0hjRdZddlZddlmcmZddlmZddlm Z ddl m Z ddl m Z ddl mZddl mZdd l mZdd lmZdd lmZdd lmZdd lmZddlmZedGddej4ZedGddej8ZedGddej8ZedGddej8ZedGddej8Z edGdd ej8Z!ed!Gd"d#ej4Z"ed$Gd%d&ej8Z#ed'Gd(d)ejHZ%d+d*Z&y),z%Regression metrics, e.g. MAE/MSE/etc.N)backend)utils)logcosh)mean_absolute_error)mean_absolute_percentage_error)mean_squared_error)mean_squared_logarithmic_error) base_metric) losses_utils) metrics_utils)is_tensor_or_variable) keras_exportzkeras.metrics.MeanRelativeErrorcXeZdZdZej dfd Zdfd ZfdZxZ S)MeanRelativeErroraComputes the mean relative error by normalizing with the given values. This metric creates two local variables, `total` and `count` that are used to compute the mean relative error. This is weighted by `sample_weight`, and it is ultimately returned as `mean_relative_error`: an idempotent operation that simply divides `total` by `count`. If `sample_weight` is `None`, weights default to 1. Use `sample_weight` of 0 to mask values. Args: normalizer: The normalizer values with same shape as predictions. name: (Optional) string name of the metric instance. dtype: (Optional) data type of the metric result. Standalone usage: >>> m = tf.keras.metrics.MeanRelativeError(normalizer=[1, 3, 2, 3]) >>> m.update_state([1, 3, 2, 3], [2, 4, 6, 8]) >>> # metric = mean(|y_pred - y_true| / normalizer) >>> # = mean([1, 1, 4, 5] / [1, 3, 2, 3]) = mean([1, 1/3, 2, 5/3]) >>> # = 5/4 = 1.25 >>> m.result().numpy() 1.25 Usage with `compile()` API: ```python model.compile( optimizer='sgd', loss='mse', metrics=[tf.keras.metrics.MeanRelativeError(normalizer=[1, 3])]) ``` cvt|||tj||j}||_y)Nnamedtype)super__init__tfcast_dtype normalizer)selfrrr __class__s a/var/www/html/engine/venv/lib/python3.12/site-packages/tf_keras/src/metrics/regression_metrics.pyrzMeanRelativeError.__init__Ks0 d%0WWZ5 $c.tj||j}tj||j}tj||g|\\}}}t j ||\}}t j||j\}|_|jj|jtjjtj||z |j}t|=||S)aAccumulates metric statistics. Args: y_true: The ground truth values. y_pred: The predicted values. sample_weight: Optional weighting of each example. Can be a `Tensor` whose rank is either 0, or the same rank as `y_true`, and must be broadcastable to `y_true`. Defaults to `1`. Returns: Update op.  sample_weight)rrrr ,ragged_assert_compatible_and_get_flat_valuesr squeeze_or_expand_dimensionsremove_squeezable_dimensionsrshapeassert_is_compatible_withmath divide_no_nanabsr update_state)ry_truey_predr!relative_errorsrs rr*zMeanRelativeError.update_stateQs--)UU V m     &BB F #/"K"K DOO#   ..v||<''// FF6F? #T__ w# =$  rc|j}dt|rtj|n|i}t|}t t|jt|jzS)Nr) rr revalr get_configdictlistitems)rnconfig base_configrs rr0zMeanRelativeError.get_configvsb OO -B1-E',,q/1 g(* D**,-V\\^0DDEEr)NNN) __name__ __module__ __qualname____doc__ dtensor_utils inject_meshrr*r0 __classcell__rs@rrr%s5"H%% # JFFrrzkeras.metrics.CosineSimilaritycBeZdZdZej dfd ZxZS)CosineSimilarityaComputes the cosine similarity between the labels and predictions. `cosine similarity = (a . b) / ||a|| ||b||` See: [Cosine Similarity](https://en.wikipedia.org/wiki/Cosine_similarity). This metric keeps the average cosine similarity between `predictions` and `labels` over a stream of data. Args: name: (Optional) string name of the metric instance. dtype: (Optional) data type of the metric result. axis: (Optional) The dimension along which the cosine similarity is computed. Defaults to `-1`. Standalone usage: >>> # l2_norm(y_true) = [[0., 1.], [1./1.414, 1./1.414]] >>> # l2_norm(y_pred) = [[1., 0.], [1./1.414, 