Three defects in the per-frame scaling of sparse (small-molecule, weak) rotation sweeps: 1. The fulls' per-frame scale pooled sparse frames by their RAW full count, but in a high-symmetry group with many systematic absences most usable counts stayed under the minimum, so most frames were never fitted and kept corr = 1 beside pinned, fitted frames (two gauges in one reference). The release step then read the gauge offset (a constant 134x on a cubic Ia-3d small-molecule sweep) as signal and gave each frame exp(kept_f * 4.9) - the e^-5 errors on a quarter of the frames, R1 0.62. A fixed box window also cannot follow a 100x absorption ramp over a few degrees, and frames under the credible floor, exempt from the window, ran away to 1e-7. Now each round fits every frame on its own fulls (no pooling, no minimum), and the scale is a penalised second-difference smoother of log G (Whittaker/Eilers), each frame at the information of its fit, lambda by cross-validation over blocks one rocking curve wide (interleaved single frames leak through shared rocking curves and chose to follow every frame). After convergence the existing ShrinkToRestrained hands back the per-frame deviation its neighbour shares. Pooling and the box window are gone from the fulls loop; the partials loop is unchanged. 2. With partial scaling off (< 50 rocking events per frame) the partials kept the integration-time corr: no incident-flux correction and not the partiality of the ingest-smoothed geometry, because only the partial scaling loop rewrote corr. They now get corr = prescaling_corr / partiality at G = 1 (host, and a device kernel). 3. The flux meter (per-frame mean background) jumped 30x between neighbouring frames of a sparse sweep - on a few reflections it measures which reflections the frame holds. It is read through the same smoother at the precision of each frame's mean. SHELXL R1(>4sig) against the published structures, rc174-cand -> this, on the in-house small-molecule sweeps: cubic Ia-3d 0.615 -> 0.119 (XDS 0.088); four organic sweeps (monoclinic / orthorhombic) 0.0515 -> 0.0459, 0.0451 -> 0.0396, 0.0747 -> 0.0709, 0.0452 -> 0.0413; ISa up to 11.6 -> 31. Raw flux instead of smoothed costs 0.002-0.003 R1 on the first two. A weak, decaying protein sweep on the fulls-only path: ISa 6.7 -> 27.1. CPU and GPU paths agree. Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01K5K8jvPPbmCrbqnWkddTuB
137 lines
6.3 KiB
C++
137 lines
6.3 KiB
C++
// SPDX-FileCopyrightText: 2026 Filip Leonarski, Paul Scherrer Institute <filip.leonarski@psi.ch>
|
|
// SPDX-License-Identifier: GPL-3.0-only
|
|
|
|
#include <cmath>
|
|
#include <catch2/catch_all.hpp>
|
|
|
|
#include "../rugnux/Rugnux.h"
|
|
#include "../image_analysis/scale_merge/RotationScaleMerge.h"
|
|
|
|
namespace {
|
|
// A synthetic sweep whose stage turned `true_scale` times the stored angles. Scored at a scale k,
|
|
// the validation spots stay on the lattice as long as the angles track the rotation, and the share
|
|
// that does falls off with the relative rate error; a wrong spindle angle keeps half a percent.
|
|
struct SyntheticSweep {
|
|
double true_scale;
|
|
int64_t spots = 35000;
|
|
int index_calls = 0;
|
|
int refit_calls = 0;
|
|
|
|
ValidationSpotEvidence IndexAt(float k) {
|
|
++index_calls;
|
|
const double error = std::fabs(true_scale / k - 1.0);
|
|
const double on = 0.9 * std::max(0.0, 1.0 - 30.0 * error);
|
|
return ValidationSpotEvidence{spots, std::llround(on * spots), std::llround(0.005 * spots)};
|
|
}
|
|
|
|
// The post-refinement at k, relative to k. It reads only 70 % of the error that is left: it
|
|
// sees only the frames the angles at k still track.
|
|
std::optional<double> RefitAt(float k) {
|
|
++refit_calls;
|
|
return 1.0 + 0.7 * (true_scale / k - 1.0);
|
|
}
|
|
|
|
RotationScaleWalk Walk(double first_fit) {
|
|
return WalkRotationScale(first_fit, [this](float k) { return IndexAt(k); },
|
|
[this](float k) { return RefitAt(k); }, 8);
|
|
}
|
|
};
|
|
}
|
|
|
|
TEST_CASE("ValidationEvidencePrefers", "[RotationScale]") {
|
|
const ValidationSpotEvidence base{10000, 3000, 50};
|
|
// 1 % more of the spots beyond chance is under the noise of two 30 % shares over 10000 spots
|
|
// (sqrt(2 * 0.3 * 0.7 / 10000) = 0.65 %, times 3.29); 5 % is well over it.
|
|
CHECK_FALSE(ValidationEvidencePrefers(base, {10000, 3100, 50}));
|
|
CHECK(ValidationEvidencePrefers(base, {10000, 3500, 50}));
|
|
// A candidate is judged against its own null: more spots on the lattice bought by a null that
|
|
// rose just as much is no gain.
|
|
CHECK_FALSE(ValidationEvidencePrefers(base, {10000, 3500, 550}));
|
|
// Never against itself, and nothing that scored nothing wins.
