python - sklearn 和 n_jobs 中的超参数优化 > 1 : Pickling

Question

我陷入了“困境”。这是我的代码的结构:

• 行为类似于抽象类的基类
• 可以实例化的子类
  • 一种设置参数并使用 n_jobs=-1 调用 RandomizedSearchCV 或 GridSearchCV 的方法。
    • 本地函数 create_model，用于创建由 KerasClassifier 或 KerasRegressor 调用的神经网络模型(请参阅 this 教程)

我收到一条错误消息，指出无法对本地对象进行 pickle。如果我更改n_jobs=1，那么就没有问题。所以我怀疑问题出在本地函数和并行处理上。有解决办法吗？经过一番谷歌搜索后，似乎序列化器dill可以在这里工作(我什至找到了一个名为multiprocessing_on_dill的包)。但我目前依赖于 sklearn 的软件包。

Answer 1

我找到了问题的“解决方案”。我真的很困惑为什么这些例子 here与 n_jobs=-1 合作，但我的代码没有。问题似乎出在本地函数 create_model 上驻留在子类的方法中。如果我将本地函数设置为子类的方法，我可以设置 n_jobs > 1 .

回顾一下，这是我的代码的结构:

• 行为类似于抽象类的基类
• 可以实例化的子类
  • 设置参数并调用 RandomizedSearchCV 的方法或GridSearchCV与 n_jobs=-1 .
  • 一种方法，create_model ，创建由 KerasClassifier 调用的神经网络模型或KerasRegressor

代码的总体思路:

from abc import ABCMeta
import numpy as np
from sklearn.model_selection import GridSearchCV, RandomizedSearchCV

class MLAlgorithms(metaclass=ABCMeta):

    def __init__(self, X_train, y_train, X_test, y_test=None):
        """
        Constructor with train and test data.
        :param X_train: Train descriptor data
        :param y_train: Train observed data
        :param X_test: Test descriptor data
        :param y_test: Test observed data
        """
        ...

    @abstractmethod
    def setmlalg(self, mlalg):
        """
        Sets a machine learning algorithm.
        :param mlalg: Dictionary of the machine learning algorithm.
        """
        pass

    @abstractmethod
    def fitmlalg(self, mlalg, rid=None):
        """
        Fits a machine learning algorithm.
        :param mlalg: Machine learning algorithm
        """
        pass


class MLClassification(MLAlgorithms):
    """
    Main class for classification machine learning algorithms.
    """

    def setmlalg(self, mlalg):
        """
        Sets a classification machine learning algorithm.
        :param mlalg: Dictionary of the classification machine learning algorithm.
        """
        ...

    def fitmlalg(self, mlalg):
        """
        Fits a classification machine learning algorithm.
        :param mlalg: Classification machine learning algorithm
        """
        ...

    # Function to create model, required for KerasClassifier
    def create_model(self, n_layers=1, units=10, input_dim=10, output_dim=1,
                     optimizer="rmsprop", loss="binary_crossentropy",
                     kernel_initializer="glorot_uniform", activation="sigmoid",
                     kernel_regularizer="l2", kernel_regularizer_weight=0.01,
                     lr=0.01, momentum=0.0, decay=0.0, nesterov=False, rho=0.9, epsilon=1E-8,
                     beta_1=0.9, beta_2=0.999, schedule_decay=0.004):
        from keras.models import Sequential
        from keras.layers import Dense
        from keras import regularizers, optimizers

        # Create model
        if kernel_regularizer.lower() == "l1":
            kernel_regularizer = regularizers.l1(l=kernel_regularizer_weight)
        elif kernel_regularizer.lower() == "l2":
            kernel_regularizer = regularizers.l2(l=kernel_regularizer_weight)
        elif kernel_regularizer.lower() == "l1_l2":
            kernel_regularizer = regularizers.l1_l2(l1=kernel_regularizer_weight, l2=kernel_regularizer_weight)
        else:
            print("Warning: Kernel regularizer {0} not supported. Using default 'l2' regularizer.".format(
                kernel_regularizer))
            kernel_regularizer = regularizers.l2(l=kernel_regularizer_weight)

        if optimizer.lower() == "sgd":
            optimizer = optimizers.sgd(lr=lr, momentum=momentum, decay=decay, nesterov=nesterov)
        elif optimizer.lower() == "rmsprop":
            optimizer = optimizers.rmsprop(lr=lr, rho=rho, epsilon=epsilon, decay=decay)
        elif optimizer.lower() == "adagrad":
            optimizer = optimizers.adagrad(lr=lr, epsilon=epsilon, decay=decay)
        elif optimizer.lower() == "adadelta":
            optimizer = optimizers.adadelta(lr=lr, rho=rho, epsilon=epsilon, decay=decay)
        elif optimizer.lower() == "adam":
            optimizer = optimizers.adam(lr=lr, beta_1=beta_1, beta_2=beta_2, epsilon=epsilon, decay=decay)
        elif optimizer.lower() == "adamax":
            optimizer = optimizers.adamax(lr=lr, beta_1=beta_1, beta_2=beta_2, epsilon=epsilon, decay=decay)
        elif optimizer.lower() == "nadam":
            optimizer = optimizers.nadam(lr=lr, beta_1=beta_1, beta_2=beta_2, epsilon=epsilon,
                                         schedule_decay=schedule_decay)
        else:
            print("Warning: Optimizer {0} not supported. Using default 'sgd' optimizer.".format(optimizer))
            optimizer = "sgd"

        model = Sequential()
        model.add(
            Dense(units=units, input_dim=input_dim,
                  kernel_initializer=kernel_initializer, activation=activation,
                  kernel_regularizer=kernel_regularizer))
        for layer_count in range(n_layers - 1):
            model.add(
                Dense(units=units, kernel_initializer=kernel_initializer, activation=activation,
                      kernel_regularizer=kernel_regularizer))
        model.add(Dense(units=output_dim,
                        kernel_initializer=kernel_initializer, activation=activation,
                        kernel_regularizer=kernel_regularizer))

        # Compile model
        model.compile(loss=loss, optimizer=optimizer, metrics=['accuracy'])
        return model


class MLRegression(MLAlgorithms):
    """
    Main class for regression machine learning algorithms.
    """
    ...