kwcoco.metrics.confusion_measures module

Classes that store accumulated confusion measures (usually derived from confusion vectors).

For each chosen threshold value:

• thresholds[i] - the i-th threshold value

The primary data we manipulate are arrays of “confusion” counts, i.e.

• tp_count[i] - true positives at the i-th threshold

• fp_count[i] - false positives at the i-th threshold

• fn_count[i] - false negatives at the i-th threshold

• tn_count[i] - true negatives at the i-th threshold

class kwcoco.metrics.confusion_measures.Measures(info)

Bases: NiceRepr, DictProxy

Holds accumulated confusion counts, and derived measures

Example

>>> from kwcoco.metrics.confusion_vectors import BinaryConfusionVectors  # NOQA
>>> binvecs = BinaryConfusionVectors.demo(n=100, p_error=0.5)
>>> self = binvecs.measures()
>>> print('self = {!r}'.format(self))
>>> # xdoctest: +REQUIRES(--show)
>>> import kwplot
>>> kwplot.autompl()
>>> self.draw(doclf=True)
>>> self.draw(key='pr',  pnum=(1, 2, 1))
>>> self.draw(key='roc', pnum=(1, 2, 2))
>>> kwplot.show_if_requested()

property catname

reconstruct()

classmethod from_json(state)

summary()

maximized_thresholds()

Returns thresholds that maximize metrics.

counts()

draw(key=None, prefix='', **kw)

Example

>>> # xdoctest: +REQUIRES(module:kwplot)
>>> # xdoctest: +REQUIRES(module:pandas)
>>> from kwcoco.metrics.confusion_vectors import ConfusionVectors  # NOQA
>>> cfsn_vecs = ConfusionVectors.demo()
>>> ovr_cfsn = cfsn_vecs.binarize_ovr(keyby='name')
>>> self = ovr_cfsn.measures()['perclass']
>>> self.draw('mcc', doclf=True, fnum=1)
>>> self.draw('pr', doclf=1, fnum=2)
>>> self.draw('roc', doclf=1, fnum=3)

summary_plot(fnum=1, title='', subplots='auto')

Example

>>> from kwcoco.metrics.confusion_measures import *  # NOQA
>>> from kwcoco.metrics.confusion_vectors import ConfusionVectors  # NOQA
>>> cfsn_vecs = ConfusionVectors.demo(n=3, p_error=0.5)
>>> binvecs = cfsn_vecs.binarize_classless()
>>> self = binvecs.measures()
>>> # xdoctest: +REQUIRES(--show)
>>> import kwplot
>>> kwplot.autompl()
>>> self.summary_plot()
>>> kwplot.show_if_requested()

classmethod demo(**kwargs)

Create a demo Measures object for testing / demos

Parameters:

**kwargs – passed to BinaryConfusionVectors.demo(). some valid keys are: n, rng, p_rue, p_error, p_miss.

classmethod combine(tocombine, precision=None, growth=None, thresh_bins=None)

Combine binary confusion metrics

Parameters:

• tocombine (List[Measures]) – a list of measures to combine into one

• precision (int | None) – If specified rounds thresholds to this precision which can prevent a RAM explosion when combining a large number of measures. However, this is a lossy operation and will impact the underlying scores. NOTE: use growth instead.

• growth (int | None) – if specified this limits how much the resulting measures are allowed to grow by. If None, growth is unlimited. Otherwise, if growth is ‘max’, the growth is limited to the maximum length of an input. We might make this more numerical in the future.

• thresh_bins (int | None) – Force this many threshold bins.

Returns:

kwcoco.metrics.confusion_measures.Measures

Example

>>> from kwcoco.metrics.confusion_measures import *  # NOQA
>>> measures1 = Measures.demo(n=15)
>>> measures2 = measures1
>>> tocombine = [measures1, measures2]
>>> new_measures = Measures.combine(tocombine)
>>> new_measures.reconstruct()
>>> print('new_measures = {!r}'.format(new_measures))
>>> print('measures1 = {!r}'.format(measures1))
>>> print('measures2 = {!r}'.format(measures2))
>>> print(ub.urepr(measures1.__json__(), nl=1, sort=0))
>>> print(ub.urepr(measures2.__json__(), nl=1, sort=0))
>>> print(ub.urepr(new_measures.__json__(), nl=1, sort=0))
>>> # xdoctest: +REQUIRES(--show)
>>> import kwplot
>>> kwplot.autompl()
>>> kwplot.figure(fnum=1)
>>> new_measures.summary_plot()
>>> measures1.summary_plot()
>>> measures1.draw('roc')
>>> measures2.draw('roc')
>>> new_measures.draw('roc')

