chore: release v0.3.25

Reviewed-on: #102

.bumpversion.toml

@@ -1,5 +1,5 @@
 [tool.bumpversion]
-current_version = "0.3.24"
+current_version = "0.3.25"
 parse = "(?P<major>\\d+)\\.(?P<minor>\\d+)\\.(?P<patch>\\d+)"
 serialize = ["{major}.{minor}.{patch}"]
 search = "{current_version}"

CHANGELOG.md

@@ -1,5 +1,11 @@
 # Changelog
 
+## [0.3.25] - 2026-09-09
+
+### Changed
+
+- Fix(analysis): keep pre_E alive through prediction range subsampling
+
 ## [0.3.24] - 2026-09-09
 
 ### Changed

README.md

@@ -10,8 +10,8 @@ calorimeter showers.
 
 [![python](https://img.shields.io/badge/python-3.12%2B-3776AB?logo=python&logoColor=white)](pyproject.toml)
 [![torch](https://img.shields.io/badge/torch-2.3.x-EE4C2C?logo=pytorch&logoColor=white)](pyproject.toml)
-[![version](https://img.shields.io/badge/version-0.3.24-informational)](CHANGELOG.md)
+[![version](https://img.shields.io/badge/version-0.3.25-informational)](CHANGELOG.md)
-[![tests](https://img.shields.io/badge/tests-1176%20passing-brightgreen)](tests/)
+[![tests](https://img.shields.io/badge/tests-1177%20passing-brightgreen)](tests/)
 [![CI](https://git.larsbogner.de/lars/giant/actions/workflows/ci.yml/badge.svg?branch=master)](https://git.larsbogner.de/lars/giant/actions)
 [![license](https://img.shields.io/badge/license-unlicensed-lightgrey)](#license)
 

giant/analysis/context.py

@@ -85,7 +85,11 @@ _LO_Q, _HI_Q = 0.001, 0.999
 
 
 def _row_subsample(lf: pl.LazyFrame, sample_rows: int, seed: int) -> pl.LazyFrame:
-    """Hash-subsample ~``sample_rows`` rows (for range estimation only)."""
+    """Hash-subsample ~``sample_rows`` rows (for range estimation only).
+
+    ``lf`` must still carry ``pre_E`` (the hash key) — subsample before
+    projecting away columns, not after.
+    """
     n_total = lf.select(pl.len()).collect(engine="streaming").item()
     if n_total <= sample_rows:
         return lf
@@ -195,20 +199,29 @@ def build_context(
     if predictions:
         sides = {ps.name: open_prediction(ps.source) for ps in predictions}
         present_vars = sorted(set().union(*(paired_vars_for_coord(s.coord) for s in sides.values())))
-        for var in present_vars:
+        true_samples: dict[str, list[np.ndarray]] = {v: [] for v in present_vars}
-            true_samples, pred_samples, residual_samples = [], [], []
+        pred_samples: dict[str, list[np.ndarray]] = {v: [] for v in present_vars}
+        residual_samples: dict[str, list[np.ndarray]] = {v: [] for v in present_vars}
+
+        # One subsample+collect per side (not per variable) — `s.paired`
+        # still carries `pre_E`, which `_row_subsample`'s hash needs, so
+        # subsample before projecting down to the pred/true columns.
         for s in sides.values():
-                if var not in paired_vars_for_coord(s.coord):
+            vars_here = paired_vars_for_coord(s.coord)
-                    continue
+            cols = [f"pred_{v}" for v in vars_here] + ([f"true_{v}" for v in vars_here] if s.has_truth else [])
-                cols = [f"pred_{var}"] + ([f"true_{var}"] if s.has_truth else [])
+            sample = _row_subsample(s.paired, sample_rows, seed).select(cols).collect(engine="streaming")
-                sample = _row_subsample(s.paired.select(cols), sample_rows, seed).collect(engine="streaming")
+            for var in vars_here:
-                pred_samples.append(sample[f"pred_{var}"].to_numpy())
+                p = sample[f"pred_{var}"].to_numpy()
+                pred_samples[var].append(p)
                 if s.has_truth:
-                    true_samples.append(sample[f"true_{var}"].to_numpy())
+                    t = sample[f"true_{var}"].to_numpy()
-                    residual_samples.append(sample[f"pred_{var}"].to_numpy() - sample[f"true_{var}"].to_numpy())
+                    true_samples[var].append(t)
-            pred_var_ranges[var] = _combined_quantiles([*true_samples, *pred_samples], _LO_Q, _HI_Q)
+                    residual_samples[var].append(p - t)
-            if residual_samples:
+
-                pred_residual_ranges[var] = _combined_quantiles(residual_samples, _LO_Q, _HI_Q)
+        for var in present_vars:
+            pred_var_ranges[var] = _combined_quantiles([*true_samples[var], *pred_samples[var]], _LO_Q, _HI_Q)
+            if residual_samples[var]:
+                pred_residual_ranges[var] = _combined_quantiles(residual_samples[var], _LO_Q, _HI_Q)
 
         sec_pdg_counts: dict[int, int] = {}
         for s in sides.values():

pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "giant"
-version = "0.3.24"
+version = "0.3.25"
 description = "Geant4 step-function surrogate via conditional flow matching"
 readme = "README.md"
 requires-python = ">=3.12"

tests/test_analysis_prediction.py

@@ -193,6 +193,28 @@ def test_build_context_resolves_prediction_ranges():
     assert ctx.pred_top_sec_pdgs  # secondaries present in the fixture
 
 
+def test_build_context_resolves_prediction_ranges_when_subsampled():
+    """Regression test: `sample_rows` smaller than the prediction row count
+    must still work — `_row_subsample`'s hash key (`pre_E`) has to survive
+    into the prediction branch's subsample call, not be projected away first
+    (see giant/analysis/context.py's predictions loop)."""
+    ctx = build_context(
+        [RolloutSpec("rollout", _rollout_frame())],
+        _reference_frame(),
+        predictions=[PredictionSpec("pred", _global_prediction_frame())],
+        n_energy_bins=2,
+        n_marginal_bins=10,
+        top_k_pdg=3,
+        sample_rows=2,  # < the 3-row prediction fixture: forces the hash-filter branch
+        seed=0,
+    )
+    for var in PAIRED_SCALARS + ("cos_scatter", "cos_travel"):
+        lo, hi = ctx.pred_var_ranges[var]
+        assert np.isfinite(lo) and np.isfinite(hi) and lo < hi
+        lo, hi = ctx.pred_residual_ranges[var]
+        assert np.isfinite(lo) and np.isfinite(hi) and lo < hi
+
+
 def test_prediction_specs_compute_valid_reduced():
     ctx = _ctx_with_predictions()
     bundle = Bundle.open(

uv.lock

@@ -825,7 +825,7 @@ wheels = [
 
 [[package]]
 name = "giant"
-version = "0.3.24"
+version = "0.3.25"
 source = { editable = "." }
 dependencies = [
     { name = "numpy" },