U 3d@sdZddlZddlmZddlmZddZddZd d Z d d Z d dZ ee ee e dZ ddZ ddZddZddZe eeedZddZddZddZeeedZdS) z)Utilities for the neural network modules N)expit)xlogycCsdS)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. NXrr@/tmp/pip-unpacked-wheel-zrfo1fqw/sklearn/neural_network/_base.pyinplace_identity srcCst||ddS)zCompute the logistic function inplace. Parameters ---------- X : {array-like, sparse matrix}, shape (n_samples, n_features) The input data. outN)logistic_sigmoidrrrrinplace_logisticsr cCstj||ddS)zCompute the hyperbolic tan function inplace. Parameters ---------- X : {array-like, sparse matrix}, shape (n_samples, n_features) The input data. r N)nptanhrrrr inplace_tanh$srcCstj|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)r maximumrrrr inplace_relu/srcCsN||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. ZaxisNr )maxr Znewaxisexpsum)rtmprrrinplace_softmax:sr)identityrlogisticreluZsoftmaxcCsdS)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_derivativePsrcCs||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. rNrrrrrinplace_logistic_derivative_sr 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. rNrrrrrinplace_tanh_derivativersr"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. rNrrrrrinplace_relu_derivativesr#)rrrrcCs||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. Returns ------- loss : float The degree to which the samples are correctly predicted. r!)Zmean)y_trueZy_predrrr squared_losssr%cCs~t|jj}t||d|}|jddkrBtjd||dd}|jddkrdtjd||dd}t|| |jdS)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) r finfodtypeepsclipshapeappendrrr$Zy_probr(rrrlog_losssr-cCsPt|jj}t||d|}t||td|d| |jdS)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)r r&r'r(r)rrr*r,rrrbinary_log_losss $r.)Z squared_errorr-r.)__doc__Znumpyr Z scipy.specialrr rrr rrrZ ACTIVATIONSrr r"r#Z DERIVATIVESr%r-r.ZLOSS_FUNCTIONSrrrrs<