diversity_percentage.py

def diversity_percentage(df, columns):
    """
    This function returns the number of different elements in each column as a percentage of the total elements in the group.
    A low value indicates there are many repeated elements.
    Example 1: a value of 0 indicates all values are the same.
    Example 2: a value of 100 indicates all values are different.
    """
    diversity = dict()

    for col in columns:
        diversity[col] = len(df[col].unique())

    diversity_series = pd.Series(diversity)
    return (100*diversity_series/len(df)).sort_values()