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

[FIX] change evaluation to more precision

Browse Source
This commit is contained in:
tqchen 2016-01-14 01:20:45 +00:00
parent 67fbf8d264
commit fd173e260f
2 changed files with 19 additions and 18 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

29
src/data/data.cc
View File

@ -158,23 +158,24 @@ DMatrix* DMatrix::Load(const std::string& uri,
LOG(CONSOLE) << "Partial load option on npart=" << npart;
}
}
// legacy handling of binary data loading
if (file_format == "auto" && !load_row_split) {
int magic;
std::unique_ptr<dmlc::Stream> fi(dmlc::Stream::Create(fname.c_str(), "r"));
common::PeekableInStream is(fi.get());
if (is.PeekRead(&magic, sizeof(magic)) == sizeof(magic) &&
magic == data::SimpleCSRSource::kMagic) {
std::unique_ptr<data::SimpleCSRSource> source(new data::SimpleCSRSource());
source->LoadBinary(&is);
DMatrix* dmat = DMatrix::Create(std::move(source), cache_file);
if (!silent) {
LOG(CONSOLE) << dmat->info().num_row << 'x' << dmat->info().num_col << " matrix with "
<< dmat->info().num_nonzero << " entries loaded from " << uri;
}
return dmat;
}
std::unique_ptr<dmlc::Stream> fi(dmlc::Stream::Create(fname.c_str(), "r", true));
if (fi.get() != nullptr) {
common::PeekableInStream is(fi.get());
if (is.PeekRead(&magic, sizeof(magic)) == sizeof(magic) &&
magic == data::SimpleCSRSource::kMagic) {
std::unique_ptr<data::SimpleCSRSource> source(new data::SimpleCSRSource());
source->LoadBinary(&is);
DMatrix* dmat = DMatrix::Create(std::move(source), cache_file);
if (!silent) {
LOG(CONSOLE) << dmat->info().num_row << 'x' << dmat->info().num_col << " matrix with "
<< dmat->info().num_nonzero << " entries loaded from " << uri;
}
return dmat;
}
}
}
std::string ftype = file_format;

8
src/metric/elementwise_metric.cc
View File

@ -28,15 +28,15 @@ struct EvalEWiseBase : public Metric {
CHECK_EQ(preds.size(), info.labels.size())
<< "label and prediction size not match, "
<< "hint: use merror or mlogloss for multi-class classification";
const bst_omp_uint ndata = static_cast<bst_omp_uint>(info.labels.size());
float sum = 0.0, wsum = 0.0;
const omp_ulong ndata = static_cast<omp_ulong>(info.labels.size());
double sum = 0.0, wsum = 0.0;
#pragma omp parallel for reduction(+: sum, wsum) schedule(static)
for (bst_omp_uint i = 0; i < ndata; ++i) {
for (omp_ulong i = 0; i < ndata; ++i) {
const float wt = info.GetWeight(i);
sum += Derived::EvalRow(info.labels[i], preds[i]) * wt;
wsum += wt;
}
float dat[2]; dat[0] = sum, dat[1] = wsum;
double dat[2]; dat[0] = sum, dat[1] = wsum;
if (distributed) {
rabit::Allreduce<rabit::op::Sum>(dat, 2);
}