MLPRegressor#

class sklearn.neural_network.MLPRegressor(loss='squared_error', hidden_layer_sizes=(100,), activation='relu', *, solver='adam', alpha=0.0001, batch_size='auto', learning_rate='constant', learning_rate_init=0.001, power_t=0.5, max_iter=200, shuffle=True, random_state=None, tol=0.0001, verbose=False, warm_start=False, momentum=0.9, nesterovs_momentum=True, early_stopping=False, validation_fraction=0.1, beta_1=0.9, beta_2=0.999, epsilon=1e-08, n_iter_no_change=10, max_fun=15000)[source]#

多层感知器回归器。

This model optimizes the squared error using LBFGS or stochastic gradient descent.

版本 0.18 新增。

参数:

loss{‘squared_error’, ‘poisson’}, default=’squared_error’

The loss function to use when training the weights. Note that the “squared error” and “poisson” losses actually implement “half squares error” and “half poisson deviance” to simplify the computation of the gradient. Furthermore, the “poisson” loss internally uses a log-link (exponential as the output activation function) and requires y >= 0.

Changed in version 1.7: Added parameter loss and option ‘poisson’.

hidden_layer_sizesarray-like of shape(n_layers - 2,), default=(100,)

The ith element represents the number of neurons in the ith hidden layer.

activation{‘identity’, ‘logistic’, ‘tanh’, ‘relu’}, default=’relu’

Activation function for the hidden layer.

‘identity’, no-op activation, useful to implement linear bottleneck, returns f(x) = x
‘logistic’, the logistic sigmoid function, returns f(x) = 1 / (1 + exp(-x)).
‘tanh’, the hyperbolic tan function, returns f(x) = tanh(x).
‘relu’, the rectified linear unit function, returns f(x) = max(0, x)

solver{‘lbfgs’, ‘sgd’, ‘adam’}, default=’adam’

The solver for weight optimization.

‘lbfgs’ is an optimizer in the family of quasi-Newton methods.
‘sgd’ refers to stochastic gradient descent.
‘adam’ refers to a stochastic gradient-based optimizer proposed by Kingma, Diederik, and Jimmy Ba

For a comparison between Adam optimizer and SGD, see Compare Stochastic learning strategies for MLPClassifier.

Note: The default solver ‘adam’ works pretty well on relatively large datasets (with thousands of training samples or more) in terms of both training time and validation score. For small datasets, however, ‘lbfgs’ can converge faster and perform better.

alphafloat, default=0.0001

Strength of the L2 regularization term. The L2 regularization term is divided by the sample size when added to the loss.

batch_sizeint, default=’auto’

Size of minibatches for stochastic optimizers. If the solver is ‘lbfgs’, the regressor will not use minibatch. When set to “auto”, batch_size=min(200, n_samples).

learning_rate{‘constant’, ‘invscaling’, ‘adaptive’}, default=’constant’

Learning rate schedule for weight updates.

‘constant’ is a constant learning rate given by ‘learning_rate_init’.
‘invscaling’ gradually decreases the learning rate learning_rate_ at each time step ‘t’ using an inverse scaling exponent of ‘power_t’. effective_learning_rate = learning_rate_init / pow(t, power_t)
‘adaptive’ keeps the learning rate constant to ‘learning_rate_init’ as long as training loss keeps decreasing. Each time two consecutive epochs fail to decrease training loss by at least tol, or fail to increase validation score by at least tol if ‘early_stopping’ is on, the current learning rate is divided by 5.

