At first glance, a false positive and a false negative can be considered as similar errors, but think about a medical prediction: while a false positive can be easily discovered with further tests, a false negative is often neglected, with repercussions as a result of this. For this reason, it's useful to introduce the concept of a confusion matrix:
The standard structure of a binary confusion matrix
In scikit-learn, it's possible to build a confusion matrix using the confusion_matrix built-in function. Let's consider a generic logistic regression on dataset X with Y labels:
X_train, X_test, Y_train, Y_test = train_test_split(X, ...
