Freelancer:
ikhan9985
Without train/test slip
If we want to train/test split then we should change this line: "score = int(precision_score(df["class"], predictions)*100) if sum(predictions) > 0 else 0" Which is outside of the function and you said before that we don't need to change the code... since we are measuring the df['class'] values with the Predicted ones. If we do train/test split here the numbers of actual and predicted values would be different