feat(output): physical branch spectra, universal factor, CSV-driven plotting
This commit is contained in:
+116
-111
@@ -1,14 +1,28 @@
|
||||
"""
|
||||
CSV export module — CSV export functionality for BetaSpectrumAnalyzer.
|
||||
|
||||
Column semantics (v0.4.0 onward):
|
||||
- The basic spectrum is ALWAYS core = phase_space x fermi; the Fermi function
|
||||
is a core spectrum component, never an optional correction. Higher-order
|
||||
corrections (finite size, charge distribution, screening, exchange,
|
||||
radiative) are multiplied on top of the core.
|
||||
- ``branch_{i}_spectrum`` columns carry the PHYSICAL branch spectrum
|
||||
(core x all enabled corrections), weighted by intensity and
|
||||
area-normalized so that the sum of branch columns equals total_spectrum
|
||||
(the total column itself is normalized to integrate to 1). In the legacy
|
||||
export branch columns contained only the per-branch phase-space x
|
||||
radiative product WITHOUT the Fermi function — physically wrong.
|
||||
- ``normalize_to_one`` mode: each branch column is normalized to
|
||||
integrate to 1 individually, intensity is ignored, no total column.
|
||||
"""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import pandas as pd
|
||||
from datetime import datetime, timezone
|
||||
from typing import TYPE_CHECKING, Dict
|
||||
from typing import TYPE_CHECKING, Dict, Optional
|
||||
|
||||
import numpy as np
|
||||
import pandas as pd
|
||||
|
||||
from beta_spectrum.logging_utils import get_git_short_hash
|
||||
|
||||
@@ -37,64 +51,80 @@ class CSVEmitter:
|
||||
source_type : str
|
||||
Source type (paceENSDF, json, etc.).
|
||||
csv_verbosity : str
|
||||
Verbosity level: 'full' (all components) or 'concise' (total spectrum and normalized branch components only).
|
||||
"""
|
||||
total = analyzer.total_spectrum(normalize=True)
|
||||
components = analyzer.components
|
||||
Verbosity level: 'full' (all components) or 'concise' (total
|
||||
spectrum and physical branch spectra only).
|
||||
|
||||
# Only include enabled corrections that are not basic components
|
||||
# Basic components (phase_space and fermi) are always used and should not be listed
|
||||
Raises
|
||||
------
|
||||
ValueError
|
||||
If every branch spectrum integrates to a non-positive area
|
||||
(e.g. all branch endpoints lie below the neutrino mass).
|
||||
"""
|
||||
components = analyzer.components
|
||||
config = analyzer.config
|
||||
to_one = config.normalize_to_one
|
||||
n_branches = analyzer._n_branches
|
||||
|
||||
# Physical branch spectra: core(phase_space x fermi) x corrections.
|
||||
physical = [analyzer.physical_branch_spectrum(i) for i in range(n_branches)]
