backend/experiments/benchmark_runner.py

import time

class BenchmarkRunner:
    def run(self, orchestrator, datasets):
        results = []
        for name, (df, target) in datasets.items():
            start = time.time()
            try:
                output = orchestrator.run(df, target, train=True)
                end = time.time()

                results.append({
                    "dataset": name,
                    "strategy": output.get("strategy"),
                    "metrics": output.get("metrics"),
                    "time": round(end - start, 2),
                    "error": None
                })
            except Exception as e:
                end = time.time()
                results.append({
                    "dataset": name,
                    "strategy": None,
                    "metrics": None,
                    "time": round(end - start, 2),
                    "error": str(e)
                })
        return results