Example

>>> # Demonstrate issues that can arrise from choosing a precision
>>> # that is too low  when combining metrics. Breakpoints
>>> # between different metrics can get muddled, but choosing a
>>> # precision that is too high can overwhelm memory.
>>> from kwcoco.metrics.confusion_measures import *  # NOQA
>>> base = ub.map_vals(np.asarray, {
>>>     'tp_count':   [ 1,  1,  2,  2,  2,  2,  3],
>>>     'fp_count':   [ 0,  1,  1,  2,  3,  4,  5],
>>>     'fn_count':   [ 1,  1,  0,  0,  0,  0,  0],
>>>     'tn_count':   [ 5,  4,  4,  3,  2,  1,  0],
>>>     'thresholds': [.0, .0, .0, .0, .0, .0, .0],
>>> })
>>> # Make tiny offsets to thresholds
>>> rng = kwarray.ensure_rng(0)
>>> n = len(base['thresholds'])
>>> offsets = [
>>>     sorted(rng.rand(n) * 10 ** -rng.randint(4, 7))[::-1]
>>>     for _ in range(20)
>>> ]
>>> tocombine = []
>>> for offset in offsets:
>>>     base_n = base.copy()
>>>     base_n['thresholds'] += offset
>>>     measures_n = Measures(base_n).reconstruct()
>>>     tocombine.append(measures_n)
>>> for precision in [6, 5, 2]:
>>>     combo = Measures.combine(tocombine, precision=precision).reconstruct()
>>>     print('precision = {!r}'.format(precision))
>>>     print('combo = {}'.format(ub.urepr(combo, nl=1)))
>>>     print('num_thresholds = {}'.format(len(combo['thresholds'])))
>>> for growth in [None, 'max', 'log', 'root', 'half']:
>>>     combo = Measures.combine(tocombine, growth=growth).reconstruct()
>>>     print('growth = {!r}'.format(growth))
>>>     print('combo = {}'.format(ub.urepr(combo, nl=1)))
>>>     print('num_thresholds = {}'.format(len(combo['thresholds'])))
>>>     #print(combo.counts().pandas())

Example

>>> # Test case: combining a single measures should leave it unchanged
>>> from kwcoco.metrics.confusion_measures import *  # NOQA
>>> measures = Measures.demo(n=40, p_true=0.2, p_error=0.4, p_miss=0.6)
>>> df1 = measures.counts().pandas().fillna(0)
>>> print(df1)
>>> tocombine = [measures]
>>> combo = Measures.combine(tocombine)
>>> df2 = combo.counts().pandas().fillna(0)
>>> print(df2)
>>> assert np.allclose(df1, df2)

>>> combo = Measures.combine(tocombine, thresh_bins=2)
>>> df3 = combo.counts().pandas().fillna(0)
>>> print(df3)

>>> # I am NOT sure if this is correct or not
>>> thresh_bins = 20
>>> combo = Measures.combine(tocombine, thresh_bins=thresh_bins)
>>> df4 = combo.counts().pandas().fillna(0)
>>> print(df4)

>>> combo = Measures.combine(tocombine, thresh_bins=np.linspace(0, 1, 20))
>>> df4 = combo.counts().pandas().fillna(0)
>>> print(df4)

assert np.allclose(combo[‘thresholds’], measures[‘thresholds’]) assert np.allclose(combo[‘fp_count’], measures[‘fp_count’]) assert np.allclose(combo[‘tp_count’], measures[‘tp_count’]) assert np.allclose(combo[‘tp_count’], measures[‘tp_count’])

globals().update(xdev.get_func_kwargs(Measures.combine))

