将模型超参数保存为字典：json.decoder.JSONDecodeError：期望值：第1行第1列（字符0）

Question

我正在调整一些

sklearn

和

tensorflow

模型，我将超参数作为字典获取，例如

{'l1': 0.001, 'lr':0.001}

，并在我的调整功能中将它们保存在更大的字典中：

def optunize_hyperparameters(X_tr: Union[List[np.ndarray], pd.DataFrame, np.ndarray], y_tr: Union[dict, pd.DataFrame, np.ndarray],
                            Objective: Callable, builder_func: Callable, model_name: str, fit_params: dict, log_path: str, n_trials: int=10, **kwargs) -> dict:


    """
    Optimizes a model's hyperparameters with grid search. Loads existing ones if they exist.

    Parameters
    ----------
    X: 
        Training features.
    y: 
        Training targets
    Objective:
        Optuna objective callable class.
    model_name:
        In the format of "<model name>_qx" for x in {5,25,50,75,95}.
    hp_grid:
        Parameter grid for grid search
    fit_params:
        Parameters to pass to model.fit()
    log_path:
        Path to hyperparameter log file, e.g., "tuning_log.txt"

    Returns
    -------
    best_hps:
        A dictionary that can be passed as **kwargs to builder_func.
    """
    
    # Check if log exists, create log file if not
    if not os.path.exists(log_path):
        with open(log_path, 'w') as f:
            log = {}
            json.dump(log, f)

    # Load log
    try:
        with open(log_path, 'r') as f:
            log = json.load(f)
            print("Successfully loaded existing hyperparameters.")
    except OSError as e: 
            print(e)

    # Look for existing hps, optimize otherwise
    try:
        best_hps = log[model_name]
        print("Existing hyperparameters found, loading...")
    
    except:

        print("No existing hyperparameters found, optimizing hyperparameters...")
        study = optuna.create_study(
            sampler=optuna.samplers.RandomSampler(),
            pruner=optuna.pruners.SuccessiveHalvingPruner(),
            direction='maximize'
        )

        study.optimize(
            Objective(
                X_tr, y_tr,
                builder_func=builder_func,
                fit_params=fit_params,
                **kwargs
            ),
            n_trials=n_trials,
            n_jobs=-1
        )
        
        best_hps = study.best_params
        
        # Add hps to log and save it
        log[model_name] = best_hps

        with open(log_path, 'w') as f:
            json.dump(log,  f)
        
    return best_hps

我正在使用 slurm 在 Compute Canada 上并行提交多个作业（大约 32 个）。我似乎随机得到

json.decoder.JSONDecodeError: Expecting value: line 1 column 1 (char 0)

，对于任何特定的工作或任何特定的模型都不一致。我无法在本地复制这个问题，所以我什至不知道如何调试它。将文件从

.json

更改为

.txt

似乎有一点帮助。过去，我也遇到过文件中其他行的解码错误，因此可能不一定是第一个字符的问题，尽管第一个字符的问题似乎是最常见的。我看过

tuning_log.txt

，看起来不错：

{"MT1_2012": {"l1": 0.01, "lr": 0.01}, "MT3_1997": {"l1": 1e-06, "lr": 0.01}, ...}

我已经浏览过有关此问题的其他帖子，但它们都与获取网络数据有关，并且问题似乎与我的不同（这似乎是随机且不一致的）。

Answer 1

发生这种情况的原因是因为我正在并行运行多个作业，这些作业试图打开并写入同一个文件。我通过使用文件锁定解决了这个问题。我这样修改了我的函数（我需要更新我的文档字符串）

def optunize_hyperparameters(X_tr: Union[List[np.ndarray], pd.DataFrame, np.ndarray], y_tr: Union[dict, pd.DataFrame, np.ndarray],
                            Objective: Callable, builder_func: Callable, model_name: str, fit_params: dict, log_path: str, n_trials: int=10, **kwargs) -> dict:


    """
    Optimizes a model's hyperparameters with grid search. Loads existing ones if they exist.

    Parameters
    ----------
    X: 
        Training features.
    y: 
        Training targets
    Objective:
        Optuna objective callable class.
    model_name:
        In the format of "<model name>_qx" for x in {5,25,50,75,95}.
    hp_grid:
        Parameter grid for grid search
    fit_params:
        Parameters to pass to model.fit()
    log_path:
        Path to hyperparameter log file, e.g., "tuning_log.txt"

    Returns
    -------
    best_hps:
        A dictionary that can be passed as **kwargs to builder_func.
    """
    
    # Check if log exists, create log file if not
    if not os.path.exists(log_path):
        with open(log_path, 'w') as f:
            portalocker.lock(f, portalocker.LOCK_EX)
            log = {}
            json.dump(log, f)
            portalocker.unlock(f)

    # Load log
    try:
        with open(log_path, 'r+') as f:
            portalocker.lock(f, portalocker.LOCK_EX)
            log = json.load(f)
            # Perform read/write operations
            portalocker.unlock(f)
    except json.JSONDecodeError as e:
        raise e
    

    # Look for existing hps, optimize otherwise
    try:
        best_hps = log[model_name]
        print("Existing hyperparameters found, loading...")
    
    except:

        print("No existing hyperparameters found, optimizing hyperparameters...")
        study = optuna.create_study(
            sampler=optuna.samplers.RandomSampler(),
            pruner=optuna.pruners.SuccessiveHalvingPruner(),
            direction='maximize'
        )

        study.optimize(
            Objective(
                X_tr, y_tr,
                builder_func=builder_func,
                fit_params=fit_params,
                **kwargs
            ),
            n_trials=n_trials,
            n_jobs=-1
        )
        
        best_hps = study.best_params
        
        # Add hps to log and save it
        log[model_name] = best_hps

        with open(log_path, 'r+') as f:
            portalocker.lock(f, portalocker.LOCK_EX)
            log[model_name] = best_hps
            f.seek(0)
            json.dump(log, f)
            f.truncate()
            portalocker.unlock(f)
            
    return best_hps