lars
25718f175e
Removes unused imports and an ambiguous variable name, narrows Optional types before use so ty's flow analysis is satisfied, swaps sum() over polars expressions for pl.sum_horizontal to avoid the Literal[0] fallback type, and converts numpy bin edges to plain lists before passing to matplotlib's hist (whose stub only accepts Sequence[float]). Also applies ruff format across the repo, which had drifted out of sync with the formatter. Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
73 lines
2.3 KiB
Python
73 lines
2.3 KiB
Python
"""Truth-only histogram of deposited photon (pdg=22) energy in eV, grouped by
|
|
the Geant4 physics process that ended the step. Step-type histograms, one per
|
|
process, in both linear and log energy space.
|
|
|
|
Data is the raw miniCaloSim steps parquet (truth), loaded lazily with polars —
|
|
only the photon rows and the (process, edep) columns are materialized.
|
|
"""
|
|
|
|
from pathlib import Path
|
|
|
|
import matplotlib.pyplot as plt
|
|
import numpy as np
|
|
import polars as pl
|
|
|
|
FILE = "/home/lars/Programming/minicalo-data-exploration/pbwo4_10000events_hits.parquet"
|
|
OUT = Path("/home/lars/knowledge-base/meta/attachments")
|
|
|
|
MEV_TO_EV = 1e6
|
|
|
|
# Lazy load: keep only photon steps and the two columns we need.
|
|
df = (
|
|
pl.scan_parquet(FILE)
|
|
.filter(pl.col("pdg") == 22)
|
|
.select(
|
|
pl.col("process"),
|
|
(pl.col("edep") * MEV_TO_EV).alias("edep_ev"),
|
|
)
|
|
.collect()
|
|
)
|
|
print("n photon rows:", df.height)
|
|
|
|
# Process order by abundance, so the legend is stable and the busiest on top.
|
|
processes = (
|
|
df.group_by("process")
|
|
.len()
|
|
.sort("len", descending=True)
|
|
.get_column("process")
|
|
.to_list()
|
|
)
|
|
series = {
|
|
p: df.filter(pl.col("process") == p).get_column("edep_ev").to_numpy()
|
|
for p in processes
|
|
}
|
|
|
|
all_edep = df.get_column("edep_ev").to_numpy()
|
|
lin_bins = np.linspace(0, np.quantile(all_edep, 0.999), 80)
|
|
pos = all_edep[all_edep > 0]
|
|
log_bins = np.geomspace(max(pos.min(), 1e-3), pos.max(), 80)
|
|
|
|
|
|
def plot(bins, xscale: str, fname: str) -> None:
|
|
fig, ax = plt.subplots(figsize=(7, 4.5))
|
|
lo, hi = bins[0], bins[-1]
|
|
for p in processes:
|
|
v = series[p]
|
|
# Skip processes with nothing inside the bin range (e.g. all-zero edep
|
|
# processes on the log axis), which would add phantom legend entries.
|
|
if not np.any((v >= lo) & (v <= hi)):
|
|
continue
|
|
ax.hist(v, bins=bins, histtype="step", density=True, label=f"{p} (n={v.size})")
|
|
ax.set_xscale(xscale)
|
|
ax.set_yscale("log")
|
|
ax.set_xlabel("deposited energy [eV] (photons, pdg=22)")
|
|
ax.set_ylabel("density")
|
|
ax.legend(fontsize=8, title="process")
|
|
fig.tight_layout()
|
|
fig.savefig(OUT / fname, dpi=150, bbox_inches="tight")
|
|
print("saved", fname)
|
|
|
|
|
|
plot(lin_bins, "linear", "giant-photon-edep-by-process-ev-lin.png")
|
|
plot(log_bins, "log", "giant-photon-edep-by-process-ev-log.png")
|