o Z&iN @sdZddlZddlmZddlmZddZddZd d Z d d Z d dZ ddZ eee e e e dZ ddZddZddZddZeeeedZd$ddZd$ddZd$dd Zd$d!d"Zeeeed#ZdS)%z(Utilities for the neural network modulesN)expit)xlogycCdS)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. NXrrGC:\wamp64\www\opt\env\Lib\site-packages\sklearn/neural_network/_base.pyinplace_identity r cCtj||ddS)zCompute the exponential inplace. Parameters ---------- X : {array-like, sparse matrix}, shape (n_samples, n_features) The input data. outN)npexprrrr inplace_exprcCst||ddS)zCompute the logistic function inplace. Parameters ---------- X : {array-like, sparse matrix}, shape (n_samples, n_features) The input data. r N)logistic_sigmoidrrrrinplace_logistic"srcCr )zCompute the hyperbolic tan function inplace. Parameters ---------- X : {array-like, sparse matrix}, shape (n_samples, n_features) The input data. r N)rtanhrrrr inplace_tanh-rrcCstj|d|ddS)zCompute the rectified linear unit function inplace. Parameters ---------- X : {array-like, sparse matrix}, shape (n_samples, n_features) The input data. rr N)rmaximumrrrr inplace_relu8srcCsN||jddddtjf}tj||d||jddddtjf}dS)zCompute the K-way softmax function inplace. Parameters ---------- X : {array-like, sparse matrix}, shape (n_samples, n_features) The input data. axisNr )maxrZnewaxisrsum)rtmprrrinplace_softmaxCs"r)identityrrlogisticreluZsoftmaxcCr)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. NrZdeltarrrinplace_identity_derivativeZr r%cCs||9}|d|9}dS)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"rrrinplace_logistic_derivativeisr&cCs|d|d9}dS)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"rrrinplace_tanh_derivative|sr(cCsd||dk<dS)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"rrrinplace_relu_derivativesr))rrr r!cCs dtj||d|ddS)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. sample_weight : array-like of shape (n_samples,), default=None Sample weights. Returns ------- loss : float The degree to which the samples are correctly predicted. g?r'rweightsr)raveragemeany_trueZy_pred sample_weightrrr squared_losssr1cCs&tjt||||||ddS)aCompute (half of the) Poisson deviance loss for regression. Parameters ---------- y_true : array-like or label indicator matrix Ground truth (correct) labels. y_pred : array-like or label indicator matrix Predicted values, as returned by a regression estimator. sample_weight : array-like of shape (n_samples,), default=None Sample weights. Returns ------- loss : float The degree to which the samples are correctly predicted. rr*)rr,rrr.rrr poisson_losss r2cCst|jj}t||d|}|jddkr!tjd||dd}|jddkr2tjd||dd}tjt|||dd S)a 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. sample_weight : array-like of shape (n_samples,), default=None Sample weights. Returns ------- loss : float The degree to which the samples are correctly predicted. rrrr*) rfinfodtypeepsclipshapeappendr,rrr/Zy_probr0r5rrrlog_losssr:cCsNt|jj}t||d|}tjt||td|d||dd 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. sample_weight : array-like of shape (n_samples,), default=None Sample weights. Returns ------- loss : float The degree to which the samples are correctly predicted. rrr*)rr3r4r5r6r,rrr9rrrbinary_log_losssr;)Z squared_errorZpoissonr:r;)N)__doc__numpyrZ scipy.specialrrrr rrrrrZ ACTIVATIONSr%r&r(r)Z DERIVATIVESr1r2r:r;ZLOSS_FUNCTIONSrrrrsF            !