Spaces:
Runtime error
Runtime error
File size: 5,467 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 |
import os
import pandas as pd
from aif360.datasets import StandardDataset
default_mappings = {
'label_maps': [{1.0: '>50K', 0.0: '<=50K'}],
'protected_attribute_maps': [{1.0: 'White', 0.0: 'Non-white'},
{1.0: 'Male', 0.0: 'Female'}]
}
class AdultDataset(StandardDataset):
"""Adult Census Income Dataset.
See :file:`aif360/data/raw/adult/README.md`.
"""
def __init__(self, label_name='income-per-year',
favorable_classes=['>50K', '>50K.'],
protected_attribute_names=['race', 'sex'],
privileged_classes=[['White'], ['Male']],
instance_weights_name=None,
categorical_features=['workclass', 'education',
'marital-status', 'occupation', 'relationship',
'native-country'],
features_to_keep=[], features_to_drop=['fnlwgt'],
na_values=['?'], custom_preprocessing=None,
metadata=default_mappings):
"""See :obj:`StandardDataset` for a description of the arguments.
Examples:
The following will instantiate a dataset which uses the `fnlwgt`
feature:
>>> from aif360.datasets import AdultDataset
>>> ad = AdultDataset(instance_weights_name='fnlwgt',
... features_to_drop=[])
WARNING:root:Missing Data: 3620 rows removed from dataset.
>>> not np.all(ad.instance_weights == 1.)
True
To instantiate a dataset which utilizes only numerical features and
a single protected attribute, run:
>>> single_protected = ['sex']
>>> single_privileged = [['Male']]
>>> ad = AdultDataset(protected_attribute_names=single_protected,
... privileged_classes=single_privileged,
... categorical_features=[],
... features_to_keep=['age', 'education-num'])
>>> print(ad.feature_names)
['education-num', 'age', 'sex']
>>> print(ad.label_names)
['income-per-year']
Note: the `protected_attribute_names` and `label_name` are kept even
if they are not explicitly given in `features_to_keep`.
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: '>50K', 0.0: '<=50K'}
>>> protected_attribute_maps = [{1.0: 'Male', 0.0: 'Female'}]
>>> ad = AdultDataset(protected_attribute_names=['sex'],
... categorical_features=['workclass', 'education', 'marital-status',
... 'occupation', 'relationship', 'native-country', 'race'],
... privileged_classes=[['Male']], metadata={'label_map': label_map,
... 'protected_attribute_maps': protected_attribute_maps})
Note that we are now adding `race` as a `categorical_features`.
Now this information will stay attached to the dataset and can be
used for more descriptive visualizations.
"""
train_path = os.path.join(os.path.dirname(os.path.abspath(__file__)),
'..', 'data', 'raw', 'adult', 'adult.data')
test_path = os.path.join(os.path.dirname(os.path.abspath(__file__)),
'..', 'data', 'raw', 'adult', 'adult.test')
# as given by adult.names
column_names = ['age', 'workclass', 'fnlwgt', 'education',
'education-num', 'marital-status', 'occupation', 'relationship',
'race', 'sex', 'capital-gain', 'capital-loss', 'hours-per-week',
'native-country', 'income-per-year']
try:
train = pd.read_csv(train_path, header=None, names=column_names,
skipinitialspace=True, na_values=na_values)
test = pd.read_csv(test_path, header=0, names=column_names,
skipinitialspace=True, 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/adult/adult.data")
print("\thttps://archive.ics.uci.edu/ml/machine-learning-databases/adult/adult.test")
print("\thttps://archive.ics.uci.edu/ml/machine-learning-databases/adult/adult.names")
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', 'adult'))))
import sys
sys.exit(1)
df = pd.concat([test, train], ignore_index=True)
super(AdultDataset, 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)
|