Spaces:
Runtime error
Runtime error
File size: 4,663 Bytes
d2a8669 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 |
import os
import pandas as pd
from aif360.datasets import StandardDataset
default_mappings = {
'label_maps': [{1.0: 'Good Credit', 2.0: 'Bad Credit'}],
'protected_attribute_maps': [{1.0: 'Male', 0.0: 'Female'},
{1.0: 'Old', 0.0: 'Young'}],
}
def default_preprocessing(df):
"""Adds a derived sex attribute based on personal_status."""
# TODO: ignores the value of privileged_classes for 'sex'
status_map = {'A91': 'male', 'A93': 'male', 'A94': 'male',
'A92': 'female', 'A95': 'female'}
df['sex'] = df['personal_status'].replace(status_map)
return df
class GermanDataset(StandardDataset):
"""German credit Dataset.
See :file:`aif360/data/raw/german/README.md`.
"""
def __init__(self, label_name='credit', favorable_classes=[1],
protected_attribute_names=['sex', 'age'],
privileged_classes=[['male'], lambda x: x > 25],
instance_weights_name=None,
categorical_features=['status', 'credit_history', 'purpose',
'savings', 'employment', 'other_debtors', 'property',
'installment_plans', 'housing', 'skill_level', 'telephone',
'foreign_worker'],
features_to_keep=[], features_to_drop=['personal_status'],
na_values=[], custom_preprocessing=default_preprocessing,
metadata=default_mappings):
"""See :obj:`StandardDataset` for a description of the arguments.
By default, this code converts the 'age' attribute to a binary value
where privileged is `age > 25` and unprivileged is `age <= 25` as
proposed by Kamiran and Calders [1]_.
References:
.. [1] F. Kamiran and T. Calders, "Classifying without
discriminating," 2nd International Conference on Computer,
Control and Communication, 2009.
Examples:
In some cases, it may be useful to keep track of a mapping from
`float -> str` for protected attributes and/or labels. If our use
case differs from the default, we can modify the mapping stored in
`metadata`:
>>> label_map = {1.0: 'Good Credit', 0.0: 'Bad Credit'}
>>> protected_attribute_maps = [{1.0: 'Male', 0.0: 'Female'}]
>>> gd = GermanDataset(protected_attribute_names=['sex'],
... privileged_classes=[['male']], metadata={'label_map': label_map,
... 'protected_attribute_maps': protected_attribute_maps})
Now this information will stay attached to the dataset and can be
used for more descriptive visualizations.
"""
filepath = os.path.join(os.path.dirname(os.path.abspath(__file__)),
'..', 'data', 'raw', 'german', 'german.data')
# as given by german.doc
column_names = ['status', 'month', 'credit_history',
'purpose', 'credit_amount', 'savings', 'employment',
'investment_as_income_percentage', 'personal_status',
'other_debtors', 'residence_since', 'property', 'age',
'installment_plans', 'housing', 'number_of_credits',
'skill_level', 'people_liable_for', 'telephone',
'foreign_worker', 'credit']
try:
df = pd.read_csv(filepath, sep=' ', header=None, names=column_names,
na_values=na_values)
except IOError as err:
print("IOError: {}".format(err))
print("To use this class, please download the following files:")
print("\n\thttps://archive.ics.uci.edu/ml/machine-learning-databases/statlog/german/german.data")
print("\thttps://archive.ics.uci.edu/ml/machine-learning-databases/statlog/german/german.doc")
print("\nand place them, as-is, in the folder:")
print("\n\t{}\n".format(os.path.abspath(os.path.join(
os.path.abspath(__file__), '..', '..', 'data', 'raw', 'german'))))
import sys
sys.exit(1)
super(GermanDataset, self).__init__(df=df, label_name=label_name,
favorable_classes=favorable_classes,
protected_attribute_names=protected_attribute_names,
privileged_classes=privileged_classes,
instance_weights_name=instance_weights_name,
categorical_features=categorical_features,
features_to_keep=features_to_keep,
features_to_drop=features_to_drop, na_values=na_values,
custom_preprocessing=custom_preprocessing, metadata=metadata)
|