Provide a parameter in order to decide if `None`/`np.nan` should be considered missing value or normal value

[smarie]

Two different concepts:

• A missing value should not be used in calculations of entropy or conditional entropies, and should be only used as "last resort" in the feature selection model (Series.mode have a flag to ignore nans)
• a "none" level, if considered an acceptable value, should be used in entropy calculations and in the calculation of mode in the feature selection model.

[smarie]

Maybe we just need two parameters: "ignore_missing_values=True" and "missing_value=np.nan". The second can be changed for example to "N/A"