retailgpt_evaluator/leaderboard.py

import pandas as pd, json

def build_leaderboard(path="models/retail_eval_results.json"):
    data = json.load(open(path))
    df = pd.DataFrame(data)
    # create composite score
    df["score"] = (df["rougeL"] + df["bleu"] + df["factuality"]) / 3
    df = df.sort_values("score", ascending=False)
    return df[["model", "rougeL", "bleu", "factuality", "score"]]