I have been running Azure AutoML on a binary classification task. When I visualize the performance and the confusion matrix in particular, I observe the following:
How can I have decimal numbers in the raw confusion matrix? As per the documentation: A cell at row i and column j in a confusion matrix contains the **number of samples** in the evaluation dataset that belong to class C_i and were classified by the model as class C_j.
Any insights, or pointers as to where I should look into to understand what is going on, is welcome!
