2Vh,MddlZddlmZddlmZddlmZddlmZddlm Z ddlm Z ddlm Z dd lm Z dd lm Z dd lmZdd lmZed Gddej$ZedGddej$ZedGddej$ZedGddej$ZedGddej.ZedGddej$ZedGd d!ej$Zed"Gd#d$ej6Zd&d%Zy)'N) initializers)ops) keras_export)squeeze_or_expand_to_same_rank)log_cosh)mean_absolute_error)mean_absolute_percentage_error)mean_squared_error)mean_squared_logarithmic_error)reduction_metrics) normalizezkeras.metrics.MeanSquaredErrorc*eZdZdZdfd ZdZxZS)MeanSquaredErroraComputes the mean squared error between `y_true` and `y_pred`. Formula: ```python loss = mean(square(y_true - y_pred)) ``` Args: name: (Optional) string name of the metric instance. dtype: (Optional) data type of the metric result. Example: >>> m = keras.metrics.MeanSquaredError() >>> m.update_state([[0, 1], [0, 0]], [[1, 1], [0, 0]]) >>> m.result() 0.25 c@t|t||d|_y)N)fnnamedtypedown)super__init__r _directionselfrr __class__s T/home/dcms/DCMS/lib/python3.12/site-packages/keras/src/metrics/regression_metrics.pyrzMeanSquaredError.__init__%s .TG c4|j|jdSNrrrrs r get_configzMeanSquaredError.get_config* DJJ77r)r N__name__ __module__ __qualname____doc__rr! __classcell__rs@rrrs&! 8rrzkeras.metrics.MeanAbsoluteErrorc*eZdZdZdfd ZdZxZS)MeanAbsoluteErroraComputes the mean absolute error between the labels and predictions. Formula: ```python loss = mean(abs(y_true - y_pred)) ``` Args: name: (Optional) string name of the metric instance. dtype: (Optional) data type of the metric result. Examples: >>> m = keras.metrics.MeanAbsoluteError() >>> m.update_state([[0, 1], [0, 0]], [[1, 1], [0, 0]]) >>> m.result() 0.25 >>> m.reset_state() >>> m.update_state([[0, 1], [0, 0]], [[1, 1], [0, 0]], ... sample_weight=[1, 0]) >>> m.result() 0.5 Usage with `compile()` API: ```python model.compile( optimizer='sgd', loss='mse', metrics=[keras.metrics.MeanAbsoluteError()]) ``` c@t|t||d|_yNrr)rrrrrs rrzMeanAbsoluteError.__init__Ss ,d%@ rc4|j|jdSrrr s rr!zMeanAbsoluteError.get_configXr"r)rNr#r)s@rr+r+.!F! 8rr+z)keras.metrics.MeanAbsolutePercentageErrorc*eZdZdZdfd ZdZxZS)MeanAbsolutePercentageErrora)Computes mean absolute percentage error between `y_true` and `y_pred`. Formula: ```python loss = 100 * mean(abs((y_true - y_pred) / y_true)) ``` Args: name: (Optional) string name of the metric instance. dtype: (Optional) data type of the metric result. Examples: >>> m = keras.metrics.MeanAbsolutePercentageError() >>> m.update_state([[0, 1], [0, 0]], [[1, 1], [0, 0]]) >>> m.result() 250000000.0 >>> m.reset_state() >>> m.update_state([[0, 1], [0, 0]], [[1, 1], [0, 0]], ... sample_weight=[1, 0]) >>> m.result() 500000000.0 Usage with `compile()` API: ```python model.compile( optimizer='sgd', loss='mse', metrics=[keras.metrics.MeanAbsolutePercentageError()]) ``` c@t|t||d|_yr-)rrr rrs rrz$MeanAbsolutePercentageError.__init__ 7UK rc4|j|jdSrrr s rr!z&MeanAbsolutePercentageError.get_configr"r)r Nr#r)s@rr2r2\s D! 8rr2z)keras.metrics.MeanSquaredLogarithmicErrorc*eZdZdZdfd ZdZxZS)MeanSquaredLogarithmicErrora,Computes mean squared logarithmic error between `y_true` and `y_pred`. Formula: ```python loss = mean(square(log(y_true + 1) - log(y_pred + 1))) ``` Args: name: (Optional) string name of the metric instance. dtype: (Optional) data type of the metric result. Examples: >>> m = keras.metrics.MeanSquaredLogarithmicError() >>> m.update_state([[0, 1], [0, 0]], [[1, 1], [0, 0]]) >>> m.result() 0.12011322 >>> m.reset_state() >>> m.update_state([[0, 1], [0, 0]], [[1, 1], [0, 0]], ... sample_weight=[1, 0]) >>> m.result() 0.24022643 Usage with `compile()` API: ```python model.compile( optimizer='sgd', loss='mse', metrics=[keras.metrics.MeanSquaredLogarithmicError()]) ``` c@t|t||d|_yr-)rrr rrs rrz$MeanSquaredLogarithmicError.