def generate_system_df()

in scripts/zeno_visualize.py [0:0]

• 26 lines of code
• 18 McCabe index (conditional complexity)

def generate_system_df(data, config):
    """Generate a dataframe for a specific system to be uploaded to Zeno.

    Args:
        data: The data to generate a dataframe from.
        config: The configuration of the task.

    Returns:
        pd.Dataframe: A dataframe that is ready to be uploaded to Zeno as a system.
    """
    ids = [x["doc_id"] for x in data]
    system_dict = {"id": ids}
    system_dict["output"] = [""] * len(ids)

    if config["output_type"] == "loglikelihood":
        system_dict["output"] = [
            "correct" if x["filtered_resps"][0][1] is True else "incorrect"
            for x in data
        ]
    elif config["output_type"] == "multiple_choice":
        system_dict["output"] = [
            ", ".join([str(y[0]) for y in x["filtered_resps"]]) for x in data
        ]
        system_dict["num_answers"] = [len(x["filtered_resps"]) for x in data]
    elif config["output_type"] == "loglikelihood_rolling":
        system_dict["output"] = [str(x["filtered_resps"][0]) for x in data]
    elif config["output_type"] == "generate_until":
        system_dict["output"] = [str(x["filtered_resps"][0]) for x in data]
        system_dict["output_length"] = [len(str(x["filtered_resps"][0])) for x in data]

    metrics = {}
    for metric in config["metric_list"]:
        if "aggregation" in metric and metric["aggregation"] == "mean":
            metrics[metric["metric"]] = [x[metric["metric"]] for x in data]

    system_dict.update(metrics)
    system_df = pd.DataFrame(system_dict)
    return system_df