FBeta¶
Binary F-Beta score.
The FBeta score is a weighted harmonic mean between precision and recall. The higher the beta
value, the higher the recall will be taken into account. When beta
equals 1, precision and recall and equivalently weighted, which results in the F1 score (see metrics.F1
).
Parameters¶
-
beta
Type → float
Weight of precision in the harmonic mean.
-
cm
Default →
None
This parameter allows sharing the same confusion matrix between multiple metrics. Sharing a confusion matrix reduces the amount of storage and computation time.
-
pos_val
Default →
True
Value to treat as "positive".
Attributes¶
-
precision (metrics.Precision)
-
recall (metrics.Recall)
Examples¶
from river import metrics
y_true = [False, False, False, True, True, True]
y_pred = [False, False, True, True, False, False]
metric = metrics.FBeta(beta=2)
for yt, yp in zip(y_true, y_pred):
metric.update(yt, yp)
metric
FBeta: 35.71%
Methods¶
get
Return the current value of the metric.
is_better_than
Indicate if the current metric is better than another one.
Parameters
- other
revert
Revert the metric.
Parameters
- y_true — 'bool'
- y_pred — 'bool | float | dict[bool, float]'
- w — defaults to
1.0
update
Update the metric.
Parameters
- y_true — 'bool'
- y_pred — 'bool | float | dict[bool, float]'
- w — defaults to
1.0
works_with
Indicates whether or not a metric can work with a given model.
Parameters
- model — 'base.Estimator'