RocCurveDisplay #

classsklearn.metrics.RocCurveDisplay(*,fpr,tpr,roc_auc=None,name=None,pos_label=None,estimator_name='deprecated')[source]#

ROC Curve visualization.

It is recommended to usefrom_estimator orfrom_predictions orfrom_cv_results to createaRocCurveDisplay. All parameters arestored as attributes.

For general information regardingscikit-learn visualization tools, seetheVisualization Guide.For guidance on interpreting these plots, refer to theModelEvaluation Guide.

Parameters:

fprndarray or list of ndarrays: False positive rates. Each ndarray should contain values for a single curve.If plotting multiple curves, list should be of same length astpr.
Changed in version 1.7:Now accepts a list for plotting multiple curves.
tprndarray or list of ndarrays: True positive rates. Each ndarray should contain values for a single curve.If plotting multiple curves, list should be of same length asfpr.
Changed in version 1.7:Now accepts a list for plotting multiple curves.
roc_aucfloat or list of floats, default=None: Area under ROC curve, used for labeling each curve in the legend.If plotting multiple curves, should be a list of the same length asfprandtpr. IfNone, ROC AUC scores are not shown in the legend.
Changed in version 1.7:Now accepts a list for plotting multiple curves.
namestr or list of str, default=None: Name for labeling legend entries. The number of legend entries is determinedby thecurve_kwargs passed toplot, and is not affected byname.To label each curve, provide a list of strings. To avoid labelingindividual curves that have the same appearance, this cannot be used inconjunction withcurve_kwargs being a dictionary or None. If astring is provided, it will be used to either label the single legend entryor if there are multiple legend entries, label each individual curve withthe same name. If stillNone, no name is shown in the legend.
Added in version 1.7.
pos_labelint, float, bool or str, default=None: The class considered as the positive class when computing the roc aucmetrics. By default,estimators.classes_[1] is consideredas the positive class.
Added in version 0.24.
estimator_namestr, default=None: Name of estimator. If None, the estimator name is not shown.
Deprecated since version 1.7:estimator_name is deprecated and will be removed in 1.9. Usenameinstead.

Attributes:

line_matplotlib Artist or list of matplotlib Artists: ROC Curves.
Changed in version 1.7:This attribute can now be a list of Artists, for when multiple curvesare plotted.
chance_level_matplotlib Artist or None: The chance level line. It isNone if the chance level is not plotted.
Added in version 1.3.
ax_matplotlib Axes: Axes with ROC Curve.
figure_matplotlib Figure: Figure containing the curve.

See also

roc_curve: Compute Receiver operating characteristic (ROC) curve.
RocCurveDisplay.from_estimator: Plot Receiver Operating Characteristic (ROC) curve given an estimator and some data.
RocCurveDisplay.from_predictions: Plot Receiver Operating Characteristic (ROC) curve given the true and predicted values.
roc_auc_score: Compute the area under the ROC curve.

Examples

>>>importmatplotlib.pyplotasplt>>>importnumpyasnp>>>fromsklearnimportmetrics>>>y_true=np.array([0,0,1,1])>>>y_score=np.array([0.1,0.4,0.35,0.8])>>>fpr,tpr,thresholds=metrics.roc_curve(y_true,y_score)>>>roc_auc=metrics.auc(fpr,tpr)>>>display=metrics.RocCurveDisplay(fpr=fpr,tpr=tpr,roc_auc=roc_auc,...name='example estimator')>>>display.plot()<...>>>>plt.show()

../../_images/sklearn-metrics-RocCurveDisplay-1.png

classmethodfrom_cv_results(cv_results,X,y,*,sample_weight=None,drop_intermediate=True,response_method='auto',pos_label=None,ax=None,name=None,curve_kwargs=None,plot_chance_level=False,chance_level_kwargs=None,despine=False)[source]#

Create a multi-fold ROC curve display given cross-validation results.

Added in version 1.7.