Only used when solver=’sgd’.

learning_rate_initfloat, default=0.001

The initial learning rate used. It controls the step-size in updating the weights. Only used when solver=’sgd’ or ‘adam’.

power_tfloat, default=0.5

The exponent for inverse scaling learning rate. It is used in updating effective learning rate when the learning_rate is set to ‘invscaling’. Only used when solver=’sgd’.

max_iter整型, 默认为 200

Maximum number of iterations. The solver iterates until convergence (determined by ‘tol’) or this number of iterations. For stochastic solvers (‘sgd’, ‘adam’), note that this determines the number of epochs (how many times each data point will be used), not the number of gradient steps.

shufflebool, default=True

Whether to shuffle samples in each iteration. Only used when solver=’sgd’ or ‘adam’.

random_stateint, RandomState instance, default=None

Determines random number generation for weights and bias initialization, train-test split if early stopping is used, and batch sampling when solver=’sgd’ or ‘adam’. Pass an int for reproducible results across multiple function calls. See Glossary.

tolfloat, default=1e-4

Tolerance for the optimization. When the loss or score is not improving by at least tol for n_iter_no_change consecutive iterations, unless learning_rate is set to ‘adaptive’, convergence is considered to be reached and training stops.

verbosebool, default=False

Whether to print progress messages to stdout.

warm_startbool, default=False

When set to True, reuse the solution of the previous call to fit as initialization, otherwise, just erase the previous solution. See the Glossary.

momentumfloat, default=0.9

Momentum for gradient descent update. Should be between 0 and 1. Only used when solver=’sgd’.

nesterovs_momentumbool, default=True

Whether to use Nesterov’s momentum. Only used when solver=’sgd’ and momentum > 0.

early_stoppingbool, default=False

Whether to use early stopping to terminate training when validation score is not improving. If set to True, it will automatically set aside validation_fraction of training data as validation and terminate training when validation score is not improving by at least tol for n_iter_no_change consecutive epochs. Only effective when solver=’sgd’ or ‘adam’.

validation_fractionfloat, default=0.1

The proportion of training data to set aside as validation set for early stopping. Must be between 0 and 1. Only used if early_stopping is True.

beta_1float, default=0.9

Exponential decay rate for estimates of first moment vector in adam, should be in [0, 1). Only used when solver=’adam’.

beta_2float, default=0.999

Exponential decay rate for estimates of second moment vector in adam, should be in [0, 1). Only used when solver=’adam’.

epsilonfloat, default=1e-8

Value for numerical stability in adam. Only used when solver=’adam’.

n_iter_no_changeint, default=10

Maximum number of epochs to not meet tol improvement. Only effective when solver=’sgd’ or ‘adam’.

0.20 版本新增。

max_funint, default=15000

Only used when solver=’lbfgs’. Maximum number of function calls. The solver iterates until convergence (determined by tol), number of iterations reaches max_iter, or this number of function calls. Note that number of function calls will be greater than or equal to the number of iterations for the MLPRegressor.

版本 0.22 新增。

属性:

loss_float: The current loss computed with the loss function.
best_loss_float: The minimum loss reached by the solver throughout fitting. If early_stopping=True, this attribute is set to None. Refer to the best_validation_score_ fitted attribute instead. Only accessible when solver=’sgd’ or ‘adam’.
loss_curve_list of shape (n_iter_,): Loss value evaluated at the end of each training step. The ith element in the list represents the loss at the ith iteration. Only accessible when solver=’sgd’ or ‘adam’.
validation_scores_list of shape (n_iter_,) or None: The score at each iteration on a held-out validation set. The score reported is the R2 score. Only available if early_stopping=True, otherwise the attribute is set to None. Only accessible when solver=’sgd’ or ‘adam’.
best_validation_score_float or None: The best validation score (i.e. R2 score) that triggered the early stopping. Only available if early_stopping=True, otherwise the attribute is set to None. Only accessible when solver=’sgd’ or ‘adam’.
t_int: The number of training samples seen by the solver during fitting. Mathematically equals n_iters * X.shape[0], it means time_step and it is used by optimizer’s learning rate scheduler.
coefs_list of shape (n_layers - 1,): The ith element in the list represents the weight matrix corresponding to layer i.
intercepts_list of shape (n_layers - 1,): The ith element in the list represents the bias vector corresponding to layer i + 1.
n_features_in_int: 在拟合期间看到的特征数。

0.24 版本新增。
feature_names_in_shape 为 (n_features_in_,) 的 ndarray: 在 fit 期间看到的特征名称。仅当 X 具有全部为字符串的特征名称时才定义。

1.0 版本新增。
n_iter_int: The number of iterations the solver has run.
n_layers_int: Number of layers.
n_outputs_int: 输出数量。
out_activation_str: Name of the output activation function.

