Skip to content

Add metric parameter to silhouette computation #336

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
sbaldu wants to merge 1 commit into
base: main
Choose a base branch
from
+32 −32
Open

Add metric parameter to silhouette computation #336

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
50 changes: 22 additions & 28 deletions include/CLUEstering/utils/detail/scores.hpp
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,6 +1,7 @@

#pragma once

#include "CLUEstering/core/DistanceMetrics.hpp"
#include "CLUEstering/data_structures/PointsHost.hpp"
#include "CLUEstering/data_structures/AssociationMap.hpp"
#include <algorithm>
Expand All @@ -20,32 +21,24 @@ namespace clue {
template <std::size_t Ndim>
using Point = typename clue::PointsHost<Ndim>::Point;

template <std::size_t Ndim>
inline auto distance(const Point<Ndim>& lhs, const Point<Ndim>& rhs) {
auto dist = 0.f;
for (auto dim = 0u; dim < Ndim; ++dim) {
dist += (lhs[dim] - rhs[dim]) * (lhs[dim] - rhs[dim]);
}
return std::sqrt(dist);
}

template <std::size_t Ndim>
template <std::size_t Ndim,
concepts::distance_metric<Ndim> DistanceMetric = clue::EuclideanMetric<Ndim>>
inline auto silhouette(const clue::host_associator& clusters,
const clue::PointsHost<Ndim>& points,
int point) {
int point,
const DistanceMetric& metric = clue::EuclideanMetric<Ndim>{}) {
auto a = 0.f;
std::vector<float> b_values;
b_values.reserve(clusters.size() - 1);

a +=
std::accumulate(clusters.lower_bound(points[point].cluster_index()),
clusters.upper_bound(points[point].cluster_index()),
0.f,
[&](float acc, int other_point) {
if (other_point == point)
return acc;
return acc + detail::distance<Ndim>(points[point], points[other_point]);
});
a += std::accumulate(clusters.lower_bound(points[point].cluster_index()),
clusters.upper_bound(points[point].cluster_index()),
0.f,
[&](float acc, int other_point) {
if (other_point == point)
return acc;
return acc + metric(points[point], points[other_point]);
});
a /= static_cast<float>(clusters.count(points[point].cluster_index()) - 1);
for (auto cluster_idx = 0; cluster_idx < static_cast<int32_t>(clusters.size());
++cluster_idx) {
Expand All @@ -56,8 +49,7 @@ namespace clue {
clusters.upper_bound(cluster_idx),
0.f,
[&](float acc, int other_point) {
return acc +
detail::distance<Ndim>(points[point], points[other_point]);
return acc + metric(points[point], points[other_point]);
});
b /= static_cast<float>(clusters.count(cluster_idx));
b_values.push_back(b);
Expand All @@ -72,23 +64,25 @@ namespace clue {

} // namespace detail

template <std::size_t Ndim>
inline auto silhouette(const clue::PointsHost<Ndim>& points, int point) {
template <std::size_t Ndim, concepts::distance_metric<Ndim> DistanceMetric>
inline auto silhouette(const clue::PointsHost<Ndim>& points,
int point,
const DistanceMetric& metric) {
const auto clusters = clue::get_clusters(points);

return detail::silhouette<Ndim>(clusters, points, point);
return detail::silhouette<Ndim>(clusters, points, point, metric);
}

template <std::size_t Ndim>
inline auto silhouette(const clue::PointsHost<Ndim>& points) {
template <std::size_t Ndim, concepts::distance_metric<Ndim> DistanceMetric>
inline auto silhouette(const clue::PointsHost<Ndim>& points, const DistanceMetric& metric) {
const auto clusters = clue::get_clusters(points);
std::vector<float> scores;
auto valid_point = [&](int point) -> bool { return points[point].cluster_index() != -1; };
auto valid_cluster = [&](int point) -> bool {
return clusters.count(points[point].cluster_index()) >= 2;
};
auto compute_silhouette = [&](std::size_t point) -> float {
return detail::silhouette(clusters, points, point);
return detail::silhouette(clusters, points, point, metric);
};
std::ranges::copy(std::views::iota(0) | std::views::take(points.size()) |
std::views::filter(valid_point) | std::views::filter(valid_cluster) |
Expand Down
14 changes: 10 additions & 4 deletions include/CLUEstering/utils/scores.hpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -4,6 +4,7 @@

#pragma once

#include "CLUEstering/core/DistanceMetrics.hpp"
#include "CLUEstering/data_structures/PointsHost.hpp"

namespace clue {
Expand All @@ -15,17 +16,22 @@ namespace clue {
/// @param point The index of the point for which to compute the silhouette score
/// @return The silhouette score of the specified point
/// @note This function currently only works for points with non-periodic coordinates.
template <std::size_t Ndim>
auto silhouette(const clue::PointsHost<Ndim>& points, std::size_t point);
template <std::size_t Ndim,
concepts::distance_metric<Ndim> DistanceMetric = clue::EuclideanMetric<Ndim>>
auto silhouette(const clue::PointsHost<Ndim>& points,
std::size_t point,
const DistanceMetric& metric = clue::EuclideanMetric<Ndim>{});

/// @brief Compute the average silhouette score for the entire dataset.
///
/// @tparam Ndim The number of dimensions of the points
/// @param points The dataset containing the points
/// @return The average silhouette score of the dataset
/// @note This function currently only works for points with non-periodic coordinates.
template <std::size_t Ndim>
auto silhouette(const clue::PointsHost<Ndim>& points);
template <std::size_t Ndim,
concepts::distance_metric<Ndim> DistanceMetric = clue::EuclideanMetric<Ndim>>
auto silhouette(const clue::PointsHost<Ndim>& points,
const DistanceMetric& metric = clue::EuclideanMetric<Ndim>{});

} // namespace clue

Expand Down
Loading