Function load_runs

visualize_instability.py:24–42

(files: List[Path])

def load_runs(files: List[Path]) -> List[Dict]:
    runs = []
    for path in files:
        with path.open() as fh:
            data = json.load(fh)
        for idx, run in enumerate(data["runs"]):
            runs.append(
                {
                    "file": path.name,
                    "run_index_in_file": idx,
                    "agent": run["model"],
                    "finalScore": run["summary"]["finalScore"],
                    "scores": {
                        score["assignment"]["name"]: score["averageScore"]
                        for score in run["scores"]
                    },
                }
            )
    return runs


def melt_scores(runs: List[Dict]) -> pd.DataFrame: