ProcessPoolExecutor don't Execute

问题

I try to get ARIMA configuration some faster that I acctually do.

So I use a Iterate method to compare all ARIMA combinations to select better. For that I create a function to Iterate:

def difference(dataset, interval=1):
    diff = list()
    for i in range(interval, len(dataset)):
        value = dataset[i] - dataset[i - interval]
        diff.append(value)
    return np.array(diff)

# invert differenced value
def inverse_difference(history, yhat, interval=1):
    return yhat + history[-interval]

# evaluate an ARIMA model for a given order (p,d,q) and return RMSE
def evaluate_arima_model(dataset, arima_order):

    dataset = dataset.astype('float32')
    train_size = int(len(dataset) * 0.50)
    train, test = dataset[0:train_size], dataset[train_size:]
    
    history = [x for x in train]
    # make predictions
    predictions = list()
    for t in range(len(test)):
        # difference data
        months_in_year = maxlength
        diff = difference(history, months_in_year)
        model = ARIMA(diff, order=arima_order)
        model_fit = model.fit(trend='nc', disp=0)
        yhat = model_fit.forecast()[0]
        yhat = inverse_difference(history, yhat, months_in_year)
        predictions.append(yhat)
        history.append(test[t])
    # calculate out of sample error
    mse = mean_squared_error(test, predictions)
    rmse = sqrt(mse)
    return rmse

Actually I do that in minutes with this method. But isn't good time for an API where I gonna use the logic.

# evaluate combinations of p, d and q values for an ARIMA model

def evaluate_models(dataset, p_values, d_values, q_values):
    dataset = dataset.astype('float32')
    train_size = int(len(dataset) * 0.50)
    train, test = dataset[0:train_size], dataset[train_size:]
    
    global best_score, best_cfg 
    best_score, best_cfg = float("inf"), None
    for p in p_values:
        for d in d_values:
            for q in q_values:
                order = (p,d,q)
                try:
                    mse = evaluate_arima_model(dataset, order)
                    if mse < best_score:
                        best_score, best_cfg = mse, order
                    print('ARIMA%s RMSE=%.3f' % (order,mse))
                except:
                    continue
        # print(best_cfg, best_score)
    print('Best ARIMA%s RMSE=%.3f' % (best_cfg, best_score))




# evaluate parameters
p_values = range(0, 7)
d_values = range(0, 3)
q_values = range(0, 7)
warnings.filterwarnings("ignore")
evaluate_models(data_train.values, p_values, d_values, q_values)

To acelerate the process I want use Multiprocessing method iterating evaluate_arima_model function. But ProcessPoolExecutor don't work because don't print any result

# evaluate combinations of p, d and q values for an ARIMA model
orders = []
def fill_orders( p_values, d_values, q_values):
    
    for p in p_values:
        for d in d_values:
            for q in q_values:
                order = (p,d,q)
                orders.append(order)

# fill orders array
p_values = range(0, 7)
d_values = range(0, 3)
q_values = range(0, 7)
warnings.filterwarnings("ignore")
fill_orders(p_values, d_values, q_values)

with concurrent.futures.ProcessPoolExecutor() as executor:
    results = [executor.submit(evaluate_arima_model, (dataset, order)) for order in orders]
    for f in concurrent.futures.as_completed(results):
        print(f.result())
        try:
            f.result()
        except:
            continue
        else:
            print(f.result())

回答1:

I wouldn't expect the second block of code you've shown to do anything. For this code:

# evaluate combinations of p, d and q values for an ARIMA model
orders = []
def evaluate_models( p_values, d_values, q_values):
    
    for p in p_values:
        for d in d_values:
            for q in q_values:
                order = (p,d,q)
                orders.append(order)

with concurrent.futures.ProcessPoolExecutor() as executor:
    results = [executor.submit(evaluate_arima_model, (dataset, order)) for order in orders]
    for f in concurrent.futures.as_completed(results):
        print(f.result())
        try:
            f.result()
        except:
            continue
        else:
            print(f.result())

orders will always be empty because you are declaring it so and then never calling evaluate_models, or anything else that could be putting objects into orders. Since orders is empty, no processes will be registered to run, and results will also be empty, and so this code won't do anything. Do you mean to call evaluate_models before you do with concurrent.futures....?

来源：https://stackoverflow.com/questions/65066091/processpoolexecutor-dont-execute