1./1.414]] >>> # l2_norm(y_true) . l2_norm(y_pred) = [[0., 0.], [0.5, 0.5]] >>> # result = mean(sum(l2_norm(y_true) . l2_norm(y_pred), axis=1)) >>> # = ((0. + 0.) + (0.5 + 0.5)) / 2 >>> m = tf.keras.metrics.CosineSimilarity(axis=1) >>> m.update_state([[0., 1.], [1., 1.]], [[1., 0.], [1., 1.]]) >>> m.result().numpy() 0.49999997 >>> m.reset_state() >>> m.update_state([[0., 1.], [1., 1.]], [[1., 0.], [1., 1.]], ... sample_weight=[0.3, 0.7]) >>> m.result().numpy() 0.6999999 Usage with `compile()` API: ```python model.compile( optimizer='sgd', loss='mse', metrics=[tf.keras.metrics.CosineSimilarity(axis=1)]) ``` c4t|t|||y)N)raxis)rrcosine_similarity)rrrrCrs rrzCosineSimilarity.__init__s *DDIr)rDNr8r9r:r;r<r=rr>r?s@rrArAs%)VJJrrAzkeras.metrics.MeanAbsoluteErrorcBeZdZdZej dfd ZxZS)MeanAbsoluteErroraComputes the mean absolute error between the labels and predictions. Args: name: (Optional) string name of the metric instance. dtype: (Optional) data type of the metric result. Standalone usage: >>> m = tf.keras.metrics.MeanAbsoluteError() >>> m.update_state([[0, 1], [0, 0]], [[1, 1], [0, 0]]) >>> m.result().numpy() 0.25 >>> m.reset_state() >>> m.update_state([[0, 1], [0, 0]], [[1, 1], [0, 0]], ... sample_weight=[1, 0]) >>> m.result().numpy() 0.5 Usage with `compile()` API: ```python model.compile( optimizer='sgd', loss='mse', metrics=[tf.keras.metrics.MeanAbsoluteError()]) ``` c2t|t||yNr)rrrrrrrs rrzMeanAbsoluteError.__init__s ,d%@r)rNrFr?s@rrHrHs$:AArrHz)keras.metrics.MeanAbsolutePercentageErrorcBeZdZdZej dfd ZxZS)MeanAbsolutePercentageErroraComputes the mean absolute percentage error between `y_true` and `y_pred`. Args: name: (Optional) string name of the metric instance. dtype: (Optional) data type of the metric result. Standalone usage: >>> m = tf.keras.metrics.MeanAbsolutePercentageError() >>> m.update_state([[0, 1], [0, 0]], [[1, 1], [0, 0]]) >>> m.result().numpy() 250000000.0 >>> m.reset_state() >>> m.update_state([[0, 1], [0, 0]], [[1, 1], [0, 0]], ... sample_weight=[1, 0]) >>> m.result().numpy() 500000000.0 Usage with `compile()` API: ```python model.compile( optimizer='sgd', loss='mse', metrics=[tf.keras.metrics.MeanAbsolutePercentageError()]) ``` c2t|t||yrJ)rrrrLs rrz$MeanAbsolutePercentageError.__init__ 7UKr)rNrFr?s@rrNrN$<LLrrNzkeras.metrics.MeanSquaredErrorcBeZdZdZej dfd ZxZS)MeanSquaredErroraComputes the mean squared error between `y_true` and `y_pred`. Args: name: (Optional) string name of the metric instance. dtype: (Optional) data type of the metric result. Standalone usage: >>> m = tf.keras.metrics.MeanSquaredError() >>> m.update_state([[0, 1], [0, 0]], [[1, 1], [0, 0]]) >>> m.result().numpy() 0.25 >>> m.reset_state() >>> m.update_state([[0, 1], [0, 0]], [[1, 1], [0, 0]], ... sample_weight=[1, 0]) >>> m.result().numpy() 0.5 Usage with `compile()` API: ```python model.compile( optimizer='sgd', loss='mse', metrics=[tf.keras.metrics.MeanSquaredError()]) ``` c2t|t||yrJ)rrrrLs rrzMeanSquaredError.__init__s +T?r)rNrFr?s@rrSrSs$:@@rrSz)keras.metrics.MeanSquaredLogarithmicErrorcBeZdZdZej dfd ZxZS)MeanSquaredLogarithmicErroraComputes the mean squared logarithmic error between `y_true` and `y_pred`. Args: name: (Optional) string name of the metric instance. dtype: (Optional) data type of the metric result. Standalone usage: >>> m = tf.keras.metrics.MeanSquaredLogarithmicError() >>> m.update_state([[0, 1], [0, 0]], [[1, 1], [0, 0]]) >>> m.result().numpy() 0.12011322 >>> m.reset_state() >>> m.update_state([[0, 1], [0, 0]], [[1, 1], [0, 0]], ... sample_weight=[1, 0]) >>> m.result().numpy() 0.24022643 Usage with `compile()` API: ```python model.compile( optimizer='sgd', loss='mse', metrics=[tf.keras.metrics.MeanSquaredLogarithmicError()]) ``` c2t|t||yrJ)rrr rLs rrz$MeanSquaredLogarithmicError.