Example

>>> # Test degenerate case
>>> from kwcoco.metrics.confusion_measures import *  # NOQA
>>> tocombine = [
>>>     {'fn_count': [0.0], 'fp_count': [359980.0], 'thresholds': [0.0], 'tn_count': [0.0], 'tp_count': [7747.0]},
>>>     {'fn_count': [0.0], 'fp_count': [360849.0], 'thresholds': [0.0], 'tn_count': [0.0], 'tp_count': [424.0]},
>>>     {'fn_count': [0.0], 'fp_count': [367003.0], 'thresholds': [0.0], 'tn_count': [0.0], 'tp_count': [991.0]},
>>>     {'fn_count': [0.0], 'fp_count': [367976.0], 'thresholds': [0.0], 'tn_count': [0.0], 'tp_count': [1017.0]},
>>>     {'fn_count': [0.0], 'fp_count': [676338.0], 'thresholds': [0.0], 'tn_count': [0.0], 'tp_count': [7067.0]},
>>>     {'fn_count': [0.0], 'fp_count': [676348.0], 'thresholds': [0.0], 'tn_count': [0.0], 'tp_count': [7406.0]},
>>>     {'fn_count': [0.0], 'fp_count': [676626.0], 'thresholds': [0.0], 'tn_count': [0.0], 'tp_count': [7858.0]},
>>>     {'fn_count': [0.0], 'fp_count': [676693.0], 'thresholds': [0.0], 'tn_count': [0.0], 'tp_count': [10969.0]},
>>>     {'fn_count': [0.0], 'fp_count': [677269.0], 'thresholds': [0.0], 'tn_count': [0.0], 'tp_count': [11188.0]},
>>>     {'fn_count': [0.0], 'fp_count': [677331.0], 'thresholds': [0.0], 'tn_count': [0.0], 'tp_count': [11734.0]},
>>>     {'fn_count': [0.0], 'fp_count': [677395.0], 'thresholds': [0.0], 'tn_count': [0.0], 'tp_count': [11556.0]},
>>>     {'fn_count': [0.0], 'fp_count': [677418.0], 'thresholds': [0.0], 'tn_count': [0.0], 'tp_count': [11621.0]},
>>>     {'fn_count': [0.0], 'fp_count': [677422.0], 'thresholds': [0.0], 'tn_count': [0.0], 'tp_count': [11424.0]},
>>>     {'fn_count': [0.0], 'fp_count': [677648.0], 'thresholds': [0.0], 'tn_count': [0.0], 'tp_count': [9804.0]},
>>>     {'fn_count': [0.0], 'fp_count': [677826.0], 'thresholds': [0.0], 'tn_count': [0.0], 'tp_count': [2470.0]},
>>>     {'fn_count': [0.0], 'fp_count': [677834.0], 'thresholds': [0.0], 'tn_count': [0.0], 'tp_count': [2470.0]},
>>>     {'fn_count': [0.0], 'fp_count': [677835.0], 'thresholds': [0.0], 'tn_count': [0.0], 'tp_count': [2470.0]},
>>>     {'fn_count': [11123.0, 0.0], 'fp_count': [0.0, 676754.0], 'thresholds': [0.0002442002442002442, 0.0], 'tn_count': [676754.0, 0.0], 'tp_count': [2.0, 11125.0]},
>>>     {'fn_count': [7738.0, 0.0], 'fp_count': [0.0, 676466.0], 'thresholds': [0.0002442002442002442, 0.0], 'tn_count': [676466.0, 0.0], 'tp_count': [0.0, 7738.0]},
>>>     {'fn_count': [8653.0, 0.0], 'fp_count': [0.0, 676341.0], 'thresholds': [0.0002442002442002442, 0.0], 'tn_count': [676341.0, 0.0], 'tp_count': [0.0, 8653.0]},
>>> ]
>>> thresh_bins = np.linspace(0, 1, 4)
>>> combo = Measures.combine(tocombine, thresh_bins=thresh_bins).reconstruct()
>>> print('tocombine = {}'.format(ub.urepr(tocombine, nl=2)))
>>> print('thresh_bins = {!r}'.format(thresh_bins))
>>> print(ub.urepr(combo.__json__(), nl=1))
>>> for thresh_bins in [4096, 1]:
>>>     combo = Measures.combine(tocombine, thresh_bins=thresh_bins).reconstruct()
>>>     print('thresh_bins = {!r}'.format(thresh_bins))
>>>     print('combo = {}'.format(ub.urepr(combo, nl=1)))
>>>     print('num_thresholds = {}'.format(len(combo['thresholds'])))
>>> for precision in [6, 5, 2]:
>>>     combo = Measures.combine(tocombine, precision=precision).reconstruct()
>>>     print('precision = {!r}'.format(precision))
>>>     print('combo = {}'.format(ub.urepr(combo, nl=1)))
>>>     print('num_thresholds = {}'.format(len(combo['thresholds'])))
>>> for growth in [None, 'max', 'log', 'root', 'half']:
>>>     combo = Measures.combine(tocombine, growth=growth).reconstruct()
>>>     print('growth = {!r}'.format(growth))
>>>     print('combo = {}'.format(ub.urepr(combo, nl=1)))
>>>     print('num_thresholds = {}'.format(len(combo['thresholds'])))

kwcoco.metrics.confusion_measures._combine_threshold(tocombine_thresh, thresh_bins, growth, precision)

Logic to take care of combining thresholds in the case bins are not given

This can be fairly slow and lead to unnecessary memory usage

kwcoco.metrics.confusion_measures.reversable_diff(arr, assume_sorted=1, reverse=False)

Does a reversable array difference operation.

