"""Build aligned tabular and sequence benchmarks from normalized cycles.""" from __future__ import annotations from collections import defaultdict from dataclasses import dataclass from pathlib import Path from typing import Iterable import numpy as np import pandas as pd from src.data.adapters import DischargeCycle from src.data.partial_cycle import ( PartialCycleConfig, extract_partial_cycle_features, make_partial_cycle_sequence, prior_equivalent_full_cycles, reference_capacity_from_characterization, ) from src.utils.config import FEATURE_COLS_V3, RATED_CAPACITY_AH, SEQUENCE_FEATURE_COLS_V3 @dataclass class BenchmarkBundle: features: pd.DataFrame sequences: np.ndarray sequence_index: pd.DataFrame exclusions: pd.DataFrame def build_benchmark_bundle( cycles: Iterable[DischargeCycle], *, config: PartialCycleConfig = PartialCycleConfig(), excluded_batteries: set[str] | None = None, rated_capacity_by_dataset: dict[str, float] | None = None, ) -> BenchmarkBundle: """Build leakage-safe inputs and SOH targets from normalized cycles.""" excluded_batteries = excluded_batteries or set() rated_capacity_by_dataset = rated_capacity_by_dataset or RATED_CAPACITY_AH grouped: dict[tuple[str, str], list[DischargeCycle]] = defaultdict(list) pre_exclusions: list[dict[str, object]] = [] for cycle in cycles: if cycle.battery_id in excluded_batteries: pre_exclusions.append({ "dataset": cycle.dataset, "battery_id": cycle.battery_id, "cycle_number": cycle.cycle_number, "source": cycle.source, "reason": "Battery excluded by the pre-registered data-quality list", }) continue grouped[(cycle.dataset, cycle.battery_id)].append(cycle) feature_rows: list[dict[str, object]] = [] sequences: list[np.ndarray] = [] sequence_rows: list[dict[str, object]] = [] exclusion_rows: list[dict[str, object]] = pre_exclusions for (dataset, battery_id), battery_cycles in sorted(grouped.items()): battery_cycles.sort(key=lambda item: item.cycle_number) valid_caps = [cycle.capacity_ah for cycle in battery_cycles if np.isfinite(cycle.capacity_ah) and cycle.capacity_ah > 0] if len(valid_caps) < config.reference_cycles: continue reference = reference_capacity_from_characterization( valid_caps, reference_cycles=config.reference_cycles ) if dataset not in rated_capacity_by_dataset: raise KeyError(f"Rated capacity is not configured for dataset: {dataset}") rated_capacity = rated_capacity_by_dataset[dataset] prior_efc_values = prior_equivalent_full_cycles( pd.Series([cycle.capacity_ah for cycle in battery_cycles]), rated_capacity, ).to_numpy(dtype=float) full_capacity_threshold = 0.85 * float(np.quantile(valid_caps, 0.95)) characterization_start = next( i for i, cycle in enumerate(battery_cycles) if np.isfinite(cycle.capacity_ah) and cycle.capacity_ah >= full_capacity_threshold ) for position, cycle in enumerate(battery_cycles): if position < characterization_start: exclusion_rows.append({ "dataset": dataset, "battery_id": battery_id, "cycle_number": cycle.cycle_number, "source": cycle.source, "reason": "Pre-characterization partial discharge; not a full-capacity SOH label", }) continue if not np.isfinite(cycle.capacity_ah) or cycle.capacity_ah <= 0: exclusion_rows.append({ "dataset": dataset, "battery_id": battery_id, "cycle_number": cycle.cycle_number, "source": cycle.source, "reason": "Non-positive or non-finite full-cycle capacity label", }) continue soh = 100.0 * cycle.capacity_ah / reference if soh > 120.0: exclusion_rows.append({ "dataset": dataset, "battery_id": battery_id, "cycle_number": cycle.cycle_number, "source": cycle.source, "reason": "Capacity characterization exceeds 120% of the robust initial reference", }) continue prior_efc = float(prior_efc_values[position]) try: features = extract_partial_cycle_features( cycle.measurements, cycle_index=cycle.cycle_number, prior_efc=prior_efc, ambient_temperature=cycle.ambient_temperature_c, rated_capacity_ah=rated_capacity, config=config, ) sequence = make_partial_cycle_sequence( cycle.measurements, ambient_temperature=cycle.ambient_temperature_c, rated_capacity_ah=rated_capacity, config=config, ) except (KeyError, ValueError, TypeError) as exc: exclusion_rows.append({ "dataset": dataset, "battery_id": battery_id, "cycle_number": cycle.cycle_number, "source": cycle.source, "reason": f"{type(exc).__name__}: {exc}", }) continue row: dict[str, object] = { "dataset": dataset, "battery_id": battery_id, "cycle_number": cycle.cycle_number, "capacity_ah": cycle.capacity_ah, "reference_capacity_ah": reference, "SoH": soh, "source": cycle.source, } row.update(features) feature_rows.append(row) sequences.append(sequence.to_numpy(dtype=np.float32)) sequence_rows.append({ "dataset": dataset, "battery_id": battery_id, "cycle_number": cycle.cycle_number, "SoH": row["SoH"], }) columns = [ "dataset", "battery_id", "cycle_number", "capacity_ah", "reference_capacity_ah", "SoH", "source", *FEATURE_COLS_V3, ] features_frame = pd.DataFrame(feature_rows, columns=columns) sequence_array = ( np.stack(sequences) if sequences else np.empty((0, config.sequence_bins, len(SEQUENCE_FEATURE_COLS_V3)), dtype=np.float32) ) return BenchmarkBundle( features=features_frame, sequences=sequence_array, sequence_index=pd.DataFrame(sequence_rows), exclusions=pd.DataFrame( exclusion_rows, columns=["dataset", "battery_id", "cycle_number", "source", "reason"], ), ) def save_benchmark_bundle(bundle: BenchmarkBundle, output_dir: str | Path) -> None: """Persist one dataset bundle using portable CSV and compressed NumPy.""" output_dir = Path(output_dir) output_dir.mkdir(parents=True, exist_ok=True) bundle.features.to_csv(output_dir / "features.csv", index=False) bundle.sequence_index.to_csv(output_dir / "sequence_index.csv", index=False) bundle.exclusions.to_csv(output_dir / "exclusions.csv", index=False) np.savez_compressed( output_dir / "sequences.npz", X=bundle.sequences, feature_names=np.asarray(SEQUENCE_FEATURE_COLS_V3), )