__init__r4rc4|j|jdSrrr s rr!z&MeanSquaredLogarithmicError.get_configr"r)r Nr#r)s@rr7r7r0rr7z"keras.metrics.RootMeanSquaredErrorc:eZdZdZdfd Zdfd ZfdZxZS)RootMeanSquaredErrora Computes root mean squared error metric between `y_true` and `y_pred`. Formula: ```python loss = sqrt(mean((y_pred - y_true) ** 2)) ``` Args: name: (Optional) string name of the metric instance. dtype: (Optional) data type of the metric result. Examples: >>> m = keras.metrics.RootMeanSquaredError() >>> m.update_state([[0, 1], [0, 0]], [[1, 1], [0, 0]]) >>> m.result() 0.5 >>> m.reset_state() >>> m.update_state([[0, 1], [0, 0]], [[1, 1], [0, 0]], ... sample_weight=[1, 0]) >>> m.result() 0.70710677 Usage with `compile()` API: ```python model.compile( optimizer='sgd', loss='mse', metrics=[keras.metrics.RootMeanSquaredError()]) ``` c6t|||d|_yr-)rrrrs rrzRootMeanSquaredError.__init__s U+ rctj||j}tj||j}t||\}}tj||z }t |||S)Accumulates root mean squared error statistics. Args: y_true: The ground truth values. y_pred: The predicted values. sample_weight: Optional weighting of each example. Can be a `Tensor` whose rank is either 0, or the same rank as `y_true`, and must be broadcastable to `y_true`. Defaults to `1`. Returns: Update op. ) sample_weight)rconvert_to_tensor_dtypersquarer update_state)ry_truey_predr?error_sqrs rrCz!RootMeanSquaredError.update_statesh&&vt{{;&&vt{{;7G::fvo.w#HM#JJrcFtjt| SN)rsqrtrresult)rrs rrJzRootMeanSquaredError.resultsxx())r)root_mean_squared_errorNrH)r$r%r&r'rrCrJr(r)s@rr;r;s!F! K(**rr;zkeras.metrics.CosineSimilarityc*eZdZdZdfd ZdZxZS)CosineSimilarityaComputes the cosine similarity between the labels and predictions. Formula: ```python loss = sum(l2_norm(y_true) * l2_norm(y_pred)) ``` 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) Defaults to `-1`. The dimension along which the cosine similarity is computed. Examples: >>> # 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 = keras.metrics.CosineSimilarity(axis=1) >>> m.update_state([[0., 1.], [1., 1.]], [[1., 0.], [1., 1.]]) >>> m.result() 0.49999997 >>> m.reset_state() >>> m.update_state([[0., 1.], [1., 1.]], [[1., 0.], [1., 1.]], ... sample_weight=[0.3, 0.7]) >>> m.result() 0.6999999 Usage with `compile()` API: ```python model.compile( optimizer='sgd', loss='mse', metrics=[keras.metrics.CosineSimilarity(axis=1)]) ``` cBt|t|||d|_y)N)raxisup)rrcosine_similarityr)rrrrOrs rrzCosineSimilarity.__init__(s! *DDIrc4|j|jdSrrr s rr!zCosineSimilarity.get_config-r"r)rQNr#r)s@rrMrMs+Z 8rrMzkeras.metrics.LogCoshErrorc*eZdZdZdfd ZdZxZS) LogCoshErrora;Computes the logarithm of the hyperbolic cosine of the prediction error. Formula: ```python error = y_pred - y_true logcosh = mean(log((exp(error) + exp(-error))/2), axis=-1) ``` Args: name: (Optional) string name of the metric instance. dtype: (Optional) data type of the metric result. Examples: >>> m = keras.metrics.LogCoshError() >>> m.update_state([[0, 1], [0, 0]], [[1, 1], [0, 0]]) >>> m.result() 0.10844523 >>> m.reset_state() >>> m.update_state([[0, 1], [0, 0]], [[1, 1], [0, 0]], ... sample_weight=[1, 0]) >>> m.result() 0.21689045 Usage with `compile()` API: ```python model.compile(optimizer='sgd', loss='mse', metrics=[keras.metrics.LogCoshError()]) ``` c@t|t||d|_yr-)rrrrrs rrzLogCoshError.