B \)O@sdZddlmZddlZddlmZmZddlmZddl m Z dd d d d d gZ ddZ dddZ ddd Zddd Zdd Zddd Zddd ZdS)zMetrics to assess performance on regression task Functions named as ``*_score`` return a scalar value to maximize: the higher the better Function named as ``*_error`` or ``*_loss`` return a scalar value to minimize: the lower the better )divisionN) check_arraycheck_consistent_length) column_or_1d) string_typesmean_absolute_errormean_squared_errormean_squared_log_errormedian_absolute_errorr2_scoreexplained_variance_scorecCst||t|dd}t|dd}|jdkr6|d}|jdkrJ|d}|jd|jdkrztd|jd|jd|jd}d}t|tr||krtd||nF|dk rt|dd}|dkrtd n |t |krtd t ||f|dkrd nd }||||fS) aCheck that y_true and y_pred belong to the same regression task Parameters ---------- y_true : array-like y_pred : array-like multioutput : array-like or string in ['raw_values', uniform_average', 'variance_weighted'] or None None is accepted due to backward compatibility of r2_score(). Returns ------- type_true : one of {'continuous', continuous-multioutput'} The type of the true target data, as output by 'utils.multiclass.type_of_target' y_true : array-like of shape = (n_samples, n_outputs) Ground truth (correct) target values. y_pred : array-like of shape = (n_samples, n_outputs) Estimated target values. multioutput : array-like of shape = (n_outputs) or string in ['raw_values', uniform_average', 'variance_weighted'] or None Custom output weights if ``multioutput`` is array-like or just the corresponding argument if ``multioutput`` is a correct keyword. F)Z ensure_2d)rz`. Parameters ---------- y_true : array-like of shape = (n_samples) or (n_samples, n_outputs) Ground truth (correct) target values. y_pred : array-like of shape = (n_samples) or (n_samples, n_outputs) Estimated target values. sample_weight : array-like of shape = (n_samples), optional Sample weights. multioutput : string in ['raw_values', 'uniform_average'] or array-like of shape (n_outputs) Defines aggregating of multiple output values. Array-like value defines weights used to average errors. 'raw_values' : Returns a full set of errors in case of multioutput input. 'uniform_average' : Errors of all outputs are averaged with uniform weight. Returns ------- loss : float or ndarray of floats If multioutput is 'raw_values', then mean absolute error is returned for each output separately. If multioutput is 'uniform_average' or an ndarray of weights, then the weighted average of all output errors is returned. MAE output is non-negative floating point. The best value is 0.0. Examples -------- >>> from sklearn.metrics import mean_absolute_error >>> y_true = [3, -0.5, 2, 7] >>> y_pred = [2.5, 0.0, 2, 8] >>> mean_absolute_error(y_true, y_pred) 0.5 >>> y_true = [[0.5, 1], [-1, 1], [7, -6]] >>> y_pred = [[0, 2], [-1, 2], [8, -5]] >>> mean_absolute_error(y_true, y_pred) 0.75 >>> mean_absolute_error(y_true, y_pred, multioutput='raw_values') array([0.5, 1. ]) >>> mean_absolute_error(y_true, y_pred, multioutput=[0.3, 0.7]) ... # doctest: +ELLIPSIS 0.85... r)weightsaxisrrN)r )rrnpaverageabsrr)rr sample_weightrr output_errorsrrrrps9   cCsht|||\}}}}t|||tj||dd|d}t|trZ|dkrN|S|dkrZd}tj||dS)aMean squared error regression loss Read more in the :ref:`User Guide `. Parameters ---------- y_true : array-like of shape = (n_samples) or (n_samples, n_outputs) Ground truth (correct) target values. y_pred : array-like of shape = (n_samples) or (n_samples, n_outputs) Estimated target values. sample_weight : array-like of shape = (n_samples), optional Sample weights. multioutput : string in ['raw_values', 'uniform_average'] or array-like of shape (n_outputs) Defines aggregating of multiple output values. Array-like value defines weights used to average errors. 'raw_values' : Returns a full set of errors in case of multioutput input. 