|
||||
|
||||
# Only higher-order corrections are toggleable; list them enabled.
|
||||
enabled = []
|
||||
if analyzer.config.use_screening:
|
||||
if config.use_screening:
|
||||
enabled.append("screening")
|
||||
if analyzer.config.use_finite_size:
|
||||
if config.use_finite_size:
|
||||
enabled.append("finite_size")
|
||||
if analyzer.config.use_charge_dist:
|
||||
if config.use_charge_dist:
|
||||
enabled.append("charge_dist")
|
||||
if analyzer.config.use_radiative:
|
||||
if config.use_radiative:
|
||||
enabled.append("radiative")
|
||||
if analyzer.config.use_exchange:
|
||||
if config.use_exchange:
|
||||
enabled.append("exchange")
|
||||
|
||||
parent_symbol = analyzer._element_symbol(analyzer.config.Z_parent)
|
||||
daughter_symbol = analyzer._element_symbol(analyzer.config.Z_daughter)
|
||||
parent_symbol = analyzer._element_symbol(config.Z_parent)
|
||||
daughter_symbol = analyzer._element_symbol(config.Z_daughter)
|
||||
|
||||
# Get git commit hash
|
||||
git_commit = get_git_short_hash()
|
||||
|
||||
# Format source line with paceENSDF URL if applicable
|
||||
if source_type == "paceENSDF":
|
||||
source_line = "# source: paceENSDF (https://pypi.org/project/paceENSDF/)"
|
||||
else:
|
||||
source_line = f"# source: {source_type}"
|
||||
|
||||
header_lines = [
|
||||
f"# beta-spectrum v{__import__('beta_spectrum').__version__}(build.{git_commit})",
|
||||
f"# beta-spectrum v{__import__('beta_spectrum').__version__}"
|
||||
f"(build.{git_commit})",
|
||||
f"# timestamp: {datetime.now(timezone.utc).isoformat()}",
|
||||
source_line,
|
||||
f"# nuclide: {parent_symbol}{analyzer.config.A_number} -> {daughter_symbol}{analyzer.config.A_number} (Z={analyzer.config.Z_parent}->{analyzer.config.Z_daughter})",
|
||||
f"# basic_endpoint: {analyzer.config.endpoint_MeV * 1000:.1f} keV",
|
||||
f"# nuclide: {parent_symbol}{config.A_number} "
|
||||
f"-> {daughter_symbol}{config.A_number} "
|
||||
f"(Z={config.Z_parent}->{config.Z_daughter})",
|
||||
f"# basic_endpoint: {config.endpoint_MeV * 1000:.1f} keV",
|
||||
]
|
||||
|
||||
# Add neutrino mass info if non-zero
|
||||
if analyzer.config.neutrino_mass_MeV > 0:
|
||||
if config.neutrino_mass_MeV > 0:
|
||||
header_lines.append(
|
||||
f"# neutrino_mass_MeV: {analyzer.config.neutrino_mass_MeV:.6f} (non-zero neutrino mass effects included)"
|
||||
f"# neutrino_mass_MeV: {config.neutrino_mass_MeV:.6f} "
|
||||
f"(non-zero neutrino mass effects included)"
|
||||
)
|
||||
else:
|
||||
header_lines.append(
|
||||
f"# neutrino_mass_MeV: {analyzer.config.neutrino_mass_MeV:.6f}"
|
||||
)
|
||||
header_lines.append(f"# neutrino_mass_MeV: {config.neutrino_mass_MeV:.6f}")
|
||||
|
||||
header_lines.append("# core: phase_space x fermi (basic spectrum)")
|
||||
header_lines.append(f"# corrections: {', '.join(enabled)}")
|
||||
header_lines.append(f"# e_step: {analyzer.config.e_step_MeV:.4f} MeV")
|
||||
header_lines.append(f"# e_step: {config.e_step_MeV:.4f} MeV")
|
||||
header_lines.append(f"# n_points: {len(analyzer.energies_MeV)}")
|
||||
|
||||
# Add normalization mode
|
||||
if analyzer.config.normalize_to_one:
|
||||
header_lines.append("# branch normalization: to_one (ignoring intensity)")
|
||||
if to_one:
|
||||
header_lines.append(
|
||||
"# branch normalization: to_one "
|
||||
"(each branch integrates to 1, intensity ignored)"
|
||||
)
|
||||
else:
|
||||
header_lines.append("# branch normalization: intensity")
|
||||
header_lines.append(
|
||||
"# branch normalization: intensity "
|
||||
"(sum of branch columns == total_spectrum)"
|
||||
)
|
||||
|
||||
# Separate branches into active and excluded lists
|
||||
active_branches = []
|
||||
@@ -102,118 +132,93 @@ class CSVEmitter:
|
||||
|
||||
for i, branch in enumerate(analyzer._unified_branches):
|
||||
branch_endpoint_keV = branch.endpoint_MeV * 1000
|
||||
neutrino_mass_keV = analyzer.config.neutrino_mass_MeV * 1000
|
||||
neutrino_mass_keV = config.neutrino_mass_MeV * 1000
|
||||
|
||||
# Check if branch is excluded due to neutrino mass
|