另请参阅

BernoulliRBM: 伯努利受限玻尔兹曼机 (RBM)。
MLPClassifier: 多层感知器分类器。
sklearn.linear_model.SGDRegressor: 通过使用 SGD 最小化正则化经验损失来拟合的线性模型。

注意事项

MLPRegressor trains iteratively since at each time step the partial derivatives of the loss function with respect to the model parameters are computed to update the parameters.

It can also have a regularization term added to the loss function that shrinks model parameters to prevent overfitting.

This implementation works with data represented as dense and sparse numpy arrays of floating point values.

References

Hinton, Geoffrey E. “Connectionist learning procedures.” Artificial intelligence 40.1 (1989): 185-234.

Glorot, Xavier, and Yoshua Bengio. “Understanding the difficulty of training deep feedforward neural networks.” International Conference on Artificial Intelligence and Statistics. 2010.

He, Kaiming, et al (2015). “Delving deep into rectifiers: Surpassing human-level performance on imagenet classification.”

Kingma, Diederik, and Jimmy Ba (2014) “Adam: A method for stochastic optimization.”

示例

>>> from sklearn.neural_network import MLPRegressor
>>> from sklearn.datasets import make_regression
>>> from sklearn.model_selection import train_test_split
>>> X, y = make_regression(n_samples=200, n_features=20, random_state=1)
>>> X_train, X_test, y_train, y_test = train_test_split(X, y,
...                                                     random_state=1)
>>> regr = MLPRegressor(random_state=1, max_iter=2000, tol=0.1)
>>> regr.fit(X_train, y_train)
MLPRegressor(max_iter=2000, random_state=1, tol=0.1)
>>> regr.predict(X_test[:2])
array([  28.98, -291])
>>> regr.score(X_test, y_test)
0.98

fit(X, y, sample_weight=None)[source]#

Fit the model to data matrix X and target(s) y.

参数:

Xndarray or sparse matrix of shape (n_samples, n_features): 输入数据。
yndarray of shape (n_samples,) or (n_samples, n_outputs): 目标值（分类中的类别标签，回归中的实数）。
sample_weightshape 为 (n_samples,) 的 array-like, default=None: 样本权重。

在版本 1.7 中新增。

返回:

selfobject: Returns a trained MLP model.

get_metadata_routing()[source]#

获取此对象的元数据路由。

请查阅用户指南，了解路由机制如何工作。

返回:

routingMetadataRequest: 封装路由信息的 MetadataRequest。

get_params(deep=True)[source]#

获取此估计器的参数。

参数:

deepbool, default=True: 如果为 True，将返回此估计器以及包含的子对象（如果它们是估计器）的参数。

返回:

paramsdict: 参数名称映射到其值。

partial_fit(X, y, sample_weight=None)[source]#

Update the model with a single iteration over the given data.

参数:

Xshape 为 (n_samples, n_features) 的 {array-like, sparse matrix}: 输入数据。
yndarray of shape (n_samples,): 目标值。
sample_weightshape 为 (n_samples,) 的 array-like, default=None: 样本权重。

版本 1.6 中新增。

返回:

selfobject: Trained MLP model.

predict(X)[source]#

Predict using the multi-layer perceptron model.

