kemalandClaude Opus 5.5
314fdc40d1
- signal/normalization/numerics.py: vendor percentile, trimmean, MAD sigma (old/new), bisquare robust fits, float32/float64 typing and sequential sums reproduced exactly (ported from gtc2vcf, MIT) - signal/normalization/fit.py: outlier removal, offset, rotation, shear, scale, nn12/rr12, single-channel model for small Infinium I bins, exact and binned nearest-neighbour sweeps; vendor quirks marked QUIRK - signal/normalization/apply.py: affine transform and theta/R - pipeline/normalize.py + CLI `simurg normalize` - oracle GTCs rebuilt with -ffp-contract=off (aarch64 gcc fuses a*b+c by default, shifting the last bits); the old FMA oracle differed by <=4 ULP Result: transforms bit-identical to the oracle for all 36 GSA samples x 48 bins, for both normalization versions (3456/3456 bins, 0 ULP). Co-Authored-By: Claude Opus 5.5 <[email protected]> Claude-Session: https://claude.ai/code/session_01814GKVzZVL3FuF3DeiZXhv
46 lines
1.8 KiB
Python
46 lines
1.8 KiB
Python
"""Phase P3 acceptance on P0 data: normalization transforms fitted from raw intensities are bit-identical to the
|
|
transforms stored in oracle GTCs (gtc2vcf built without FMA), for normalization 1.2.0 and 1.1.2.
|
|
The same check against vendor GTCs runs in scripts/validate_p1_large.py --p3.
|
|
"""
|
|
|
|
from __future__ import annotations
|
|
|
|
import numpy as np
|
|
import pytest
|
|
from tests.conftest import GSA_BPM, ORACLE_GTCS, ORACLE_GTCS_GT2, need
|
|
|
|
from simurg.formats.bpm import read_bpm
|
|
from simurg.formats.gtc import read_gtc
|
|
from simurg.signal.normalization.fit import fit_transforms
|
|
|
|
pytestmark = pytest.mark.data
|
|
|
|
FIELDS = ("offset_x", "offset_y", "scale_x", "scale_y", "shear", "theta")
|
|
|
|
|
|
def as_bits(xf) -> np.ndarray: # type: ignore[no-untyped-def,type-arg]
|
|
v = [getattr(xf, f) for f in FIELDS] + [xf.nn12, xf.rr12, xf.taa, xf.tbb]
|
|
return np.array(v, dtype=np.float32).view(np.int32)
|
|
|
|
|
|
def ref_bits(rec) -> np.ndarray: # type: ignore[no-untyped-def,type-arg]
|
|
v = [rec[f] for f in FIELDS] + list(rec["reserved"][2:6])
|
|
return np.array(v, dtype=np.float32).view(np.int32)
|
|
|
|
|
|
@pytest.mark.parametrize(
|
|
("folder", "version"), [(ORACLE_GTCS, "1.2.0"), (ORACLE_GTCS_GT2, "1.1.2")], ids=["1.2.0", "1.1.2"]
|
|
)
|
|
def test_transforms_bit_identical(folder, version) -> None: # type: ignore[no-untyped-def]
|
|
need(GSA_BPM, folder)
|
|
m = read_bpm(GSA_BPM)
|
|
bins = m.norm_bin_ids()
|
|
gtcs = sorted(folder.glob("*.gtc"))
|
|
assert len(gtcs) >= 18
|
|
for g in gtcs:
|
|
ref = read_gtc(g)
|
|
mine = fit_transforms(ref.raw_x, ref.raw_y, bins, version)
|
|
assert len(mine) == len(ref.normalization_transforms)
|
|
for k, (a, b) in enumerate(zip(mine, ref.normalization_transforms, strict=True)):
|
|
assert np.array_equal(as_bits(a), ref_bits(b)), f"{g.name} bin {k}"
|