CODEWITHSUNDEEP
kerasscikit-learn
SonicProtein
SonicProtein

Reputation: 850

Keras metric equivalent to scikit learn's average precision score metric

I've had a look at the Keras metrics documentation and couldn't find an equivalent to scikit learn's average precision score metric (which I think is the same as the area under the precision-recall curve, AUPRC). It isn't the same as the average_precision_at_k, I believe unless someone can correct me on that.

Upvotes: 1

Views: 1668

Answers (2)

C. V.
C. V.

Reputation: 71

Late answer, but I was facing the same issue recently.

You can use the AUC metric with the parameter curve . Something like:

AUC(curve='PR')

Upvotes: 5

Amine Benatmane
Amine Benatmane

Reputation: 1261

You can implement custom metrics for keras to be passed at the compilation step. (https://keras.io/metrics/) The function would need to take (y_true, y_pred) as arguments and return a single tensor value.

Here is an implementation of average_precision for keras:

import keras.backend as K

def average_precision(y_true, y_pred):
    true_positives = K.sum(K.round(K.clip(y_true * y_pred, 0, 1)))
    predicted_positives = K.sum(K.round(K.clip(y_pred, 0, 1)))
    precision = true_positives / (predicted_positives + K.epsilon())
    return precision

Upvotes: 1

Related Questions