__init__Vs 4u5 rc4|j|jdSrrr s rr!zLogCoshError.get_config[r"r)logcoshNr#r)s@rrUrU1r0rrUzkeras.metrics.R2ScorecPeZdZdZ dfd ZdZd dZdZdZfdZ xZ S) R2ScoreaComputes R2 score. Formula: ```python sum_squares_residuals = sum((y_true - y_pred) ** 2) sum_squares = sum((y_true - mean(y_true)) ** 2) R2 = 1 - sum_squares_residuals / sum_squares ``` 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 = keras.metrics.R2Score() >>> metric.update_state(y_true, y_pred) >>> result = metric.result() >>> result 0.57142854 c t|||d|_d}||vrtd|d||dkrtd|||_||_|j dtjd |_ d |_ y) NrrP)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_samples)shape initializerrF) rrr ValueErrorclass_aggregationnum_regressors add_variablerZerosr__built)rrcrdrrvalid_class_aggregation_valuesrs rrzR2Score.__init__s d%0* & $B B89://@.AC  A ,,:+;=  "3,,,$**,-   rct|dk7st|dk7rtd|d|d|d|dtd|d|d|d}|jd|gtj|_|jd |gtj|_|jd |gtj|_|jd |gtj|_d |_ y) NzcR2Score expects 2D inputs with shape (batch_size, output_dim). Received input shapes: y_pred.shape=z and y_true.shape=.rSzR2Score expects 2D inputs with shape (batch_size, output_dim), with output_dim fully defined (not None). Received input shapes: y_pred.shape= squared_sum)rr`rasumresidualcountT) lenrbrerrfrlrm total_mserorg)r y_true_shape y_pred_shape num_classess r_buildzR2Score._buildsL |  !S%6!%;((4~6 ,~Q0    #|B'7'?()5~6 ,~Q 0 #2& ,,-$**,-  $$-$**,%  **-$**,+  &&-$**,'   rc tj||j}tj||j}t||\}}|js&|j |j |j |d}tj||j}t|j dk(rtj|d}tj|tj |}|tj||jz}|jj|jtj|dz|jj|jtj||zdz|jj|jtj||z dztj||jzdz|j j|j tj|dz|j"j|j"tj$|zy)r>r.NrOrrj)rr@rArrgrur`rrp expand_dims broadcast_tocastrmassignrlrqror_size)rrDrEr?weighted_y_trues rrCzR2Score.update_states&&vT[[A&&vT[[A7G{{ KK fll 3  M--m4::N }"" #q (OOMBM(( &8IJ  388M6<<#HH 377?#CCD    swwv'?aH H   NNgg&Q&-)NN   $**sww}1'EEF  0 0388F3C CDrcV|j|jz }|j|j|zz }d|j|z z }t j t j |d|}|jdk(rt j|}nD|jdk(r3t j||z}t j|}||z }n|}|jdk7r>|j|jdz kDrtjdd|S|j|jdz k(rtjd d|St j|jd }t j|jd }t jt jd |t j|d } t jt j||d } t jd t j | | }|S) Nrwgr\r]rzdMore independent predictors than datapoints in adjusted R2 score. Falling back to standard R2 score.rj) stacklevelzIDivision by zero in Adjusted R2 score. Falling back to standard R2 score.float32r.g?)rmrorlrqrwhereisinfrcmeanrdr_warningswarnr@multiplysubtractdivide) rrtotal raw_scoresr2_score weighted_sumsum_of_weightsnpnumdens rrJzR2Score.resultsxx$**$  488d?2$..501 YYsyy4c:F  ! !%6 6xx +H  # #'B B775:#56L WWU^N#n4H!H   ! #""T%5%5%99 O &$$(8(81(<< 9 ))$*:*:)L))$*=*=YOllLLh/a1Ell3<<1#5s;<<SZZS-ABrc|jD]<}|jtj|j|j >y)Nr.) variablesr|rzerosr`r)rvs r reset_statezR2Score.reset_state4s4 8A HHSYYqwwagg6 7 8rc|j|j|j|jd}t|}i||S)N)rrrcrd)rrrcrdrr!)rconfig base_configrs rr!zR2Score.get_config8sIIIZZ!%!7!7"11   g(* (+(((r)r\rrNrH) r$r%r&r'rrurCrJrr!r(r)s@rrZrZ`s?0h,  #J%N,E\$L8))rrZctj|}tj||j}t||\}}t ||}t ||}tj ||z|S)aNComputes the cosine similarity between labels and predictions. Formula: ```python loss = sum(l2_norm(y_true) * l2_norm(y_pred)) ``` Args: y_true: Tensor of true targets. y_pred: Tensor of predicted targets. axis: Axis along which to determine similarity. Defaults to `-1`. Returns: Cosine similarity tensor. Example: >>> y_true = [[0., 1.], [1., 1.], [1., 1.]] >>> y_pred = [[1., 0.], [1., 1.], [-1., -1.]] >>> loss = keras.losses.cosine_similarity(y_true, y_pred, axis=-1) [0., 0.99999994, -0.99999994] r.rx)rr@rrr rm)rDrErOs rrQrQCsg0 " "6 *F  " "6 >F3FFCNFF vD )F vD )F 776F? ..r)rS)r keras.srcrrkeras.src.api_exportrkeras.src.losses.lossrkeras.src.losses.lossesrrr r r keras.src.metricsr keras.src.utils.numerical_utilsr MeanMetricWrapperrr+r2r7Meanr;rMrUMetricrZrQr^rrrsx"-@,7B6B/5./8(::808:/0*8);;*81*8Z9:)8"3"E"E)8;)8X9:*8"3"E"E*8;*8Z23>*,11>*4>*B./48(::48048n*+*8$66*8,*8\%&_)&&_)'_)D/r