This will be used to find positions where accumulation happened in confusion count array.

class kwcoco.metrics.confusion_measures.PerClass_Measures(cx_to_info)

Bases: NiceRepr, DictProxy

summary()

classmethod from_json(state)

draw(key='mcc', prefix='', **kw)

Example

>>> # xdoctest: +REQUIRES(module:kwplot)
>>> from kwcoco.metrics.confusion_vectors import ConfusionVectors  # NOQA
>>> cfsn_vecs = ConfusionVectors.demo()
>>> ovr_cfsn = cfsn_vecs.binarize_ovr(keyby='name')
>>> self = ovr_cfsn.measures()['perclass']
>>> self.draw('mcc', doclf=True, fnum=1)
>>> self.draw('pr', doclf=1, fnum=2)
>>> self.draw('roc', doclf=1, fnum=3)

draw_roc(prefix='', **kw)

draw_pr(prefix='', **kw)

summary_plot(fnum=1, title='', subplots='auto')

CommandLine

python ~/code/kwcoco/kwcoco/metrics/confusion_measures.py PerClass_Measures.summary_plot --show

Example

>>> from kwcoco.metrics.confusion_measures import *  # NOQA
>>> from kwcoco.metrics.detect_metrics import DetectionMetrics
>>> dmet = DetectionMetrics.demo(
>>>     n_fp=(0, 1), n_fn=(0, 3), nimgs=32, nboxes=(0, 32),
>>>     classes=3, rng=0, newstyle=1, box_noise=0.7, cls_noise=0.2, score_noise=0.3, with_probs=False)
>>> cfsn_vecs = dmet.confusion_vectors()
>>> ovr_cfsn = cfsn_vecs.binarize_ovr(keyby='name', ignore_classes=['vector', 'raster'])
>>> self = ovr_cfsn.measures()['perclass']
>>> # xdoctest: +REQUIRES(--show)
>>> import kwplot
>>> kwplot.autompl()
>>> import seaborn as sns
>>> sns.set()
>>> self.summary_plot(title='demo summary_plot ovr', subplots=['pr', 'roc'])
>>> kwplot.show_if_requested()
>>> self.summary_plot(title='demo summary_plot ovr', subplots=['mcc', 'acc'], fnum=2)

class kwcoco.metrics.confusion_measures.MeasureCombiner(precision=None, growth=None, thresh_bins=None)

Bases: object

Helper to iteravely combine binary measures generated by some process

Example

>>> from kwcoco.metrics.confusion_measures import *  # NOQA
>>> from kwcoco.metrics.confusion_vectors import BinaryConfusionVectors
>>> rng = kwarray.ensure_rng(0)
>>> bin_combiner = MeasureCombiner(growth='max')
>>> for _ in range(80):
>>>     bin_cfsn_vecs = BinaryConfusionVectors.demo(n=rng.randint(40, 50), rng=rng, p_true=0.2, p_error=0.4, p_miss=0.6)
>>>     bin_measures = bin_cfsn_vecs.measures()
>>>     bin_combiner.submit(bin_measures)
>>> combined = bin_combiner.finalize()
>>> print('combined = {!r}'.format(combined))

property queue_size

submit(other)

combine()

finalize()

class kwcoco.metrics.confusion_measures.OneVersusRestMeasureCombiner(precision=None, growth=None, thresh_bins=None)

Bases: object

Helper to iteravely combine ovr measures generated by some process

Example

>>> from kwcoco.metrics.confusion_measures import *  # NOQA
>>> from kwcoco.metrics.confusion_vectors import OneVsRestConfusionVectors
>>> rng = kwarray.ensure_rng(0)
>>> ovr_combiner = OneVersusRestMeasureCombiner(growth='max')
>>> for _ in range(80):
>>>     ovr_cfsn_vecs = OneVsRestConfusionVectors.demo()
>>>     ovr_measures = ovr_cfsn_vecs.measures()
>>>     ovr_combiner.submit(ovr_measures)
>>> combined = ovr_combiner.finalize()
>>> print('combined = {!r}'.format(combined))

submit(other)

_summary()

combine()

finalize()

kwcoco.metrics.confusion_measures.populate_info(info)

Given raw accumulated confusion counts, populated secondary measures like AP, AUC, F1, MCC, etc..