__init__>rPr)r NrFr?s@rrVrVrQrrVz"keras.metrics.RootMeanSquaredErrorcTeZdZdZej dfd Zdfd ZdZxZ S)RootMeanSquaredErroraSComputes root mean squared error metric between `y_true` and `y_pred`. Standalone usage: >>> m = tf.keras.metrics.RootMeanSquaredError() >>> m.update_state([[0, 1], [0, 0]], [[1, 1], [0, 0]]) >>> m.result().numpy() 0.5 >>> m.reset_state() >>> m.update_state([[0, 1], [0, 0]], [[1, 1], [0, 0]], ... sample_weight=[1, 0]) >>> m.result().numpy() 0.70710677 Usage with `compile()` API: ```python model.compile( optimizer='sgd', loss='mse', metrics=[tf.keras.metrics.RootMeanSquaredError()]) ``` c(t|||yrJ)rrrLs rrzRootMeanSquaredError.__init__^s U+rctj||j}tj||j}tj||\}}tj j ||}t|!||S)aAccumulates root mean squared error statistics. Args: y_true: The ground truth values. y_pred: The predicted values. sample_weight: Optional weighting of each example. Can be a `Tensor` whose rank is either 0, or the same rank as `y_true`, and must be broadcastable to `y_true`. Defaults to `1`. Returns: Update op. r ) rrrr r#r'squared_differencerr*)rr+r,r!error_sqrs rr*z!RootMeanSquaredError.update_statebss--%BB F 77--ff=w#HM#JJrctjtjj|j|j Sr7)rsqrtr'r(totalcount)rs rresultzRootMeanSquaredError.resultws*wwrww,,TZZDEEr)root_mean_squared_errorNr7) r8r9r:r;r<r=rr*rbr>r?s@rrYrYCs.2,,K*FrrYzkeras.metrics.LogCoshErrorcBeZdZdZej dfd ZxZS) LogCoshErrora,Computes the logarithm of the hyperbolic cosine of the prediction error. `logcosh = log((exp(x) + exp(-x))/2)`, where x is the error (y_pred - y_true) Args: name: (Optional) string name of the metric instance. dtype: (Optional) data type of the metric result. Standalone usage: >>> m = tf.keras.metrics.LogCoshError() >>> m.update_state([[0, 1], [0, 0]], [[1, 1], [0, 0]]) >>> m.result().numpy() 0.10844523 >>> m.reset_state() >>> m.update_state([[0, 1], [0, 0]], [[1, 1], [0, 0]], ... sample_weight=[1, 0]) >>> m.result().numpy() 0.21689045 Usage with `compile()` API: ```python model.compile(optimizer='sgd', loss='mse', metrics=[tf.keras.metrics.LogCoshError()]) ``` c2t|t||yrJ)rrrrLs rrzLogCoshError.__init__s $e4r)rNrFr?s@rrere{s">55rrezkeras.metrics.R2ScorecneZdZdZej dfd ZdZd dZdZ dZ fdZ xZ S) R2Scorea.Computes R2 score. This is also called the [coefficient of determination](https://en.wikipedia.org/wiki/Coefficient_of_determination). It indicates how close the fitted regression line is to ground-truth data. - The highest score possible is 1.0. It indicates that the predictors perfectly accounts for variation in the target. - A score of 0.0 indicates that the predictors do not account for variation in the target. - It can also be negative if the model is worse than random. This metric can also compute the "Adjusted R2" score. Args: class_aggregation: Specifies how to aggregate scores corresponding to different output classes (or target dimensions), i.e. different dimensions on the last axis of the predictions. Equivalent to `multioutput` argument in Scikit-Learn. Should be one of `None` (no aggregation), `"uniform_average"`, `"variance_weighted_average"`. num_regressors: Number of independent regressors used ("Adjusted R2" score). 