'uniform_average' : Errors of all outputs are averaged with uniform weight. Returns ------- loss : float or ndarray of floats A non-negative floating point value (the best value is 0.0), or an array of floating point values, one for each individual target. Examples -------- >>> from sklearn.metrics import mean_squared_error >>> y_true = [3, -0.5, 2, 7] >>> y_pred = [2.5, 0.0, 2, 8] >>> mean_squared_error(y_true, y_pred) 0.375 >>> y_true = [[0.5, 1],[-1, 1],[7, -6]] >>> y_pred = [[0, 2],[-1, 2],[8, -5]] >>> mean_squared_error(y_true, y_pred) # doctest: +ELLIPSIS 0.708... >>> mean_squared_error(y_true, y_pred, multioutput='raw_values') ... # doctest: +ELLIPSIS array([0.41666667, 1. ]) >>> mean_squared_error(y_true, y_pred, multioutput=[0.3, 0.7]) ... # doctest: +ELLIPSIS 0.825... rr)r!r rrN)r )rrr"r#rr)rrr%rrr&rrrr s6  cCsZt|||\}}}}t||||dks8|dkr@tdtt|t|||S)aMean squared logarithmic error regression loss Read more in the :ref:`User Guide `. Parameters ---------- y_true : array-like of shape = (n_samples) or (n_samples, n_outputs) Ground truth (correct) target values. y_pred : array-like of shape = (n_samples) or (n_samples, n_outputs) Estimated target values. sample_weight : array-like of shape = (n_samples), optional Sample weights. multioutput : string in ['raw_values', 'uniform_average'] or array-like of shape = (n_outputs) Defines aggregating of multiple output values. Array-like value defines weights used to average errors. 'raw_values' : Returns a full set of errors when the input is of multioutput format. 'uniform_average' : Errors of all outputs are averaged with uniform weight. Returns ------- loss : float or ndarray of floats A non-negative floating point value (the best value is 0.0), or an array of floating point values, one for each individual target. Examples -------- >>> from sklearn.metrics import mean_squared_log_error >>> y_true = [3, 5, 2.5, 7] >>> y_pred = [2.5, 5, 4, 8] >>> mean_squared_log_error(y_true, y_pred) # doctest: +ELLIPSIS 0.039... >>> y_true = [[0.5, 1], [1, 2], [7, 6]] >>> y_pred = [[0.5, 2], [1, 2.5], [8, 8]] >>> mean_squared_log_error(y_true, y_pred) # doctest: +ELLIPSIS 0.044... >>> mean_squared_log_error(y_true, y_pred, multioutput='raw_values') ... # doctest: +ELLIPSIS array([0.00462428, 0.08377444]) >>> mean_squared_log_error(y_true, y_pred, multioutput=[0.3, 0.7]) ... # doctest: +ELLIPSIS 0.060... rzSMean Squared Logarithmic Error cannot be used when targets contain negative values.)rranyrr r"Zlog1p)rrr%rrrrrr s8 cCs8t||d\}}}}|dkr$tdtt||S)arMedian absolute error regression loss Read more in the :ref:`User Guide `. Parameters ---------- y_true : array-like of shape = (n_samples) Ground truth (correct) target values. y_pred : array-like of shape = (n_samples) Estimated target values. Returns ------- loss : float A positive floating point value (the best value is 0.0). Examples -------- >>> from sklearn.metrics import median_absolute_error >>> y_true = [3, -0.5, 2, 7] >>> y_pred = [2.5, 0.0, 2, 8] >>> median_absolute_error(y_true, y_pred) 0.5 rzcontinuous-multioutputz2Multioutput not supported in median_absolute_error)rrr"Zmedianr$)rrr_rrrr As cCs t|||\}}}}t|||tj|||dd}tj|||d|dd}tj||dd}tj||d|dd}|dk} |dk} | | @} t|jd} d|| || | | <d| | | @<t|tr|dkr| S|dkrd} q|d kr|} n|} tj| | d S) aExplained variance regression score function Best possible score is 1.0, lower values are worse. Read more in the :ref:`User Guide `. Parameters ---------- y_true : array-like of shape = (n_samples) or (n_samples, n_outputs) Ground truth (correct) target values. y_pred : array-like of shape = (n_samples) or (n_samples, n_outputs) Estimated target values. sample_weight : array-like of shape = (n_samples), optional Sample weights. multioutput : string in ['raw_values', 'uniform_average', 'variance_weighted'] or array-like of shape (n_outputs) Defines aggregating of multiple output scores. Array-like value defines weights used to average scores. 