How to calculate accuracy, precision, recall and f1-score? Deep learning precision recall f score, calculating precision recall, python precision recall, scikit precision recall, ml metrics to use, binary classification metrics, f score scikit, scikit-learn metrics

Here is how you can calculate accuracy, precision, recall and f1-score for your binary classification predictions, a plain vanilla implementation in python:

# i made this method based on this discussion:
# https://stackoverflow.com/questions/14117997/what-does-recall-mean-in-machine-learning
def calculate_recall_precision(label, prediction):
    true_positives = 0
    false_positives = 0
    true_negatives = 0
    false_negatives = 0

    for i in range(0, len(label)):
        if prediction[i] == 1:
            if prediction[i] == label[i]:
                true_positives += 1
            else:
                false_positives += 1
        else:
            if prediction[i] == label[i]:
                true_negatives += 1
            else:
                false_negatives += 1

    # a ratio of correctly predicted observation to the total observations
    accuracy = (true_positives + true_negatives) \
               / (true_positives + true_negatives + false_positives + false_negatives)

    # precision is "how useful the search results are"
    precision = true_positives / (true_positives + false_positives)
    # recall is "how complete the results are"
    recall = true_positives / (true_positives + false_negatives)

    f1_score = 2 / ((1 / precision) + (1 / recall))

    return accuracy, precision, recall, f1_score

# usage example:
y_true = [1, 1, 0, 1, 1]
y_pred = [0, 1, 0, 0, 1]

accuracy, precision, recall, f1_score = calculate_recall_precision(y_true, y_pred)

print("Accuracy: ", accuracy)
print("Precision: ", precision)
print("Recall: ", recall)
print("F1 score: ", f1_score)

# outputs:
# Accuracy:  0.6
# Precision:  1.0
# Recall:  0.5
# F1 score:  0.6666666666666666

And here is the same result using scikit-learn library (which allows flexibility for calculating these metrics):

from sklearn.metrics import precision_recall_fscore_support, accuracy_score

accuracy = accuracy_score(y_true, y_pred)
precision, recall, f1_score, _ = precision_recall_fscore_support(y_true, y_pred, average='binary')

print("Accuracy: ", accuracy)
print("Precision: ", precision)
print("Recall: ", recall)
print("F1 score: ", f1_score)

# outputs:
# Accuracy:  0.6
# Precision:  1.0
# Recall:  0.5
# F1 score:  0.666666666667