr), findex(p_findex), aclist(p_aclist) {
@@ -62,7 +62,7 @@ struct SparseCSRMBuilder {
* \param row_id the id of the row
* \param nelem number of element budget add to this row
*/
inline void AddBudget(size_t row_id, size_t nelem = 1) {
inline void AddBudget(size_t row_id, SizeType nelem = 1) {
if (rptr.size() < row_id + 2) {
rptr.resize(row_id + 2, 0);
}
@@ -101,7 +101,7 @@ struct SparseCSRMBuilder {
* element to each row, the number of calls shall be exactly same as add_budget
*/
inline void PushElem(size_t row_id, IndexType col_id) {
size_t &rp = rptr[row_id + 1];
SizeType &rp = rptr[row_id + 1];
findex[rp++] = col_id;
}
/*!

10
src/utils/omp.h
View File

@@ -21,4 +21,14 @@ inline int omp_get_thread_num() { return 0; }
inline int omp_get_num_threads() { return 1; }
inline void omp_set_num_threads(int nthread) {}
#endif
// loop variable used in openmp
namespace xgboost {
#ifdef _MSC_VER
typedef int bst_omp_uint;
#else
typedef unsigned bst_omp_uint;
#endif
} // namespace xgboost
#endif // XGBOOST_UTILS_OMP_H_