0 is the standard R2 score. Defaults to `0`. name: Optional. string name of the metric instance. dtype: Optional. data type of the metric result. Example: >>> y_true = np.array([[1], [4], [3]], dtype=np.float32) >>> y_pred = np.array([[2], [4], [4]], dtype=np.float32) >>> metric = tf.keras.metrics.R2Score() >>> metric.update_state(y_true, y_pred) >>> result = metric.result() >>> result.numpy() 0.57142854 ct|||d}||vrtd|d||dkrtd|||_||_|j dd|_d |_y) Nr)Nuniform_averagevariance_weighted_averagez@Invalid value for argument `class_aggregation`. Expected one of z. Received: class_aggregation=rz]Invalid value for argument `num_regressors`. Expected a value >= 0. Received: num_regressors= num_samplesint32F)rr ValueErrorclass_aggregationnum_regressors add_weightrlbuilt)rrorprrvalid_class_aggregation_valuesrs rrzR2Score.__init__s d%0* & $B B89://@.AC  A ,,:+;=  "3,?? W?M rct|dk7st|dk7rtd|d|d|d|dtd|d|d|d}|jd|gd |_|jd |gd |_|jd |gd |_|jd |gd |_d |_y)NzcR2Score expects 2D inputs with shape (batch_size, output_dim). Received input shapes: y_pred.shape=z and y_true.shape=.rEzR2Score expects 2D inputs with shape (batch_size, output_dim), with output_dim fully defined (not None). Received input shapes: y_pred.shape= squared_sumzeros)rr% initializersumresidualraT)lenrnrqrwrz total_mserarr)r y_true_shape y_pred_shape num_classess rbuildz R2Score.builds  |  !S%6!%;((4~6 ,~Q0    #|B'7'?()5~6 ,~Q 0 #2& ??-+  ??-#  -)  __-%   rctj||j}tj||j}|js&|j |j |j |d}tj||j}|j j dk(rtj|d}tjjj||}||z}|jjtj|d|jjtj||zd|jjtj||z dz|zd|j jtj|d|j"jtj$|y)NrKrC)weightsvaluesrru)rconvert_to_tensorrrrrr%rank expand_dims __internal__opsbroadcast_weightsrz assign_add reduce_sumrwr}rarlsize)rr+r,r!weighted_y_trues rr*zR2Score.update_stateso%%fDJJ?%%fDJJ?zz JJv||V\\ 2  M,,]$**M    # #q (NN=qAM++==!&> !=0 BMM/BC ## MM&?2 ;  !! MM6F?q0=@q I  bmmMBC ##BGGFO4rc|j|jz }|j|j|zz }d|j|z z }t j tj j|d|}|jdk(rt j|}nD|jdk(r3t j||z}t j|}||z }n|}|jdk7rZ|j|jdz kDrtjdd|S|j|jdz k(rtjd d|St j|jtj }t j|jtj }t j"t j$d |t j$|d } t j$t j$||d } t j$d t j&| | }|S) NrgrjrkrzdMore independent predictors than datapoints in adjusted R2 score. Falling back to standard R2 score.ru) stacklevelzIDivision by zero in Adjusted R2 score. Falling back to standard R2 score.rKg?)rzrarwr}rwherer'is_infro reduce_meanrrprlwarningswarnrfloat32multiplysubtractdivide) rmeanr` raw_scoresr2_score weighted_sumsum_of_weightsr4pnumdens rrbzR2Score.result1sxx$**$  488d?2$..501 XXbggnnZ8#zJ  ! !%6 6~~j1H  # #'B B==);yrJ) variablesassignrrxr%r)rvs r reset_statezR2Score.reset_stateWs4 7A HHRXXaggQWW5 6 7rc^|j|jd}t| }i||S)N)rorp)rorprr0)rr5r6rs rr0zR2Score.get_config[s;!%!7!7"11 g(* (+(((r)rjrrNr7) r8r9r:r;r<r=rrr*rbrr0r>r?s@rrhrhsQ(T,  >%N58$L7))rrhctjj||}tjj||}tj||z|S)a;Computes the cosine similarity between labels and predictions. Args: y_true: The ground truth values. y_pred: The prediction values. axis: (Optional) -1 is the dimension along which the cosine similarity is computed. Defaults to `-1`. Returns: Cosine similarity value. r)rlinalg l2_normalizer)r+r,rCs rrDrDdsKYY # #F # 6F YY # #F # 6F ==&t 44r)rE)'r;rtensorflow.compat.v2compatv2r tf_keras.srcrtf_keras.src.dtensorrr<tf_keras.src.lossesrrrrr tf_keras.src.metricsr tf_keras.src.utilsr r tf_keras.src.utils.tf_utilsr tensorflow.python.util.tf_exportrMeanrMeanMetricWrapperrArHrNrSrVrYreMetricrhrDrrrs,!! 7'3>2>,+,=:/0VF ((VF1VFr./.J{44.J0.Jb/0 A 55 A1 AF9:!L+"?"?!L;!LH./ @{44 @0 @F9:!L+"?"?!L;!LH234F;++4F44Fn*+"5;00"5,"5L%&~)k  ~)'~)B5r