ó ‡ˆ\c@ sÑdZddlmZddlZddlmZmZddlmZddl m Z dd d d d d gZ d„Z ddd„Zddd„Zddd„Zd„Zddd„Zddd„ZdS(sïMetrics 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 iÿÿÿÿ(tdivisionNi(t check_arraytcheck_consistent_length(t column_or_1d(t string_typestmean_absolute_errortmean_squared_errortmean_squared_log_errortmedian_absolute_errortr2_scoretexplained_variance_scorecC s—t||ƒt|dtƒ}t|dtƒ}|jdkrR|jd ƒ}n|jdkrs|jdƒ}n|jd|jdkr¶tdj|jd|jdƒƒ‚n|jd}d}t|t ƒr||krotdj||ƒƒ‚qonm|dk rot|dtƒ}|dkr;td ƒ‚qo|t |ƒkrotd t |ƒ|fƒ‚qon|dkrd nd }||||fS(síCheck 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. t ensure_2diiÿÿÿÿs<y_true and y_pred have different number of output ({0}!={1})t raw_valuestuniform_averagetvariance_weightedsIAllowed 'multioutput' string values are {}. You provided multioutput={!r}s5Custom weights are useful only in multi-output cases.s?There must be equally many custom weights (%d) as outputs (%d).t continuousscontinuous-multioutput(iÿÿÿÿi(iÿÿÿÿi(R R RN( RRtFalsetndimtreshapetshapet ValueErrortformatt isinstanceRtNonetlen(ty_truety_predt multioutputt n_outputstallowed_multioutput_strty_type((s9lib/python2.7/site-packages/sklearn/metrics/regression.pyt_check_reg_targets+s6        R cC s t|||ƒ\}}}}t|||ƒtjtj||ƒd|ddƒ}t|tƒr|dkru|S|dkrd}qntj|d|ƒS(s Mean absolute 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 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... tweightstaxisiR R N(RRtnptaveragetabsRRR(RRt sample_weightRRt output_errors((s9lib/python2.7/site-packages/sklearn/metrics/regression.pyRps9   cC s›t|||ƒ\}}}}t|||ƒtj||dddd|ƒ}t|tƒrˆ|dkrp|S|dkrˆd}qˆntj|d|ƒS(s•Mean 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... iR!iR R R N(RRR"R#RRR(RRR%RRR&((s9lib/python2.7/site-packages/sklearn/metrics/regression.pyR¸s6    cC s†t|||ƒ\}}}}t|||ƒ|dkjƒsR|dkjƒratdƒ‚nttj|ƒtj|ƒ||ƒS(sñMean 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... isSMean Squared Logarithmic Error cannot be used when targets contain negative values.(RRtanyRRR"tlog1p(RRR%RR((s9lib/python2.7/site-packages/sklearn/metrics/regression.pyRýs8$cC sSt||dƒ\}}}}|dkr9tdƒ‚ntjtj||ƒƒS(srMedian absolute error regression loss Read more in the :ref:`User Guide `. Parameters ---------- y_true : array-like of shape = (n_samples) Ground truth (correct) target values. y_pred : array-like of shape = (n_samples) Estimated target values. Returns ------- loss : float A positive floating point value (the best value is 0.0). Examples -------- >>> from sklearn.metrics import median_absolute_error >>> y_true = [3, -0.5, 2, 7] >>> y_pred = [2.5, 0.0, 2, 8] >>> median_absolute_error(y_true, y_pred) 0.5 R scontinuous-multioutputs2Multioutput not supported in median_absolute_error(RRR"tmedianR$(RRRt_((s9lib/python2.7/site-packages/sklearn/metrics/regression.pyRAs   cC sxt|||ƒ\}}}}t|||ƒtj||d|ddƒ}tj|||dd|ddƒ}tj|d|ddƒ}tj||dd|ddƒ}|dk} |dk} | | @} tj|jdƒ} d|| || | | `. 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!iiigR R RN( RRR"R#tonesRRRR(RRR%RRt y_diff_avgt numeratort y_true_avgt denominatortnonzero_numeratortnonzero_denominatort valid_scoret output_scorest avg_weights((s9lib/python2.7/site-packages/sklearn/metrics/regression.pyR cs2:         c C s½t|||ƒ\}}}}t|||ƒ|dk rbt|ƒ}|dd…tjf}nd}|||djdddtjƒ}||tj|ddd|ƒdjdddtjƒ}|dk}|dk} || @} tj |j dgƒ} d|| || | | `. 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 Ngð?iR!itdtypeR igR R R(RRRRR"tnewaxistsumtfloat64R#R+RRRR'( RRR%RRtweightR-R/R1R0R2R3R4((s9lib/python2.7/site-packages/sklearn/metrics/regression.pyR Às@U    $          (t__doc__t __future__RtnumpyR"tutils.validationRRRt externals.sixRt__ALL__RRRRRRR R (((s9lib/python2.7/site-packages/sklearn/metrics/regression.pyts.   F G D B # [