Parameters:

cv_resultsdict: Dictionary as returned bycross_validateusingreturn_estimator=True andreturn_indices=True (i.e., dictionaryshould contain the keys “estimator” and “indices”).
X{array-like, sparse matrix} of shape (n_samples, n_features): Input values.
yarray-like of shape (n_samples,): Target values.
sample_weightarray-like of shape (n_samples,), default=None: Sample weights.
drop_intermediatebool, default=True: Whether to drop some suboptimal thresholds which would not appearon a plotted ROC curve. This is useful in order to create lighterROC curves.
response_method{‘predict_proba’, ‘decision_function’, ‘auto’} default=’auto’: Specifies whether to usepredict_proba ordecision_function as the target response. If set to ‘auto’,predict_proba is tried first and if it does not existdecision_function is tried next.
pos_labelint, float, bool or str, default=None: The class considered as the positive class when computing the ROC AUCmetrics. By default,estimators.classes_[1] is consideredas the positive class.
axmatplotlib axes, default=None: Axes object to plot on. IfNone, a new figure and axes iscreated.
namestr or list of str, default=None: Name for labeling legend entries. The number of legend entriesis determined bycurve_kwargs, and is not affected byname.To label each curve, provide a list of strings. To avoid labelingindividual curves that have the same appearance, this cannot be used inconjunction withcurve_kwargs being a dictionary or None. If astring is provided, it will be used to either label the single legend entryor if there are multiple legend entries, label each individual curve withthe same name. IfNone, no name is shown in the legend.
curve_kwargsdict or list of dict, default=None: Keywords arguments to be passed to matplotlib’splot functionto draw individual ROC curves. If a list is provided theparameters are applied to the ROC curves of each CV foldsequentially and a legend entry is added for each curve.If a single dictionary is provided, the same parameters are appliedto all ROC curves and a single legend entry for all curves is added,labeled with the mean ROC AUC score.
plot_chance_levelbool, default=False: Whether to plot the chance level.
chance_level_kwargsdict, default=None: Keyword arguments to be passed to matplotlib’splot for renderingthe chance level line.
despinebool, default=False: Whether to remove the top and right spines from the plot.

Returns:

displayRocCurveDisplay: The multi-fold ROC curve display.

See also

roc_curve: Compute Receiver operating characteristic (ROC) curve.
RocCurveDisplay.from_estimator: ROC Curve visualization given an estimator and some data.
RocCurveDisplay.from_predictions: ROC Curve visualization given the probabilities of scores of a classifier.
roc_auc_score: Compute the area under the ROC curve.

Examples

>>>importmatplotlib.pyplotasplt>>>fromsklearn.datasetsimportmake_classification>>>fromsklearn.metricsimportRocCurveDisplay>>>fromsklearn.model_selectionimportcross_validate>>>fromsklearn.svmimportSVC>>>X,y=make_classification(random_state=0)>>>clf=SVC(random_state=0)>>>cv_results=cross_validate(...clf,X,y,cv=3,return_estimator=True,return_indices=True)>>>RocCurveDisplay.from_cv_results(cv_results,X,y)<...>>>>plt.show()

../../_images/sklearn-metrics-RocCurveDisplay-2.png

classmethodfrom_estimator(estimator,X,y,*,sample_weight=None,drop_intermediate=True,response_method='auto',pos_label=None,name=None,ax=None,curve_kwargs=None,plot_chance_level=False,chance_level_kw=None,despine=False,**kwargs)[source]#

Create a ROC Curve display from an estimator.

For general information regardingscikit-learn visualization tools,see theVisualization Guide.For guidance on interpreting these plots, refer to theModelEvaluation Guide.

