bias.py

def bias_replace_missing_with_avg(data_set):
    '''
    For some reason, this is my longest function.
    It's all the partitioning and partition undoing.

    Replace 'None' values (missing values) with the average of all existing
    values for that attribute.
    '''
    notNone = lambda x: x is not None

    partitioned_by_attr = [
        (mean(filter(notNone, attr_values)), attr_values)
        for attr_values in [ getall(data_set, attr) for attr in
                            range(len(data_set[0])) ]
    ]

    filled_in = [
        [ avg if value is None else value for value in values ]
        for (avg, values) in partitioned_by_attr
    ]

    return [
        [ biased_attr_values[i] for biased_attr_values in filled_in ]
        for i in range(len(data_set))
    ]