group_variance.hpp

Go to the documentation of this file.

#ifndef TATAMI_STATS_GROUP_VARIANCE_HPP
#define TATAMI_STATS_GROUP_VARIANCE_HPP
 
#include <vector>
#include <algorithm>
#include <cstddef>
#include <optional>
#include <cassert>
#include <limits>
#include <cmath>
 
#include "tatami/tatami.hpp"
#include "sanisizer/sanisizer.hpp"
 
#include "group_rss.hpp"
#include "skip_nan/group_rss.hpp"
#include "utils.hpp"
 
namespace tatami_stats {
 
struct GroupVarianceOptions {
    bool skip_nan = false;
 
    int num_threads = 1;
};
 
template<typename Output_>
struct GroupVarianceBuffers {
    std::vector<Output_*> mean;
 
    std::vector<Output_*> variance;
};
 
template<typename Value_, typename Index_, typename Group_, typename Output_>
void group_variance(
    bool row,
    const tatami::Matrix<Value_, Index_>& mat,
    const Group_* const group,
    const std::size_t num_groups,
    GroupVarianceBuffers<Output_>& output,
    const GroupVarianceOptions& opt
) {
    assert(sanisizer::is_equal(num_groups, output.mean.size()));
    assert(sanisizer::is_equal(num_groups, output.variance.size()));
    const auto dim = (row ? mat.nrow() : mat.ncol());
 
    nanable_ifelse<Value_>(
        opt.skip_nan,
        [&]() -> void {
            skip_nan::GroupRssBuffers<Output_, Index_> tmp;
            tmp.mean = output.mean;
            tmp.rss = output.variance;
 
            auto count = sanisizer::create<std::vector<std::vector<Index_> > >(num_groups);
            tmp.count.reserve(num_groups);
            for (std::size_t g = 0; g < num_groups; ++g) {
                tatami::resize_container_to_Index_size(count[g], dim);
                tmp.count.push_back(count[g].data());
            }
 
            skip_nan::GroupRssOptions ropt;
            ropt.num_threads = opt.num_threads;
            skip_nan::group_rss(row, mat, group, num_groups, tmp, ropt);
            for (std::size_t g = 0; g < num_groups; ++g) {
                quickstats::rss_to_variance(dim, count[g].data(), output.variance[g]);
            }
        },
        [&]() -> void {
            GroupRssBuffers<Output_, Index_> tmp;
            tmp.mean = output.mean;
            tmp.rss = output.variance;
            auto group_sizes = sanisizer::create<std::vector<Index_> >(num_groups);
            tmp.count = group_sizes.data();
 
            GroupRssOptions ropt;
            ropt.num_threads = opt.num_threads;
            group_rss(row, mat, group, num_groups, tmp, ropt);
            for (std::size_t g = 0; g < num_groups; ++g) {
                quickstats::rss_to_variance(dim, group_sizes[g], output.variance[g]);
            }
        }
    );
}
 
template<typename Output_>
struct GroupVarianceResult {
    std::vector<std::vector<Output_> > mean;
 
    std::vector<std::vector<Output_> > variance;
};
 
template<typename Output_ = double, typename Value_, typename Index_, typename Group_> 
GroupVarianceResult<Output_> group_variance(
    bool row,
    const tatami::Matrix<Value_, Index_>& mat,
    const Group_* const group,
    const std::size_t num_groups,
    const GroupVarianceOptions& opt
) {
    GroupVarianceResult<Output_> output;
    sanisizer::resize(output.mean, num_groups);
    sanisizer::resize(output.variance, num_groups);
 
    GroupVarianceBuffers<Output_> buffers;
    sanisizer::resize(buffers.mean, num_groups);
    sanisizer::resize(buffers.variance, num_groups);
    const auto dim = (row ? mat.nrow() : mat.ncol());
 
    for (std::size_t g = 0; g < num_groups; ++g) {
        tatami::resize_container_to_Index_size(output.mean[g], dim
#ifdef TATAMI_STATS_TEST_DIRTY
            , -1
#endif
        );
        buffers.mean[g] = output.mean[g].data();
        tatami::resize_container_to_Index_size(output.variance[g], dim
#ifdef TATAMI_STATS_TEST_DIRTY
            , -1
#endif
        );
        buffers.variance[g] = output.variance[g].data();
    }
 
    group_variance(row, mat, group, num_groups, buffers, opt);
    return output;
}
 
}
 
#endif