'raw_values' : Returns a full set of scores in case of multioutput input. 'uniform_average' : Scores of all outputs are averaged with uniform weight. 'variance_weighted' : Scores of all outputs are averaged, weighted by the variances of each individual output. Returns ------- score : float or ndarray of floats The explained variance or ndarray if 'multioutput' is 'raw_values'. Notes ----- This is not a symmetric function. Examples -------- >>> from sklearn.metrics import explained_variance_score >>> y_true = [3, -0.5, 2, 7] >>> y_pred = [2.5, 0.0, 2, 8] >>> explained_variance_score(y_true, y_pred) # doctest: +ELLIPSIS 0.957... >>> y_true = [[0.5, 1], [-1, 1], [7, -6]] >>> y_pred = [[0, 2], [-1, 2], [8, -5]] >>> explained_variance_score(y_true, y_pred, multioutput='uniform_average') ... # doctest: +ELLIPSIS 0.983... r)r r!rrgrrNr)r )rrr"r#onesrrr)rrr%rrZ y_diff_avg numeratorZ y_true_avg denominatornonzero_numeratornonzero_denominator valid_score output_scores avg_weightsrrrr cs2:    c CsFt|||\}}}}t||||dk rDt|}|ddtjf}nd}|||djdtjd}||tj|d|ddjdtjd}|dk}|dk} || @} t|j dg} d|| || | | <d| | |@<t |t r4|d kr| S|d krd} n.|d kr8|} t |s8t | s.dSdSn|} tj| | d S) a3 R^2 (coefficient of determination) regression score function. Best possible score is 1.0 and it can be negative (because the model can be arbitrarily worse). A constant model that always predicts the expected value of y, disregarding the input features, would get a R^2 score of 0.0. Read more in the :ref:`User Guide `. Parameters ---------- y_true : array-like of shape = (n_samples) or (n_samples, n_outputs) Ground truth (correct) target values. y_pred : array-like of shape = (n_samples) or (n_samples, n_outputs) Estimated target values. sample_weight : array-like of shape = (n_samples), optional Sample weights. multioutput : string in ['raw_values', 'uniform_average', 'variance_weighted'] or None or array-like of shape (n_outputs) Defines aggregating of multiple output scores. Array-like value defines weights used to average scores. Default is "uniform_average". 'raw_values' : Returns a full set of scores in case of multioutput input. 'uniform_average' : Scores of all outputs are averaged with uniform weight. 'variance_weighted' : Scores of all outputs are averaged, weighted by the variances of each individual output. .. versionchanged:: 0.19 Default value of multioutput is 'uniform_average'. Returns ------- z : float or ndarray of floats The R^2 score or ndarray of scores if 'multioutput' is 'raw_values'. Notes ----- This is not a symmetric function. Unlike most other scores, R^2 score may be negative (it need not actually be the square of a quantity R). References ---------- .. [1] `Wikipedia entry on the Coefficient of determination `_ Examples -------- >>> from sklearn.metrics import r2_score >>> y_true = [3, -0.5, 2, 7] >>> y_pred = [2.5, 0.0, 2, 8] >>> r2_score(y_true, y_pred) # doctest: +ELLIPSIS 0.948... >>> y_true = [[0.5, 1], [-1, 1], [7, -6]] >>> y_pred = [[0, 2], [-1, 2], [8, -5]] >>> r2_score(y_true, y_pred, ... multioutput='variance_weighted') # doctest: +ELLIPSIS 0.938... >>> y_true = [1, 2, 3] >>> y_pred = [1, 2, 3] >>> r2_score(y_true, y_pred) 1.0 >>> y_true = [1, 2, 3] >>> y_pred = [2, 2, 2] >>> r2_score(y_true, y_pred) 0.0 >>> y_true = [1, 2, 3] >>> y_pred = [3, 2, 1] >>> r2_score(y_true, y_pred) -3.0 Ng?rr)r!Zdtype)r!r rgrrr)r ) rrrr"ZnewaxissumZfloat64r#r)rrrr') rrr%rrZweightr*r+r-r,r.r/r0rrrr s@U        )Nr)Nr)Nr)Nr)Nr)__doc__Z __future__rZnumpyr"Zutils.validationrrrZ externals.sixrZ__ALL__rrr r r r r rrrrs.   F G D B# [