||||
if branch_endpoint_keV <= neutrino_mass_keV:
|
||||
excluded_branches.append(
|
||||
f" branch_{i + 1}: E₀={branch_endpoint_keV:.1f} keV, transition={branch.transition_type}, intensity={branch.intensity:.4f} - excluded: endpoint < m_nu"
|
||||
f" branch_{i + 1}: E₀={branch_endpoint_keV:.1f} keV, "
|
||||
f"transition={branch.transition_type}, "
|
||||
f"intensity={branch.intensity:.4f} - excluded: endpoint < m_nu"
|
||||
)
|
||||
# Check if branch is excluded due to intensity cutoff
|
||||
elif branch.intensity < analyzer.config.intensity_cutoff:
|
||||
elif branch.intensity < config.intensity_cutoff:
|
||||
excluded_branches.append(
|
||||
f" branch_{i + 1}: E₀={branch_endpoint_keV:.1f} keV, transition={branch.transition_type}, intensity={branch.intensity:.4f} - excluded: intensity < cutoff"
|
||||
f" branch_{i + 1}: E₀={branch_endpoint_keV:.1f} keV, "
|
||||
f"transition={branch.transition_type}, "
|
||||
f"intensity={branch.intensity:.4f} "
|
||||
"- excluded: intensity < cutoff"
|
||||
)
|
||||
else:
|
||||
active_branches.append(
|
||||
f" branch_{i + 1}: E₀={branch_endpoint_keV:.1f} keV, transition={branch.transition_type}, intensity={branch.intensity:.4f}"
|
||||
f" branch_{i + 1}: E₀={branch_endpoint_keV:.1f} keV, "
|
||||
f"transition={branch.transition_type}, "
|
||||
f"intensity={branch.intensity:.4f}"
|
||||
)
|
||||
|
||||
# Add active branches list
|
||||
if active_branches:
|
||||
header_lines.append("# active branches:")
|
||||
for branch_info in active_branches:
|
||||
header_lines.append(f"# {branch_info}")
|
||||
header_lines.extend(f"# {b}" for b in active_branches)
|
||||
|
||||
# Add excluded branches list if there are any
|
||||
if excluded_branches:
|
||||
header_lines.append("# excluded branches:")
|
||||
for branch_info in excluded_branches:
|
||||
header_lines.append(f"# {branch_info}")
|
||||
header_lines.extend(f"# {b}" for b in excluded_branches)
|
||||
|
||||
# Create data dictionary with concise column headers
|
||||
# ----- data columns -----
|
||||
data: Dict[str, np.ndarray] = {
|
||||
"energy_MeV": analyzer.energies_MeV,
|
||||
}
|
||||
|
||||
# Only add total_spectrum if not normalizing to one
|
||||
if not analyzer.config.normalize_to_one:
|
||||
data["total_spectrum"] = total
|
||||
integral: Optional[float] = None
|
||||
if not to_one:
|
||||
total_raw = analyzer.spectrum(analyzer.W)
|
||||
integral = float(np.trapezoid(total_raw, analyzer.energies_MeV))
|
||||
if integral <= 0.0:
|
||||
raise ValueError(
|
||||
"Total spectrum integral is non-positive: every branch "
|
||||
"is degenerate (check neutrino_mass vs branch endpoints "
|
||||
"and intensity_cutoff)"
|
||||
)
|
||||
data["total_spectrum"] = total_raw / integral
|
||||
|
||||
for i in range(n_branches):
|
||||
key_i = i + 1
|
||||
if csv_verbosity == "concise":
|
||||
col_name = f"branch_{key_i}"
|
||||
else:
|
||||
col_name = f"branch_{key_i}_spectrum"
|
||||
|
||||
if to_one:
|
||||
area = float(np.trapezoid(physical[i], analyzer.energies_MeV))
|
||||
if area > 0.0:
|
||||
data[col_name] = physical[i] / area
|
||||
else:
|
||||
data[col_name] = np.zeros_like(physical[i])
|
||||
else:
|
||||
assert integral is not None
|
||||
intensity_i = analyzer._unified_branches[i].intensity
|
||||
data[col_name] = physical[i] * intensity_i / integral
|
||||
|
||||
if csv_verbosity == "full":
|
||||
# Per-branch spectra and components with concise branch naming
|
||||
for i in range(analyzer._n_branches):
|
||||
# Get branch spectrum
|
||||
branch_spectrum = analyzer._get_branch_spectrum(i)
|
||||
|
||||
if analyzer.config.normalize_to_one:
|
||||
# Normalize to 1, ignoring intensity
|
||||
sum_spectrum = np.sum(branch_spectrum)
|
||||
if sum_spectrum > 0:
|
||||
normalized_spectrum = branch_spectrum / sum_spectrum
|
||||
else:
|
||||
normalized_spectrum = branch_spectrum
|
||||
else:
|
||||
# Use original spectrum with intensity
|
||||
normalized_spectrum = (
|
||||
branch_spectrum * analyzer._unified_branches[i].intensity
|
||||
)
