void GBDT::LogLossProcess(DataVector *d, size_t samples, int i) {
#ifdef USE_OPENMP
#pragma omp parallel for
#endif
for (size_t j = 0; j < samples; ++j) {
ValueType p = Predict(*(*d)[j], i);
(*d)[j]->target =
static_cast<ValueType>(LogitLossGradient((*d)[j]->label, p));
}
if (g_conf.debug) {
Auc auc;
DataVector::iterator iter = d->begin();
for ( ; iter != d->end(); ++iter) {
ValueType p = Logit(Predict(**iter, i));
auc.Add(p, (*iter)->label);
}
std::cout << "auc: " << auc.CalculateAuc() << std::endl;
}
}
void GBDT::Fit(DataVector *d) {
delete[] trees;
trees = new RegressionTree[g_conf.iterations];
size_t samples = d->size();
if (g_conf.data_sample_ratio < 1) {
samples = static_cast<size_t>(d->size() * g_conf.data_sample_ratio);
}
Init(*d, d->size());
for (size_t i = 0; i < g_conf.iterations; ++i) {
std::cout << "iteration: " << i << std::endl;
if (samples < d->size()) {
#ifndef USE_OPENMP
std::random_shuffle(d->begin(), d->end());
#else
__gnu_parallel::random_shuffle(d->begin(), d->end());
#endif
}
if (g_conf.loss == SQUARED_ERROR) {
for (size_t j = 0; j < samples; ++j) {
ValueType p = Predict(*(*d)[j], i);
(*d)[j]->target = (*d)[j]->label - p;
}
if (g_conf.debug) {
double s = 0;
double c = 0;
DataVector::iterator iter = d->begin();
for ( ; iter != d->end(); ++iter) {
ValueType p = Predict(**iter, i);
s += Squared((*iter)->label - p) * (*iter)->weight;
c += (*iter)->weight;
}
std::cout << "rmse: " << std::sqrt(s / c) << std::endl;
}
} else if (g_conf.loss == LOG_LIKELIHOOD) {
for (size_t j = 0; j < samples; ++j) {
ValueType p = Predict(*(*d)[j], i);
(*d)[j]->target =
static_cast<ValueType>(LogitLossGradient((*d)[j]->label, p));
}
if (g_conf.debug) {
Auc auc;
DataVector::iterator iter = d->begin();
for ( ; iter != d->end(); ++iter) {
ValueType p = Logit(Predict(**iter, i));
auc.Add(p, (*iter)->label);
}
std::cout << "auc: " << auc.CalculateAuc() << std::endl;
}
}
trees[i].Fit(d, samples);
}
// Calculate gain
delete[] gain;
gain = new double[g_conf.number_of_feature];
for (size_t i = 0; i < g_conf.number_of_feature; ++i) {
gain[i] = 0.0;
}
for (size_t j = 0; j < iterations; ++j) {
double *g = trees[j].GetGain();
for (size_t i = 0; i < g_conf.number_of_feature; ++i) {
gain[i] += g[i];
}
}
}