|
|
CHECK_FALSE(ValidationEvidencePrefers(base, base));
|
|
CHECK_FALSE(ValidationEvidencePrefers(base, {}));
|
|
CHECK(ValidationEvidencePrefers({}, base));
|
|
}
|
|
|
|
TEST_CASE("WalkRotationScale_ReachesTheFixedPoint", "[RotationScale]") {
|
|
// A stage 3 % slow. The first fit reads 70 % of that; each refit at the adopted scale reads 70 %
|
|
// of what is left, and the walk goes on as long as the validation frames prefer the new scale.
|
|
SyntheticSweep sweep{0.97};
|
|
const auto walk = sweep.Walk(sweep.RefitAt(1.0f).value());
|
|
CHECK(walk.scale == Catch::Approx(0.97).margin(0.001));
|
|
CHECK(walk.scale != 1.0f);
|
|
CHECK(walk.evidence.on_lattice > sweep.IndexAt(1.0f).on_lattice);
|
|
CHECK(sweep.refit_calls > 2);
|
|
CHECK_FALSE(walk.trail.empty());
|
|
}
|
|
|
|
TEST_CASE("WalkRotationScale_StoredAnglesStand", "[RotationScale]") {
|
|
SECTION("A healthy stage: a fit off by noise scores no better than the stored angles") {
|
|
SyntheticSweep sweep{1.0};
|
|
const auto walk = sweep.Walk(1.0002);
|
|
CHECK(walk.scale == 1.0f);
|
|
CHECK(sweep.index_calls == 2); // the stored angles and the fit, nothing more
|
|
CHECK(sweep.refit_calls == 0);
|
|
}
|
|
SECTION("A real but small error the spots cannot resolve beyond their noise") {
|
|
SyntheticSweep sweep{0.999};
|
|
sweep.spots = 400;
|
|
const auto walk = sweep.Walk(0.9993);
|
|
CHECK(walk.scale == 1.0f);
|
|
}
|
|
SECTION("A fit that tracks something other than the rotation scores worse, and is refused") {
|
|
SyntheticSweep sweep{1.0};
|
|
const auto walk = sweep.Walk(0.98);
|
|
CHECK(walk.scale == 1.0f);
|
|
CHECK(sweep.refit_calls == 0);
|
|
}
|
|
SECTION("A fit of exactly one asks for no probe at all") {
|
|
SyntheticSweep sweep{1.0};
|
|
const auto walk = sweep.Walk(1.0);
|
|
CHECK(walk.scale == 1.0f);
|
|
CHECK(walk.trail.empty());
|
|
CHECK(sweep.index_calls == 0);
|
|
}
|
|
}
|
|
|
|
TEST_CASE("SmoothLogScale_FollowsInformationBridgesGaps", "[RotationScale]") {
|
|
const int n = 60;
|
|
// A ramp is no curvature, so any amount of smoothing keeps it exactly.
|
|
std::vector<double> ramp(n), J(n, 1.0);
|
|
for (int f = 0; f < n; ++f) ramp[f] = -0.1 * f;
|
|
auto x = RotationScaleMerge::SmoothLogScale(ramp, J, 1e6);
|
|
for (int f = 0; f < n; ++f) CHECK(x[f] == Catch::Approx(ramp[f]).margin(1e-6));
|
|
// A stretch with no information is bridged by the straight line through its neighbours.
|
|
std::vector<double> Jgap(J);
|
|
for (int f = 20; f < 40; ++f) Jgap[f] = 0.0;
|
|
x = RotationScaleMerge::SmoothLogScale(ramp, Jgap, 1.0);
|
|
CHECK(x[30] == Catch::Approx(-3.0).margin(1e-6));
|
|
// A frame with far more information than its neighbours keeps its own value.
|
|
std::vector<double> y(n, 0.0), Jone(n, 1.0);
|
|
y[30] = 1.0; Jone[30] = 1e6;
|
|
x = RotationScaleMerge::SmoothLogScale(y, Jone, 10.0);
|
|
CHECK(x[30] == Catch::Approx(1.0).margin(1e-3));
|
|
// Fewer than two frames with information: nothing to smooth against.
|
|
std::vector<double> Jsingle(n, 0.0);
|
|
Jsingle[5] = 1.0;
|
|
CHECK(RotationScaleMerge::SmoothLogScale(y, Jsingle, 1.0) == y);
|
|
}
|
|
|
|
TEST_CASE("ChooseLogScaleSmoothing_SmoothsNoiseFollowsSignal", "[RotationScale]") {
|
|
const int n = 400;
|
|
std::vector<double> J(n, 1.0), noisy(n), step(n);
|
|
// Deterministic noise about a flat scale: the chosen curve is close to flat.
|
|
for (int f = 0; f < n; ++f) noisy[f] = 0.3 * std::sin(12.9898 * f) * std::cos(78.233 * f);
|
|
const double l_noise = RotationScaleMerge::ChooseLogScaleSmoothing(noisy, J, 1);
|
|
const auto flat = RotationScaleMerge::SmoothLogScale(noisy, J, l_noise);
|
|
double rms = 0.0;
|
|
for (double v : flat) rms += v * v;
|
|
CHECK(std::sqrt(rms / n) < 0.05);
|
|
// A precise slow wave is followed.
|
|
for (int f = 0; f < n; ++f) step[f] = 2.0 * std::sin(f / 30.0);
|
|
const double l_wave = RotationScaleMerge::ChooseLogScaleSmoothing(step, J, 1);
|
|
const auto wave = RotationScaleMerge::SmoothLogScale(step, J, l_wave);
|
|
CHECK(wave[47] == Catch::Approx(step[47]).margin(0.01));
|
|
CHECK(l_wave < l_noise);
|
|
}
|