8.19.2.8. sklearn.metrics.fbeta_score

sklearn.metrics.fbeta_score(y_true, y_pred, beta, labels=None, pos_label=1, average='weighted')

Compute the F-beta score

The F-beta score is the weighted harmonic mean of precision and recall, reaching its optimal value at 1 and its worst value at 0.

The beta parameter determines the weight of precision in the combined score. beta < 1 lends more weight to precision, while beta > 1 favors precision (beta == 0 considers only precision, beta == inf only recall).

Parameters :

y_true : array-like or list of labels or label indicator matrix

Ground truth (correct) target values.

y_true : array-like or list of labels or label indicator matrix

Estimated targets as returned by a classifier.

beta: float :

Weight of precision in harmonic mean.

labels : array

Integer array of labels.

pos_label : int, 1 by default

If average is not None and the classification target is binary, only this class’s scores will be returned. In multilabel classification, it is used to infer what is a positive label in the label indicator matrix format.

average : string, [None, ‘micro’, ‘macro’, ‘samples’, ‘weighted’ (default)]

If None, the scores for each class are returned. Otherwise, unless pos_label is given in binary classification, this determines the type of averaging performed on the data:

'samples':

Average over instance. Only meaningful and available in multilabel classification.

'macro':

Average over classes (does not take imbalance into account).

'micro':

Aggregate classes and average over instances (takes imbalance into account). This implies that precision == recall == F1. In multilabel classification, this is true only if every sample has a label.

'weighted':

Average over classes weighted by support (takes imbalance into account). Can result in F-score that is not between precision and recall.

Returns :

fbeta_score : float (if average is not None) or array of float, shape = [n_unique_labels]

F-beta score of the positive class in binary classification or weighted average of the F-beta score of each class for the multiclass task.

References

[R127]R. Baeza-Yates and B. Ribeiro-Neto (2011). Modern Information Retrieval. Addison Wesley, pp. 327-328.
[R128]Wikipedia entry for the F1-score

Examples

In the binary case:

>>> from sklearn.metrics import fbeta_score
>>> y_pred = [0, 1, 0, 0]
>>> y_true = [0, 1, 0, 1]
>>> fbeta_score(y_true, y_pred, beta=0.5)  
0.83...
>>> fbeta_score(y_true, y_pred, beta=1)  
0.66...
>>> fbeta_score(y_true, y_pred, beta=2)  
0.55...

In the multiclass case:

>>> from sklearn.metrics import fbeta_score
>>> y_true = [0, 1, 2, 0, 1, 2]
>>> y_pred = [0, 2, 1, 0, 0, 1]
>>> fbeta_score(y_true, y_pred, average='macro', beta=0.5)
... 
0.23...
>>> fbeta_score(y_true, y_pred, average='micro', beta=0.5)
... 
0.33...
>>> fbeta_score(y_true, y_pred, average='weighted', beta=0.5)
... 
0.23...
>>> fbeta_score(y_true, y_pred, average=None, beta=0.5)
... 
array([ 0.71...,  0.        ,  0.        ])

In the multilabel case with binary indicator format:

>>> from sklearn.metrics import fbeta_score
>>> y_true = np.array([[0.0, 1.0, 0.0], [1.0, 1.0, 0.0], [0.0, 0.0, 1.0]])
>>> y_pred = np.ones((3, 3))
>>> fbeta_score(y_true, y_pred, average='macro', beta=0.5)
... 
0.49...
>>> fbeta_score(y_true, y_pred, average='micro', beta=0.5)
0.5
>>> fbeta_score(y_true, y_pred, average='weighted', beta=0.5)
... 
0.54...
>>> fbeta_score(y_true, y_pred, average='samples', beta=0.5)
... 
0.66...
>>> fbeta_score(y_true, y_pred, average=None, beta=0.5)
... 
array([ 0.38...,  0.71...,  0.38...])

and with a list of labels format:

>>> from sklearn.metrics import fbeta_score
>>> y_true = [(1, 2), (3,)]
>>> y_pred = [(1, 2), tuple()]
>>> fbeta_score(y_true, y_pred, average='macro', beta=0.5)
... 
0.66...
>>> fbeta_score(y_true, y_pred, average='micro', beta=0.5)
... 
0.90...
>>> fbeta_score(y_true, y_pred, average='weighted', beta=0.5)
... 
0.66...
>>> fbeta_score(y_true, y_pred, average='samples', beta=0.5)
... 
0.42...
>>> fbeta_score(y_true, y_pred, average=None, beta=0.5)
array([ 1.,  1.,  0.])
Previous
Next