Parameters:

estimatorestimator instance: Fitted classifier or a fittedPipelinein which the last estimator is a classifier.
X{array-like, sparse matrix} of shape (n_samples, n_features): Input values.
yarray-like of shape (n_samples,): Target values.
sample_weightarray-like of shape (n_samples,), default=None: Sample weights.
drop_intermediatebool, default=True: Whether to drop thresholds where the resulting point is collinearwith its neighbors in ROC space. This has no effect on the ROC AUCor visual shape of the curve, but reduces the number of plottedpoints.
response_method{‘predict_proba’, ‘decision_function’, ‘auto’} default=’auto’: Specifies whether to usepredict_proba ordecision_function as the target response. If set to ‘auto’,predict_proba is tried first and if it does not existdecision_function is tried next.
pos_labelint, float, bool or str, default=None: The class considered as the positive class when computing the ROC AUC.By default,estimators.classes_[1] is consideredas the positive class.
namestr, default=None: Name of ROC Curve for labeling. IfNone, use the name of theestimator.
axmatplotlib axes, default=None: Axes object to plot on. IfNone, a new figure and axes is created.
curve_kwargsdict, default=None: Keywords arguments to be passed to matplotlib’splot function.
Added in version 1.7.
plot_chance_levelbool, default=False: Whether to plot the chance level.
Added in version 1.3.
chance_level_kwdict, default=None: Keyword arguments to be passed to matplotlib’splot for renderingthe chance level line.
Added in version 1.3.
despinebool, default=False: Whether to remove the top and right spines from the plot.
Added in version 1.6.
**kwargsdict: Keyword arguments to be passed to matplotlib’splot.
Deprecated since version 1.7:kwargs is deprecated and will be removed in 1.9. Pass matplotlibarguments tocurve_kwargs as a dictionary instead.

Returns:

displayRocCurveDisplay: The ROC Curve display.

See also

roc_curve: Compute Receiver operating characteristic (ROC) curve.
RocCurveDisplay.from_predictions: ROC Curve visualization given the probabilities of scores of a classifier.
roc_auc_score: Compute the area under the ROC curve.

Examples

>>>importmatplotlib.pyplotasplt>>>fromsklearn.datasetsimportmake_classification>>>fromsklearn.metricsimportRocCurveDisplay>>>fromsklearn.model_selectionimporttrain_test_split>>>fromsklearn.svmimportSVC>>>X,y=make_classification(random_state=0)>>>X_train,X_test,y_train,y_test=train_test_split(...X,y,random_state=0)>>>clf=SVC(random_state=0).fit(X_train,y_train)>>>RocCurveDisplay.from_estimator(...clf,X_test,y_test)<...>>>>plt.show()

../../_images/sklearn-metrics-RocCurveDisplay-3.png

classmethodfrom_predictions(y_true,y_score=None,*,sample_weight=None,drop_intermediate=True,pos_label=None,name=None,ax=None,curve_kwargs=None,plot_chance_level=False,chance_level_kw=None,despine=False,y_pred='deprecated',**kwargs)[source]#

Plot ROC curve given the true and predicted values.

For general information regardingscikit-learn visualization tools,see theVisualization Guide.For guidance on interpreting these plots, refer to theModelEvaluation Guide.

Added in version 1.0.

Parameters:

