{KgdZddlZddlmZddlmZdZdZdZ dZ d Z ee ee e d Z d Z d Zd ZdZe eeedZdZdZdZeeedZy)z(Utilities for the neural network modulesN)expit)xlogycy)zSimply 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. NXs `/home/alanp/www/video.onchill/myenv/lib/python3.12/site-packages/sklearn/neural_network/_base.pyinplace_identityr ct||y)zCompute the logistic function inplace. Parameters ---------- X : {array-like, sparse matrix}, shape (n_samples, n_features) The input data. outN)logistic_sigmoidrs r inplace_logisticrsQAr c2tj||y)zCompute the hyperbolic tan function inplace. Parameters ---------- X : {array-like, sparse matrix}, shape (n_samples, n_features) The input data. rN)nptanhrs r inplace_tanhr"sGGA1r c4tj|d|y)zCompute the rectified linear unit function inplace. Parameters ---------- X : {array-like, sparse matrix}, shape (n_samples, n_features) The input data. rrN)rmaximumrs r inplace_relur-sJJq!r c||jdddtjfz }tj||||j dddtjfz}y)zCompute the K-way softmax function inplace. Parameters ---------- X : {array-like, sparse matrix}, shape (n_samples, n_features) The input data. axisNr)maxrnewaxisexpsum)rtmps r inplace_softmaxr"8sT aeeemArzzM* *CFF3AAq"**} %%Ar )identityrlogisticrelusoftmaxcy)aApply 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. NrZdeltas r inplace_identity_derivativer+Nr r c||z}|d|z z}y)aApply 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. rNrr(s r inplace_logistic_derivativer-]s QJE QUNEr c|d|dzz z}y)aApply 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. rNrr(s r inplace_tanh_derivativer0ps QAXEr cd||dk(<y)aApply 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. rNrr(s r inplace_relu_derivativer2sE!q&Mr )r#rr$r%c4||z dzjdz S)aCompute 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. r/)mean)y_truey_preds r squared_lossr7s! f_ " ( ( *Q ..r ctj|jj}tj||d|z }|j ddk(rtj d|z |d}|j ddk(rtj d|z |d}t||j |j dz S)aCompute 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. rrr) rfinfodtypeepsclipshapeappendrr r5y_probr;s r log_lossrAs" ((6<< $ $C WWVS!c' *F ||A!1v:vA6 ||A!1v:vA6 && ! % % ' '&,,q/ 99r c tj|jj}tj||d|z }t ||j t d|z d|z j z |jdz S)a!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. rr)rr9r:r;r<rr r=r?s r binary_log_lossrCsz( ((6<< $ $C WWVS!c' *F   # # %a&j!f*(E(I(I(K KL ,,q/ r ) squared_errorrArC)__doc__numpyr scipy.specialrrrr rrrr" ACTIVATIONSr+r-r0r2 DERIVATIVESr7rArCLOSS_FUNCTIONSrr r rKs. 3 &!     &$&, #+ #  /&:8:"&r