core/dataset.py

import json
from pathlib import Path
from typing import Any


REQUIRED_FIELDS = {"x", "y", "reasoning_type"}


def load_dataset(path: str | Path) -> list[dict[str, Any]]:
    """Load and validate the small CARB-style seed dataset."""
    dataset_path = Path(path)
    with dataset_path.open("r", encoding="utf-8") as f:
        rows = json.load(f)

    if not isinstance(rows, list):
        raise ValueError("Dataset must be a JSON list.")

    for index, row in enumerate(rows):
        missing = REQUIRED_FIELDS.difference(row)
        if missing:
            raise ValueError(f"Row {index} is missing required fields: {sorted(missing)}")
        if row["y"] not in (0, 1):
            raise ValueError(f"Row {index} has non-binary label: {row['y']!r}")
        if not isinstance(row["x"], str) or not row["x"].strip():
            raise ValueError(f"Row {index} has an empty input string.")
        if not isinstance(row["reasoning_type"], str) or not row["reasoning_type"].strip():
            raise ValueError(f"Row {index} has an empty reasoning_type.")

    return rows