y_truearray-like of shape (n_samples,): True labels.
y_scorearray-like of shape (n_samples,): Target scores, can either be probability estimates of the positiveclass, confidence values, or non-thresholded measure of decisions(as returned by “decision_function” on some classifiers).
Added in version 1.7:y_pred has been renamed toy_score.
sample_weightarray-like of shape (n_samples,), default=None: Sample weights.
drop_intermediatebool, default=True: Whether to drop thresholds where the resulting point is collinearwith its neighbors in ROC space. This has no effect on the ROC AUCor visual shape of the curve, but reduces the number of plottedpoints.
pos_labelint, float, bool or str, default=None: The label of the positive class when computing the ROC AUC.Whenpos_label=None, ify_true is in {-1, 1} or {0, 1},pos_labelis set to 1, otherwise an error will be raised.
namestr, default=None: Name of ROC curve for legend labeling. IfNone, name will be set to"Classifier".
axmatplotlib axes, default=None: Axes object to plot on. IfNone, a new figure and axes iscreated.
curve_kwargsdict, default=None: Keywords arguments to be passed to matplotlib’splot function.
Added in version 1.7.
plot_chance_levelbool, default=False: Whether to plot the chance level.
Added in version 1.3.
chance_level_kwdict, default=None: Keyword arguments to be passed to matplotlib’splot for renderingthe chance level line.
Added in version 1.3.
despinebool, default=False: Whether to remove the top and right spines from the plot.
Added in version 1.6.
y_predarray-like of shape (n_samples,): Target scores, can either be probability estimates of the positiveclass, confidence values, or non-thresholded measure of decisions(as returned by “decision_function” on some classifiers).
Deprecated since version 1.7:y_pred is deprecated and will be removed in 1.9. Usey_score instead.
**kwargsdict: Additional keywords arguments passed to matplotlibplot function.
Deprecated since version 1.7:kwargs is deprecated and will be removed in 1.9. Pass matplotlibarguments tocurve_kwargs as a dictionary instead.

Returns:

displayRocCurveDisplay: Object that stores computed values.

See also

roc_curve: Compute Receiver operating characteristic (ROC) curve.
RocCurveDisplay.from_estimator: ROC Curve visualization given an estimator and some data.
roc_auc_score: Compute the area under the ROC curve.

Examples

>>>importmatplotlib.pyplotasplt>>>fromsklearn.datasetsimportmake_classification>>>fromsklearn.metricsimportRocCurveDisplay>>>fromsklearn.model_selectionimporttrain_test_split>>>fromsklearn.svmimportSVC>>>X,y=make_classification(random_state=0)>>>X_train,X_test,y_train,y_test=train_test_split(...X,y,random_state=0)>>>clf=SVC(random_state=0).fit(X_train,y_train)>>>y_score=clf.decision_function(X_test)>>>RocCurveDisplay.from_predictions(y_test,y_score)<...>>>>plt.show()

../../_images/sklearn-metrics-RocCurveDisplay-4.png

plot(ax=None,*,name=None,curve_kwargs=None,plot_chance_level=False,chance_level_kw=None,despine=False,**kwargs)[source]#

Plot visualization.

Parameters:

axmatplotlib axes, default=None: Axes object to plot on. IfNone, a new figure and axes iscreated.
namestr or list of str, default=None: Name for labeling legend entries. The number of legend entriesis determined bycurve_kwargs, and is not affected byname.To label each curve, provide a list of strings. To avoid labelingindividual curves that have the same appearance, this cannot be used inconjunction withcurve_kwargs being a dictionary or None. If astring is provided, it will be used to either label the single legend entryor if there are multiple legend entries, label each individual curve withthe same name. IfNone, set toname provided atRocCurveDisplayinitialization. If stillNone, no name is shown in the legend.
Added in version 1.7.
curve_kwargsdict or list of dict, default=None: Keywords arguments to be passed to matplotlib’splot functionto draw individual ROC curves. For single curve plotting, should bea dictionary. For multi-curve plotting, if a list is provided theparameters are applied to the ROC curves of each CV foldsequentially and a legend entry is added for each curve.If a single dictionary is provided, the same parameters are appliedto all ROC curves and a single legend entry for all curves is added,labeled with the mean ROC AUC score.
Added in version 1.7.
plot_chance_levelbool, default=False: Whether to plot the chance level.
Added in version 1.3.
chance_level_kwdict, default=None: Keyword arguments to be passed to matplotlib’splot for renderingthe chance level line.
Added in version 1.3.
despinebool, default=False: Whether to remove the top and right spines from the plot.
Added in version 1.6.
**kwargsdict: Keyword arguments to be passed to matplotlib’splot.
Deprecated since version 1.7:kwargs is deprecated and will be removed in 1.9. Pass matplotlibarguments tocurve_kwargs as a dictionary instead.

Returns: