def __post_init__()

in src/open_r1/configs.py [0:0]

• 37 lines of code
• 13 McCabe index (conditional complexity)

    def __post_init__(self):
        if self.dataset_name is None and self.dataset_mixture is None:
            raise ValueError("Either `dataset_name` or `dataset_mixture` must be provided")

        if self.dataset_mixture is not None:
            if not isinstance(self.dataset_mixture, dict) or "datasets" not in self.dataset_mixture:
                raise ValueError(
                    "dataset_mixture must be a dictionary with a 'datasets' key. "
                    "Expected format: {'datasets': [...], 'seed': int}"
                )

            datasets_list = []
            datasets_data = self.dataset_mixture.get("datasets", [])

            if isinstance(datasets_data, list):
                for dataset_config in datasets_data:
                    datasets_list.append(
                        DatasetConfig(
                            id=dataset_config.get("id"),
                            config=dataset_config.get("config"),
                            split=dataset_config.get("split", "train"),
                            columns=dataset_config.get("columns"),
                            weight=dataset_config.get("weight", 1.0),
                        )
                    )
            else:
                raise ValueError("'datasets' must be a list of dataset configurations")

            self.dataset_mixture = DatasetMixtureConfig(
                datasets=datasets_list,
                seed=self.dataset_mixture.get("seed", 0),
                test_split_size=self.dataset_mixture.get("test_split_size", None),
            )

            # Check that column names are consistent across all dataset configs
            columns_sets = [set(dataset.columns) for dataset in datasets_list if dataset.columns is not None]
            if columns_sets:
                first_columns = columns_sets[0]
                if not all(columns == first_columns for columns in columns_sets):
                    raise ValueError(
                        "Column names must be consistent across all dataset configurations in a mixture. "
                        f"Found different column sets: {[list(cols) for cols in columns_sets]}"
                    )