backtest error using gru

[LiuHao-THU]

here is the problem, i am using GRU for prediction, here is my backtest config ` ###################################

prediction, backtest & analysis

################################### port_analysis_config = { "executor": { "class": "SimulatorExecutor", "module_path": "qlib.backtest.executor", "kwargs": { "time_per_step": "day", "generate_portfolio_metrics": True, }, }, "strategy": { "class": "TopkDropoutStrategy", "module_path": "qlib.contrib.strategy.signal_strategy", "kwargs": { "model": model, "dataset": dataset, "topk":50, "n_drop": 5, }, }, "backtest": { "start_time": "2022-01-01", "end_time": '2022-05-20', "account": 100000000, "benchmark": benchmark, "exchange_kwargs": { "freq": "day", "limit_threshold": 0.0, "deal_price": "close", "open_cost": 0.0005, "close_cost": 0.0015, "min_cost": 5, }, }, }

backtest and analysis

with R.start(experiment_name="backtest_analysis"): recorder = R.get_recorder(recorder_id=rid, experiment_name="GRU") model = recorder.load_object("trained_model")

# prediction
recorder = R.get_recorder()
ba_rid = recorder.id
sr = SignalRecord(model, dataset, recorder)
sr.generate()

# backtest & analysis
par = PortAnaRecord(recorder, port_analysis_config, "day")
par.generate()

then, the ffr report nan which is very strange 'The following are analysis results of benchmark return(1day).' risk mean -0.000600 std 0.011434 annualized_return -0.142707 information_ratio -0.809016 max_drawdown -0.140281 'The following are analysis results of the excess return without cost(1day).' risk mean 0.000600 std 0.011434 annualized_return 0.142707 information_ratio 0.809016 max_drawdown -0.069261 'The following are analysis results of the excess return with cost(1day).' risk mean 0.000600 std 0.011434 annualized_return 0.142707 information_ratio 0.809016 max_drawdown -0.069261 'The following are analysis results of indicators(1day).' value ffr NaN pa NaN pos NaN

`

can someone answer this question?

[LiuHao-THU]

solved

[davidyu0319]

solved

Could you guide me how to resolve this? I also meet this issue...