kwcoco.metrics.drawing module

kwcoco.metrics.drawing.draw_roc(roc_info, prefix='', fnum=1, **kw)

NOTE: There needs to be enough negative examples for using ROC to make any sense!

Example

>>> # xdoctest: +REQUIRES(module:kwplot)
>>> from kwcoco.metrics import DetectionMetrics
>>> dmet = DetectionMetrics.demo(
>>>     nimgs=100, nboxes=(0, 30), n_fp=(0, 1), nclasses=3,
>>>     box_noise=0.00, cls_noise=.0, score_noise=1.0)
>>> dmet.true_detections(0).data
>>> cfsn_vecs = dmet.confusion_vectors(compat='mutex', prioritize='iou', bias=0)
>>> print(cfsn_vecs.data._pandas().sort_values('score'))
>>> classes = cfsn_vecs.classes
>>> roc_info = ub.peek(cfsn_vecs.binarize_ovr().measures()['perclass'].values())
>>> # xdoctest: +REQUIRES(--show)
>>> import kwplot
>>> kwplot.autompl()
>>> draw_roc(roc_info)
>>> kwplot.show_if_requested()

kwcoco.metrics.drawing.draw_perclass_roc(cx_to_rocinfo, classes=None, prefix='', fnum=1, fp_axis='count', **kw)

fp_axis can be count or rate

cx_to_rocinfo = roc_perclass

kwcoco.metrics.drawing.draw_perclass_prcurve(cx_to_peritem, classes=None, prefix='', fnum=1, **kw)

Example

>>> # xdoctest: +REQUIRES(module:kwplot)
>>> from kwcoco.metrics import DetectionMetrics
>>> dmet = DetectionMetrics.demo(
>>>     nimgs=10, nboxes=(0, 10), n_fp=(0, 1), nclasses=3)
>>> cfsn_vecs = dmet.confusion_vectors()
>>> classes = cfsn_vecs.classes
>>> cx_to_peritem = cfsn_vecs.binarize_ovr().measures()['perclass']
>>> import kwplot
>>> kwplot.autompl()
>>> draw_perclass_prcurve(cx_to_peritem, classes)
>>> # xdoctest: +REQUIRES(--show)
>>> kwplot.show_if_requested()

kwcoco.metrics.drawing.draw_perclass_thresholds(cx_to_peritem, key='mcc', classes=None, prefix='', fnum=1, **kw)

Notes

Each category is inspected independently of one another, there is no notion of confusion.

Example

>>> # xdoctest: +REQUIRES(module:kwplot)
>>> from kwcoco.metrics.drawing import *  # NOQA
>>> from kwcoco.metrics import ConfusionVectors
>>> cfsn_vecs = ConfusionVectors.demo()
>>> classes = cfsn_vecs.classes
>>> ovr_cfsn = cfsn_vecs.binarize_ovr(keyby='name')
>>> cx_to_peritem = ovr_cfsn.measures()['perclass']
>>> import kwplot
>>> kwplot.autompl()
>>> key = 'mcc'
>>> draw_perclass_thresholds(cx_to_peritem, key, classes)
>>> # xdoctest: +REQUIRES(--show)
>>> kwplot.show_if_requested()

kwcoco.metrics.drawing.draw_prcurve(peritem, prefix='', fnum=1, **kw)

TODO: rename to draw prcurve. Just draws a single pr curve.

Example

>>> # xdoctest: +REQUIRES(module:kwplot)
>>> from kwcoco.metrics import DetectionMetrics
>>> dmet = DetectionMetrics.demo(
>>>     nimgs=10, nboxes=(0, 10), n_fp=(0, 1), nclasses=3)
>>> cfsn_vecs = dmet.confusion_vectors()

>>> classes = cfsn_vecs.classes
>>> peritem = cfsn_vecs.binarize_peritem().measures()
>>> import kwplot
>>> kwplot.autompl()
>>> draw_prcurve(peritem)
>>> # xdoctest: +REQUIRES(--show)
>>> kwplot.show_if_requested()

kwcoco.metrics.drawing.draw_threshold_curves(info, keys=None, prefix='', fnum=1, **kw)

Example

>>> # xdoctest: +REQUIRES(module:kwplot)
>>> import sys, ubelt
>>> sys.path.append(ubelt.expandpath('~/code/kwcoco'))
>>> from kwcoco.metrics.drawing import *  # NOQA
>>> from kwcoco.metrics import DetectionMetrics
>>> dmet = DetectionMetrics.demo(
>>>     nimgs=10, nboxes=(0, 10), n_fp=(0, 1), nclasses=3)
>>> cfsn_vecs = dmet.confusion_vectors()
>>> info = cfsn_vecs.binarize_peritem().measures()
>>> keys = None
>>> import kwplot
>>> kwplot.autompl()
>>> draw_threshold_curves(info, keys)
>>> # xdoctest: +REQUIRES(--show)
>>> kwplot.show_if_requested()