I have a dataset of 21 variables and 75 datapoints/rows. I am trying to investigate the mutual information between each pair of variables. I have used the mutual_info_score function in sklearn.metrics and this returns a number that is more than 0. How do I know which values of the value of mutual_info_score reflect dependency? For example how do you know whether to only explore the values of 1 and above, or 2 and above etc. Continue reading...
