feat: polish CSV header format with improved metadata and column naming

2026-07-03 14:58:19 +03:00
parent 876e1e3ab8
commit a7eef7bc20
7 changed files with 86 additions and 577 deletions
@@ -15,6 +15,7 @@ from beta_spectrum.components.screening import ScreeningCorrection
 from beta_spectrum.components.exchange import ExchangeCorrection
 from beta_spectrum.components.radiative import RadiativeCorrection
 from beta_spectrum.utils import T_to_W
+from beta_spectrum.constants import ME_MEV


@dataclass
@@ -250,11 +251,13 @@ class BetaSpectrum:
        W0 = float(T_to_W(config.endpoint_MeV))

        if config.use_phase_space:
+            # Convert neutrino mass from MeV to natural units
+            m_nu_natural = config.neutrino_mass_MeV / ME_MEV
            components.append(
                PhaseSpace(
                    W0=W0,
                    transition_type=config.transition_type,
-                    m_nu=config.neutrino_mass_MeV,
+                    m_nu=m_nu_natural,
                    logger=logger,
                )
            )
@@ -628,11 +628,9 @@ class BetaSpectrumAnalyzer:
        total = self.total_spectrum(normalize=True)
        components = self.components

+        # Only include enabled corrections that are not basic components
+        # Basic components (phase_space and fermi) are always used and should not be listed
        enabled = []
-        if self.config.use_phase_space:
-            enabled.append("phase_space")
-        if self.config.use_fermi:
-            enabled.append("fermi")
        if self.config.use_screening:
            enabled.append("screening")
        if self.config.use_finite_size:
@@ -647,10 +645,19 @@ class BetaSpectrumAnalyzer:
        parent_symbol = self._element_symbol(self.config.Z_parent)
        daughter_symbol = self._element_symbol(self.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__}",
+            f"# beta-spectrum v{__import__('beta_spectrum').__version__}(build.{git_commit})",
            f"# timestamp: {datetime.now(timezone.utc).isoformat()}",
-            f"# source: {source_type}",
+            source_line,
            f"# nuclide: {parent_symbol}{self.config.A_number} -> {daughter_symbol}{self.config.A_number} (Z={self.config.Z_parent}->{self.config.Z_daughter})",
            f"# basic_endpoint: {self.config.endpoint_MeV * 1000:.1f} keV",
        ]
@@ -667,49 +674,82 @@ class BetaSpectrumAnalyzer:

        header_lines.append(f"# corrections: {', '.join(enabled)}")
        header_lines.append(f"# e_step: {self.config.e_step_MeV:.4f} MeV")
+        header_lines.append(f"# n_points: {len(self.energies_MeV)}")
+
+        # Add normalization mode
+        header_lines.append("# branch normalization: intensity")
+
+        # Separate branches into active and excluded lists
+        active_branches = []
+        excluded_branches = []

-        # Add transition types for all branches
-        transition_types = []
        for i, branch in enumerate(self._unified_branches):
-            transition_types.append(f"branch_{i + 1}:{branch.transition_type}")
-        header_lines.append(f"# transition_types: {'; '.join(transition_types)}")
+            branch_endpoint_keV = branch.endpoint_MeV * 1000
+            neutrino_mass_keV = self.config.neutrino_mass_MeV * 1000

-        # Branch info — unified view
-        for i, branch in enumerate(self._unified_branches):
-            header_lines.append(
-                f"#   branch_{i + 1}: E₀={branch.endpoint_MeV * 1000:.1f} keV, "
-                f"transition={branch.transition_type}, "
-                f"intensity={branch.intensity:.4f}"
-            )
+            # 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"
+                )
+            # Check if branch is excluded due to intensity cutoff
+            elif branch.intensity < self.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"
+                )
+            else:
+                active_branches.append(
+                    f"  branch_{i + 1}: E₀={branch_endpoint_keV:.1f} keV, transition={branch.transition_type}, intensity={branch.intensity:.4f}"
+                )

-        header_lines.append(f"# git_commit: {get_git_short_hash()}")
+        # Add active branches list
+        if active_branches:
+            header_lines.append("# active branches:")
+            for branch_info in active_branches:
+                header_lines.append(f"# {branch_info}")

+        # 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}")
+
+        # Create data dictionary with concise column headers
        data: Dict[str, np.ndarray] = {
            "energy_MeV": self.energies_MeV,
-            "spectrum": total,
+            "total_spectrum": total,
        }

        if csv_verbosity == "full":
-            # Per-branch spectra and components
+            # Per-branch spectra and components with concise branch naming
            for i in range(self._n_branches):
-                data[f"branch_{i + 1}_spectrum"] = self._get_branch_spectrum(i)
+                data[f"branch {i + 1}"] = self._get_branch_spectrum(i)
                for comp_name in ["PhaseSpace", "Radiative"]:
                    key = self._get_component_key(i, comp_name)
                    if key in components:
-                        data[f"branch_{i + 1}_{comp_name}"] = components[key]
+                        data[f"branch {i + 1}_{comp_name}"] = components[key]

            # Universal components (no prefix)
            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
+            # Only total spectrum and normalized branch components with concise naming
            for i in range(self._n_branches):
-                data[f"branch_{i + 1}_spectrum_normalized"] = (
-                    self._get_branch_spectrum(i) / np.sum(self._get_branch_spectrum(i))
-                    if np.sum(self._get_branch_spectrum(i)) > 0
-                    else self._get_branch_spectrum(i)
-                )
+                branch_spectrum = self._get_branch_spectrum(i)
+                # Check if branch is degenerate (neutrino mass >= branch endpoint)
+                branch_endpoint_keV = self._unified_branches[i].endpoint_MeV * 1000
+                neutrino_mass_keV = self.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
+                    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

        df = pd.DataFrame(data)
        df.to_csv(filename, index=False, float_format="%.4e")