def default_metrics(self):
return [
metrics.Accuracy(),
metrics.CrossEntropy(),
metrics.MacroPrecision(),
metrics.MacroRecall(),
metrics.MacroF1(),
metrics.MicroPrecision(),
metrics.MicroRecall(),
metrics.MicroF1()
]
import math
import pytest
from creme import metrics
from sklearn import metrics as sk_metrics
@pytest.mark.parametrize(
'metric, sk_metric, y_true, y_pred',
[(metrics.Precision(), sk_metrics.precision_score,
[True, False, True, True, True], [True, True, False, True, True]),
(metrics.MacroPrecision(),
functools.partial(sk_metrics.precision_score,
average='macro'), [0, 1, 2, 2, 2], [0, 0, 2, 2, 1]),
(metrics.MicroPrecision(),
functools.partial(sk_metrics.precision_score,
average='micro'), [0, 1, 2, 2, 2], [0, 0, 2, 2, 1]),
(metrics.Recall(), sk_metrics.recall_score,
[True, False, True, True, True], [True, True, False, True, True]),
(metrics.MacroRecall(),
functools.partial(sk_metrics.recall_score,
average='macro'), [0, 1, 2, 2, 2], [0, 0, 2, 2, 1]),
(metrics.MicroRecall(),
functools.partial(sk_metrics.recall_score,
average='micro'), [0, 1, 2, 2, 2], [0, 0, 2, 2, 1]),
(metrics.FBeta(beta=0.5),
functools.partial(sk_metrics.fbeta_score, beta=0.5),
[True, False, True, True, True], [True, True, False, True, True]),
(metrics.MacroFBeta(beta=0.5),
functools.partial(sk_metrics.fbeta_score, beta=0.5,
y_pred = [np.random.dirichlet(np.ones(3)).tolist() for _ in range(n)]
yield y_true, y_pred, sample_weights
if isinstance(metric, base.RegressionMetric):
yield (
[random.random() for _ in range(n)],
[random.random() for _ in range(n)],
sample_weights
)
TEST_CASES = [
(metrics.Accuracy(), sk_metrics.accuracy_score),
(metrics.Precision(), sk_metrics.precision_score),
(metrics.MacroPrecision(), functools.partial(sk_metrics.precision_score, average='macro')),
(metrics.MicroPrecision(), functools.partial(sk_metrics.precision_score, average='micro')),
(metrics.WeightedPrecision(), functools.partial(sk_metrics.precision_score, average='weighted')),
(metrics.Recall(), sk_metrics.recall_score),
(metrics.MacroRecall(), functools.partial(sk_metrics.recall_score, average='macro')),
(metrics.MicroRecall(), functools.partial(sk_metrics.recall_score, average='micro')),
(metrics.WeightedRecall(), functools.partial(sk_metrics.recall_score, average='weighted')),
(metrics.FBeta(beta=.5), functools.partial(sk_metrics.fbeta_score, beta=.5)),
(metrics.MacroFBeta(beta=.5), functools.partial(sk_metrics.fbeta_score, beta=.5, average='macro')),
(metrics.MicroFBeta(beta=.5), functools.partial(sk_metrics.fbeta_score, beta=.5, average='micro')),
(metrics.WeightedFBeta(beta=.5), functools.partial(sk_metrics.fbeta_score, beta=.5, average='weighted')),
(metrics.F1(), sk_metrics.f1_score),
(metrics.MacroF1(), functools.partial(sk_metrics.f1_score, average='macro')),
(metrics.MicroF1(), functools.partial(sk_metrics.f1_score, average='micro')),
(metrics.WeightedF1(), functools.partial(sk_metrics.f1_score, average='weighted')),
(metrics.MCC(), sk_metrics.matthews_corrcoef),
(metrics.MAE(), sk_metrics.mean_absolute_error),