void Tree::bootstrapWeighted() {
// Use fraction (default 63.21%) of the samples
size_t num_samples_inbag = (size_t) num_samples * sample_fraction;
// Reserve space, reserve a little more to be save)
sampleIDs[0].reserve(num_samples_inbag);
oob_sampleIDs.reserve(num_samples * (exp(-sample_fraction) + 0.1));
std::discrete_distribution<> weighted_dist(case_weights->begin(), case_weights->end());
// Start with all samples OOB
inbag_counts.resize(num_samples, 0);
// Draw num_samples samples with replacement (n out of n) as inbag and mark as not OOB
for (size_t s = 0; s < num_samples_inbag; ++s) {
size_t draw = weighted_dist(random_number_generator);
sampleIDs[0].push_back(draw);
++inbag_counts[draw];
}
// Save OOB samples
for (size_t s = 0; s < inbag_counts.size(); ++s) {
if (inbag_counts[s] == 0) {
oob_sampleIDs.push_back(s);
}
}
num_samples_oob = oob_sampleIDs.size();
if (!keep_inbag) {
inbag_counts.clear();
}
}
void drawWithoutReplacementWeighted(std::vector<size_t>& result, std::mt19937_64& random_number_generator,
std::vector<size_t>& indizes, size_t num_samples, std::vector<double>& weights) {
result.reserve(num_samples);
// Set all to not selected
std::vector<bool> temp;
temp.resize(indizes.size(), false);
std::discrete_distribution<> weighted_dist(weights.begin(), weights.end());
for (size_t i = 0; i < num_samples; ++i) {
size_t draw;
do {
draw = weighted_dist(random_number_generator);
} while (temp[draw]);
temp[draw] = true;
result.push_back(indizes[draw]);
}
}