参数:

Xshape 为 (n_samples, n_features) 的 {array-like, sparse matrix}: 输入数据。

返回:

yndarray of shape (n_samples, n_outputs): 预测值。

score(X, y, sample_weight=None)[source]#

返回测试数据的决定系数。

The coefficient of determination, $R^2$, is defined as $(1 - \frac{u}{v})$, where $u$ is the residual sum of squares ((y_true - y_pred)** 2).sum() and $v$ is the total sum of squares ((y_true - y_true.mean()) ** 2).sum(). The best possible score is 1.0 and it can be negative (because the model can be arbitrarily worse). A constant model that always predicts the expected value of y, disregarding the input features, would get a $R^2$ score of 0.0.

参数:

Xshape 为 (n_samples, n_features) 的 array-like: 测试样本。对于某些估计器，这可能是一个预先计算的核矩阵或一个通用对象列表，形状为 (n_samples, n_samples_fitted)，其中 n_samples_fitted 是用于估计器拟合的样本数。
yshape 为 (n_samples,) 或 (n_samples, n_outputs) 的 array-like: X 的真实值。
sample_weightshape 为 (n_samples,) 的 array-like, default=None: 样本权重。

返回:

scorefloat: self.predict(X) 相对于 y 的 $R^2$。

注意事项

The $R^2$ score used when calling score on a regressor uses multioutput='uniform_average' from version 0.23 to keep consistent with default value of r2_score. This influences the score method of all the multioutput regressors (except for MultiOutputRegressor).

set_fit_request(*, sample_weight: bool | None | str = '$UNCHANGED$') → MLPRegressor[source]#

配置是否应请求元数据以传递给 fit 方法。

请注意，此方法仅在以下情况下相关：此估计器用作元估计器中的子估计器，并且通过 enable_metadata_routing=True 启用了元数据路由（请参阅 sklearn.set_config）。请查看用户指南以了解路由机制的工作原理。

每个参数的选项如下：

True：请求元数据，如果提供则传递给 fit。如果未提供元数据，则忽略该请求。
False：不请求元数据，元估计器不会将其传递给 fit。
None：不请求元数据，如果用户提供元数据，元估计器将引发错误。
str：应将元数据以给定别名而不是原始名称传递给元估计器。

默认值 (sklearn.utils.metadata_routing.UNCHANGED) 保留现有请求。这允许您更改某些参数的请求而不更改其他参数。

在版本 1.3 中新增。

参数:

sample_weightstr, True, False, or None, default=sklearn.utils.metadata_routing.UNCHANGED: fit 方法中 sample_weight 参数的元数据路由。

返回:

selfobject: 更新后的对象。

set_params(**params)[source]#

设置此估计器的参数。

此方法适用于简单的估计器以及嵌套对象（如 Pipeline）。后者具有 <component>__<parameter> 形式的参数，以便可以更新嵌套对象的每个组件。

参数:

**paramsdict: 估计器参数。

返回:

selfestimator instance: 估计器实例。

set_partial_fit_request(*, sample_weight: bool | None | str = '$UNCHANGED$') → MLPRegressor[source]#

Configure whether metadata should be requested to be passed to the partial_fit method.

请注意，此方法仅在以下情况下相关：此估计器用作元估计器中的子估计器，并且通过 enable_metadata_routing=True 启用了元数据路由（请参阅 sklearn.set_config）。请查看用户指南以了解路由机制的工作原理。

每个参数的选项如下：

True: metadata is requested, and passed to partial_fit if provided. The request is ignored if metadata is not provided.
False: metadata is not requested and the meta-estimator will not pass it to partial_fit.
None：不请求元数据，如果用户提供元数据，元估计器将引发错误。
str：应将元数据以给定别名而不是原始名称传递给元估计器。

默认值 (sklearn.utils.metadata_routing.UNCHANGED) 保留现有请求。这允许您更改某些参数的请求而不更改其他参数。

在版本 1.3 中新增。

参数:

sample_weightstr, True, False, or None, default=sklearn.utils.metadata_routing.UNCHANGED: Metadata routing for sample_weight parameter in partial_fit.

返回: