Files
Jungfraujoch/common/ScanResultGenerator.cpp
T
leonarski_fandClaude Opus 5 0f00b76a9a image analysis: the ice score takes the pipeline's own band width, and the ice quantities are named for what kind of number they are
Two things, both about telling one ice quantity from another.

The ice score's spot channel had its own band half-width of 0.02 A^-1 while the spot finder marks
ice rings at 0.03 (ice_ring_width_Q_recipA). The 0.02 was justified by a 5 pp specificity gain
measured on the PYTHON PROTOTYPE, which used a fitted beam centre and a mask-derived coverage table;
the shipped port, which takes the geometry's centre and the azimuthal profile's own live pixel
count, does not reproduce it. Measured over the corpus by truth class rather than by directory
label, at 0.02 vs 0.03 on the combined score: ice loops 62.13/62.19%, _icy protein 89.03/89.79%,
_clean protein 16.51/16.31%, water 17.19/20.03%. The widths are indistinguishable except on water,
where one of the four loops is independently known to carry a full hexagonal pattern. So the width
is now a parameter and the pipeline's own value is passed in - one band width, not two. The 0.012
tolerance in the radial channel is NOT a second band width, and is renamed CENTRE_SMEAR_Q to say so:
it is how far either side the channel looks for the bin a mis-set beam centre moved the ring to.

The rest is naming. Three kinds of number were all called score, or built from things called count,
and a reader could not tell from the name whether 1 meant "none" or "certain" - which are opposite.
The convention, now stated in docs/CPU_DATA_ANALYSIS.md: *_score is bounded [0,1] and 1 is
certainty, *_ratio is unbounded and 1 is nothing, *_count is a count. The C++ identifiers for the
ice ring ratio follow it (ice_ring_score -> ice_ring_ratio, GetIceRingScore -> GetIceRingRatio,
PlotType::IceRingScore -> IceRingRatio), and the local in the scaling gate that shadowed the new
ice_score while meaning the ring ratio is renamed with them.

Nothing outside the source moved: the CBOR keys ice_ring_score and ice_ring_score_mean, the datasets
/entry/MX/iceRingScore and iceRingScoreMean, the ice_ring_score plot type and the --ice-min-score
flag are all unchanged, and were checked to be after the rename. Renaming those changes stored
files, the stream format, the REST API and a CLI flag, and is a separate decision.

Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01EFEJG6WBQv8th4UJFNe53N
2026-09-08 07:19:03 +02:00

