DualFlow/models/uf-rl/data_to_rl/loader.py

import pandas as pd
from pathlib import Path


def resolve_path(project_root: Path, relative_path: str) -> Path:
    return project_root / relative_path


def load_all_units_cycles(cfg: dict) -> pd.DataFrame:
    """
    读取所有启用 UF 机组的 filtered_cycles 数据，
    返回【物理周期层级】的合并 DataFrame。
    """
    project_root = Path(cfg["Paths"]["project_root"])
    raw_cfg = cfg["Paths"]["raw_data"]

    all_dfs = []

    for unit in raw_cfg["enabled_units"]:
        file_name = raw_cfg["cycle_file_pattern"].format(unit=unit)
        file_path = resolve_path(
            project_root,
            raw_cfg["filtered_cycles_dir"]
        ) / file_name

        if not file_path.exists():
            raise FileNotFoundError(f"未找到 UF{unit} 数据文件: {file_path}")

        df_unit = pd.read_csv(file_path)
        df_unit["unit_id"] = unit  # 仅用于分组，不进入状态
        all_dfs.append(df_unit)

    return pd.concat(all_dfs, ignore_index=True)