ProcessPoolExecutor don't Execute

Question

我试图以比实际更快的速度获得ARIMA配置。

因此，我使用迭代方法来比较所有ARIMA组合，以选择更好的组合。为此，我创建了一个迭代函数：

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

事实上，我用这种方法只需几分钟就可以做到。但现在不是API使用逻辑的好时机。

# 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)

为了简化过程，我想使用多重处理方法迭代evaluate_arima_model函数。但是ProcessPoolExecutor不工作，因为不打印任何结果

# 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())

Answer 1

我不希望您展示的第二块代码能做任何事情。对于此代码：

# 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将始终为空，因为您这样声明它，然后从不调用evaluate_models或任何其他可能将对象放入orders的东西。由于orders为空，所以不会注册任何进程来运行，results也将为空，因此此代码不会执行任何操作。你的意思是在做with concurrent.futures....之前先打evaluate_models吗？