3RNN/Lib/site-packages/sklearn/neural_network/_base.py
2024-05-26 19:49:15 +02:00

236 lines
6.2 KiB
Python

"""Utilities for the neural network modules"""
# Author: Issam H. Laradji <issam.laradji@gmail.com>
# License: BSD 3 clause
import numpy as np
from scipy.special import expit as logistic_sigmoid
from scipy.special import xlogy
def inplace_identity(X):
"""Simply leave the input array unchanged.
Parameters
----------
X : {array-like, sparse matrix}, shape (n_samples, n_features)
Data, where `n_samples` is the number of samples
and `n_features` is the number of features.
"""
# Nothing to do
def inplace_logistic(X):
"""Compute the logistic function inplace.
Parameters
----------
X : {array-like, sparse matrix}, shape (n_samples, n_features)
The input data.
"""
logistic_sigmoid(X, out=X)
def inplace_tanh(X):
"""Compute the hyperbolic tan function inplace.
Parameters
----------
X : {array-like, sparse matrix}, shape (n_samples, n_features)
The input data.
"""
np.tanh(X, out=X)
def inplace_relu(X):
"""Compute the rectified linear unit function inplace.
Parameters
----------
X : {array-like, sparse matrix}, shape (n_samples, n_features)
The input data.
"""
np.maximum(X, 0, out=X)
def inplace_softmax(X):
"""Compute the K-way softmax function inplace.
Parameters
----------
X : {array-like, sparse matrix}, shape (n_samples, n_features)
The input data.
"""
tmp = X - X.max(axis=1)[:, np.newaxis]
np.exp(tmp, out=X)
X /= X.sum(axis=1)[:, np.newaxis]
ACTIVATIONS = {
"identity": inplace_identity,
"tanh": inplace_tanh,
"logistic": inplace_logistic,
"relu": inplace_relu,
"softmax": inplace_softmax,
}
def inplace_identity_derivative(Z, delta):
"""Apply the derivative of the identity function: do nothing.
Parameters
----------
Z : {array-like, sparse matrix}, shape (n_samples, n_features)
The data which was output from the identity activation function during
the forward pass.
delta : {array-like}, shape (n_samples, n_features)
The backpropagated error signal to be modified inplace.
"""
# Nothing to do
def inplace_logistic_derivative(Z, delta):
"""Apply the derivative of the logistic sigmoid function.
It exploits the fact that the derivative is a simple function of the output
value from logistic function.
Parameters
----------
Z : {array-like, sparse matrix}, shape (n_samples, n_features)
The data which was output from the logistic activation function during
the forward pass.
delta : {array-like}, shape (n_samples, n_features)
The backpropagated error signal to be modified inplace.
"""
delta *= Z
delta *= 1 - Z
def inplace_tanh_derivative(Z, delta):
"""Apply the derivative of the hyperbolic tanh function.
It exploits the fact that the derivative is a simple function of the output
value from hyperbolic tangent.
Parameters
----------
Z : {array-like, sparse matrix}, shape (n_samples, n_features)
The data which was output from the hyperbolic tangent activation
function during the forward pass.
delta : {array-like}, shape (n_samples, n_features)
The backpropagated error signal to be modified inplace.
"""
delta *= 1 - Z**2
def inplace_relu_derivative(Z, delta):
"""Apply the derivative of the relu function.
It exploits the fact that the derivative is a simple function of the output
value from rectified linear units activation function.
Parameters
----------
Z : {array-like, sparse matrix}, shape (n_samples, n_features)
The data which was output from the rectified linear units activation
function during the forward pass.
delta : {array-like}, shape (n_samples, n_features)
The backpropagated error signal to be modified inplace.
"""
delta[Z == 0] = 0
DERIVATIVES = {
"identity": inplace_identity_derivative,
"tanh": inplace_tanh_derivative,
"logistic": inplace_logistic_derivative,
"relu": inplace_relu_derivative,
}
def squared_loss(y_true, y_pred):
"""Compute the squared loss for regression.
Parameters
----------
y_true : array-like or label indicator matrix
Ground truth (correct) values.
y_pred : array-like or label indicator matrix
Predicted values, as returned by a regression estimator.
Returns
-------
loss : float
The degree to which the samples are correctly predicted.
"""
return ((y_true - y_pred) ** 2).mean() / 2
def log_loss(y_true, y_prob):
"""Compute Logistic loss for classification.
Parameters
----------
y_true : array-like or label indicator matrix
Ground truth (correct) labels.
y_prob : array-like of float, shape = (n_samples, n_classes)
Predicted probabilities, as returned by a classifier's
predict_proba method.
Returns
-------
loss : float
The degree to which the samples are correctly predicted.
"""
eps = np.finfo(y_prob.dtype).eps
y_prob = np.clip(y_prob, eps, 1 - eps)
if y_prob.shape[1] == 1:
y_prob = np.append(1 - y_prob, y_prob, axis=1)
if y_true.shape[1] == 1:
y_true = np.append(1 - y_true, y_true, axis=1)
return -xlogy(y_true, y_prob).sum() / y_prob.shape[0]
def binary_log_loss(y_true, y_prob):
"""Compute binary logistic loss for classification.
This is identical to log_loss in binary classification case,
but is kept for its use in multilabel case.
Parameters
----------
y_true : array-like or label indicator matrix
Ground truth (correct) labels.
y_prob : array-like of float, shape = (n_samples, 1)
Predicted probabilities, as returned by a classifier's
predict_proba method.
Returns
-------
loss : float
The degree to which the samples are correctly predicted.
"""
eps = np.finfo(y_prob.dtype).eps
y_prob = np.clip(y_prob, eps, 1 - eps)
return (
-(xlogy(y_true, y_prob).sum() + xlogy(1 - y_true, 1 - y_prob).sum())
/ y_prob.shape[0]
)
LOSS_FUNCTIONS = {
"squared_error": squared_loss,
"log_loss": log_loss,
"binary_log_loss": binary_log_loss,
}