[ENH]: Default behavior of predict_model in classification

[moezali1]

pycaret version checks

• [X] I have checked that this issue has not already been reported here.

• [X] I have confirmed this bug exists on the latest version of pycaret.

• [X] I have confirmed this bug exists on the develop branch of pycaret (pip install -U git+https://github.com/pycaret/pycaret.git@develop).

Issue Description

I have opened this issue to discuss the default behavior of the predict_model function in the classification module.

At the moment when predict_model is called, we show the Label column and the Score column which represents the probability of predicted class as opposed to (commonly known/used) probability of positive class.

Should we take 3.0 as an opportunity to change this behavior and show the probability of predicted class as opposed to predicted class? why or why not?

Reproducible Example

.

Expected Behavior

.

Actual Results

.

Installed Versions

3.0

[tvdboom]

And what would you show with multiclass classification tasks? Since there is not one positive class... We could show the predicted probabilities of all classes

[moezali1]

Let's take a poll.