166 lines
7.6 KiB
C++

// SPDX-FileCopyrightText: 2025 Filip Leonarski, Paul Scherrer Institute <filip.leonarski@psi.ch>
// SPDX-License-Identifier: GPL-3.0-only
#include <algorithm>
#include <cmath>
#include "ScanResultGenerator.h"
namespace {
template<class T>
T value_or_zero(const std::optional<T>& v) {
return v.value_or(static_cast<T>(0));
}
}
ScanResultGenerator::ScanResultGenerator(const DiffractionExperiment &experiment) {
grid_scan = experiment.GetGridScan();
goniometer_axis = experiment.GetGoniometer();
if (grid_scan)
v.resize(grid_scan->GetNElem());
else
v.resize(experiment.GetImageNum());
file_prefix = experiment.GetFilePrefix();
}
void ScanResultGenerator::Add(const DataMessage &message) {
std::unique_lock ul(m);
int64_t image_number = message.number;
if (grid_scan)
image_number = grid_scan->Rearrange(image_number);
if (image_number >= 0 && static_cast<size_t>(image_number) < v.size()) {
if (grid_scan) {
v[image_number].x = grid_scan->GetElementPosX_step(message.number);
v[image_number].y = grid_scan->GetElementPosY_step(message.number);
} else if (goniometer_axis) {
v[image_number].angle_deg = goniometer_axis->GetAngle_deg(message.number);
}
v[image_number].number = message.number;
v[image_number].pixel_sum = message.pixel_sum;
v[image_number].collection_efficiency = message.image_collection_efficiency.value_or(1.0);
v[image_number].bkg = message.bkg_estimate;
v[image_number].spindle_blind = message.spindle_blind_fraction;
v[image_number].spot_count = message.spot_count;
v[image_number].indexing_solution = message.indexing_result;
v[image_number].indexed_lattice_count = message.indexing_lattice_count;
v[image_number].profile_radius = message.profile_radius;
v[image_number].mosaicity = message.mosaicity_deg;
v[image_number].b_factor = message.b_factor;
v[image_number].uc = message.indexing_unit_cell;
v[image_number].xfel_pulse_id = message.xfel_pulse_id;
v[image_number].err_pixels = message.error_pixel_count;
v[image_number].min_viable_pixel = message.min_viable_pixel_value;
v[image_number].max_viable_pixel = message.max_viable_pixel_value;
v[image_number].sat_pixels = message.saturated_pixel_count;
v[image_number].spot_count_ice = message.spot_count_ice_rings;
v[image_number].spot_count_ice_control = message.spot_count_ice_control;
v[image_number].spot_count_low_res = message.spot_count_low_res;
v[image_number].spot_count_indexed = message.spot_count_indexed;
v[image_number].res = message.resolution_estimate;
v[image_number].integrated_reflections = message.integrated_reflections;
v[image_number].image_scale_factor = message.image_scale_factor;
v[image_number].image_scale_cc = message.image_scale_cc;
v[image_number].ice_ring_ratio = message.ice_ring_ratio;
v[image_number].protein_score = message.protein_score;
v[image_number].ice_score = message.ice_score;
if (message.lattice_type)
v[image_number].niggli_class = message.lattice_type->niggli_class;
}
}
ScanResult ScanResultGenerator::GetResult() const {
std::unique_lock ul(m);
ScanResult ret;
ret.file_prefix = file_prefix;
for (const auto &e: v) {
if (e.number >= 0)
ret.images.push_back(e);
}
return ret;
}
void ScanResultGenerator::FillEndMessage(EndMessage &message) const {
std::unique_lock ul(m);
size_t n = 0;
for (const auto &e: v) {
if (e.number >= 0)
n = std::max(n, static_cast<size_t>(e.number) + 1);
}
if (n == 0)
return;
// The vectors the loop below fills with value_or(NAN) are sized with NAN, not with the
// value-initialised zero: an image that never reached the loop at all - dropped, never
// arrived, numbered outside the run - has no measurement, and zero is a measurement. A
// blind fraction of 0.0 reads as "this frame lost nothing", a mosaicity of 0.0 as a
// perfect crystal, and a resolution estimate of 0.0 as nothing at all. The counts keep
// their zeros, because a count of zero is a thing that can be true.
message.data_collection_efficiency.resize(n);
message.spot_count.resize(n);
message.spot_count_ice_ring.resize(n);
message.spot_count_ice_control.resize(n, NAN);
message.spot_count_low_res.resize(n);
message.spot_count_indexed.resize(n);
message.image_indexed.resize(n);
message.v_bkg_estimate.resize(n, NAN);
message.v_spindle_blind_fraction.resize(n, NAN);
message.profile_radius.resize(n, NAN);
message.mosaicity.resize(n, NAN);
message.bFactor.resize(n, NAN);
message.resolution_estimate.resize(n, NAN);
message.min_viable_pixel_value.resize(n);
message.max_viable_pixel_value.resize(n);
message.saturated_pixel_count.resize(n);
message.error_pixel_count.resize(n);
message.image_scale_factor.resize(n, NAN);
message.image_scale_cc.resize(n, NAN);
message.ice_ring_ratio.resize(n, NAN);
message.v_protein_score.resize(n, NAN);
message.v_ice_score.resize(n, NAN);
message.integrated_reflections.resize(n);
message.niggli_class.resize(n);
message.pixel_sum.resize(n);
message.indexed_lattice_count.resize(n);
for (const auto &e: v) {
if (e.number < 0)
continue;
const auto number = static_cast<size_t>(e.number);
if (number >= n)
continue;
message.data_collection_efficiency[number] = e.collection_efficiency;
message.spot_count[number] = static_cast<int32_t>(value_or_zero(e.spot_count));
message.spot_count_ice_ring[number] = static_cast<int32_t>(value_or_zero(e.spot_count_ice));
message.spot_count_ice_control[number] = e.spot_count_ice_control.value_or(NAN);
message.spot_count_low_res[number] = static_cast<int32_t>(value_or_zero(e.spot_count_low_res));
message.spot_count_indexed[number] = static_cast<int32_t>(value_or_zero(e.spot_count_indexed));
message.image_indexed[number] = static_cast<uint8_t>(e.indexing_solution.value_or(0));
message.v_bkg_estimate[number] = e.bkg.value_or(NAN);
message.v_spindle_blind_fraction[number] = e.spindle_blind.value_or(NAN);
message.profile_radius[number] = e.profile_radius.value_or(NAN);
message.mosaicity[number] = e.mosaicity.value_or(NAN);
message.bFactor[number] = e.b_factor.value_or(NAN);
message.resolution_estimate[number] = e.res.value_or(NAN);
message.min_viable_pixel_value[number] = value_or_zero(e.min_viable_pixel);
message.max_viable_pixel_value[number] = value_or_zero(e.max_viable_pixel);
message.saturated_pixel_count[number] = static_cast<int32_t>(value_or_zero(e.sat_pixels));
message.error_pixel_count[number] = static_cast<int32_t>(value_or_zero(e.err_pixels));
message.image_scale_factor[number] = e.image_scale_factor.value_or(NAN);
message.image_scale_cc[number] = e.image_scale_cc.value_or(NAN);
message.ice_ring_ratio[number] = e.ice_ring_ratio.value_or(NAN);
message.v_protein_score[number] = e.protein_score.value_or(NAN);
message.v_ice_score[number] = e.ice_score.value_or(NAN);
message.integrated_reflections[number] = static_cast<int32_t>(value_or_zero(e.integrated_reflections));
message.niggli_class[number] = static_cast<uint8_t>(value_or_zero(e.niggli_class));
message.pixel_sum[number] = value_or_zero(e.pixel_sum);
message.indexed_lattice_count[number] = static_cast<int32_t>(value_or_zero(e.indexed_lattice_count));
}
}