|
||||
|
||||
data[f"branch_{i + 1}_spectrum"] = normalized_spectrum
|
||||
|
||||
# Per-branch component columns (factorized ingredients).
|
||||
for i in range(n_branches):
|
||||
for comp_name in ["PhaseSpace", "Radiative"]:
|
||||
key = analyzer._get_component_key(i, comp_name)
|
||||
if key in components:
|
||||
data[f"branch_{i + 1}_{comp_name}"] = components[key]
|
||||
|
||||
# Universal components (no prefix)
|
||||
# Universal components (no prefix): Fermi plus universal
|
||||
# higher-order corrections.
|
||||
for name, values in components.items():
|
||||
if not name.startswith("branch_"):
|
||||
data[name] = values
|
||||
elif csv_verbosity == "concise":
|
||||
# Only total spectrum and normalized branch components with concise naming
|
||||
for i in range(analyzer._n_branches):
|
||||
branch_spectrum = analyzer._get_branch_spectrum(i)
|
||||
# Check if branch is degenerate (neutrino mass >= branch endpoint)
|
||||
branch_endpoint_keV = analyzer._unified_branches[i].endpoint_MeV * 1000
|
||||
neutrino_mass_keV = analyzer.config.neutrino_mass_MeV * 1000
|
||||
if branch_endpoint_keV <= neutrino_mass_keV:
|
||||
# Branch is degenerate, spectrum should be all zeros
|
||||
data[f"branch_{i + 1}"] = np.zeros_like(branch_spectrum)
|
||||
else:
|
||||
# Branch is valid, normalize as usual
|
||||
if analyzer.config.normalize_to_one:
|
||||
# Normalize to 1, ignoring intensity
|
||||
sum_spectrum = np.sum(branch_spectrum)
|
||||
if sum_spectrum > 0:
|
||||
data[f"branch_{i + 1}"] = branch_spectrum / sum_spectrum
|
||||
else:
|
||||
data[f"branch_{i + 1}"] = branch_spectrum
|
||||
else:
|
||||
# Normalize as usual with intensity
|
||||
sum_spectrum = np.sum(branch_spectrum)
|
||||
if sum_spectrum > 0:
|
||||
data[f"branch_{i + 1}"] = (
|
||||
branch_spectrum
|
||||
/ sum_spectrum
|
||||
* analyzer._unified_branches[i].intensity
|
||||
)
|
||||
else:
|
||||
data[f"branch_{i + 1}"] = branch_spectrum
|
||||
|
||||
df = pd.DataFrame(data)
|
||||
# Determine separator
|
||||
separator = (
|
||||
"\t"
|
||||
if analyzer.config.csv_separator == "tab"
|
||||
else analyzer.config.csv_separator
|
||||
)
|
||||
df.to_csv(filename, index=False, float_format="%.4e", sep=separator)
|
||||
|
||||
with open(filename, "r") as f:
|
||||
content = f.read()
|
||||
with open(filename, "w") as f:
|
||||
f.write("\n".join(header_lines) + "\n" + content)
|
||||
separator = "\t" if config.csv_separator == "tab" else config.csv_separator
|
||||
try:
|
||||
with open(filename, "w") as f:
|
||||
f.write("\n".join(header_lines) + "\n")
|
||||
df.to_csv(f, index=False, float_format="%.4e", sep=separator)
|
||||
except OSError as exc:
|
||||
raise ValueError(f"Cannot write spectrum CSV {filename}: {exc}") from exc
|
||||
|
||||
if analyzer._logger:
|
||||
analyzer._logger.info("CSV exported to %s", filename)
|
||||
|
||||
Reference in New Issue
Block a user