How to use the aif360.datasets.StandardDataset function in aif360

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):

'label_maps': [{1.0: 'Did recid.', 0.0: 'No recid.'}],
    'protected_attribute_maps': [{0.0: 'Male', 1.0: 'Female'},
                                 {1.0: 'Caucasian', 0.0: 'Not Caucasian'}]
}

def default_preprocessing(df):
    """Perform the same preprocessing as the original analysis:
    https://github.com/propublica/compas-analysis/blob/master/Compas%20Analysis.ipynb
    """
    return df[(df.days_b_screening_arrest <= 30)
            & (df.days_b_screening_arrest >= -30)
            & (df.is_recid != -1)
            & (df.c_charge_degree != 'O')
            & (df.score_text != 'N/A')]

class CompasDataset(StandardDataset):
    """ProPublica COMPAS Dataset.

    See :file:`aif360/data/raw/compas/README.md`.
    """

    def __init__(self, label_name='two_year_recid', favorable_classes=[0],
                 protected_attribute_names=['sex', 'race'],
                 privileged_classes=[['Female'], ['Caucasian']],
                 instance_weights_name=None,
                 categorical_features=['age_cat', 'c_charge_degree',
                     'c_charge_desc'],
                 features_to_keep=['sex', 'age', 'age_cat', 'race',
                     'juv_fel_count', 'juv_misd_count', 'juv_other_count',
                     'priors_count', 'c_charge_degree', 'c_charge_desc',
                     'two_year_recid'],
                 features_to_drop=[], na_values=[],

'PHQ242','EMPST','POVCAT','INSCOV']] >= -1).all(1)]  #for all other categorical features, remove values < -1

    def utilization(row):
        return row['OBTOTV15'] + row['OPTOTV15'] + row['ERTOT15'] + row['IPNGTD15'] + row['HHTOTD15']

    df['TOTEXP15'] = df.apply(lambda row: utilization(row), axis=1)
    lessE = df['TOTEXP15'] < 10.0
    df.loc[lessE,'TOTEXP15'] = 0.0
    moreE = df['TOTEXP15'] >= 10.0
    df.loc[moreE,'TOTEXP15'] = 1.0

    df = df.rename(columns = {'TOTEXP15' : 'UTILIZATION'})
    return df


class MEPSDataset19(StandardDataset):
    """MEPS Dataset.

    See :file:`aif360/data/raw/meps/README.md`.
    """

    def __init__(self, label_name='UTILIZATION', favorable_classes=[1.0],
                 protected_attribute_names=['RACE'],
                 privileged_classes=[['White']],
                 instance_weights_name='PERWT15F',
                 categorical_features=['REGION','SEX','MARRY',
                                 'FTSTU','ACTDTY','HONRDC','RTHLTH','MNHLTH','HIBPDX','CHDDX','ANGIDX',
                                 'MIDX','OHRTDX','STRKDX','EMPHDX','CHBRON','CHOLDX','CANCERDX','DIABDX',
                                 'JTPAIN','ARTHDX','ARTHTYPE','ASTHDX','ADHDADDX','PREGNT','WLKLIM',
                                 'ACTLIM','SOCLIM','COGLIM','DFHEAR42','DFSEE42','ADSMOK42',
                                 'PHQ242','EMPST','POVCAT','INSCOV'],
                 features_to_keep=['REGION','AGE','SEX','RACE','MARRY',

'PHQ242','EMPST','POVCAT','INSCOV']] >= -1).all(1)]  #for all other categorical features, remove values < -1

    def utilization(row):
        return row['OBTOTV16'] + row['OPTOTV16'] + row['ERTOT16'] + row['IPNGTD16'] + row['HHTOTD16']

    df['TOTEXP16'] = df.apply(lambda row: utilization(row), axis=1)
    lessE = df['TOTEXP16'] < 10.0
    df.loc[lessE,'TOTEXP16'] = 0.0
    moreE = df['TOTEXP16'] >= 10.0
    df.loc[moreE,'TOTEXP16'] = 1.0

    df = df.rename(columns = {'TOTEXP16' : 'UTILIZATION'})
    return df


class MEPSDataset21(StandardDataset):
    """MEPS Dataset.

    See :file:`aif360/data/raw/meps/README.md`.
    """

    def __init__(self, label_name='UTILIZATION', favorable_classes=[1.0],
                 protected_attribute_names=['RACE'],
                 privileged_classes=[['White']],
                 instance_weights_name='PERWT16F',
                 categorical_features=['REGION','SEX','MARRY',
                                 'FTSTU','ACTDTY','HONRDC','RTHLTH','MNHLTH','HIBPDX','CHDDX','ANGIDX',
                                 'MIDX','OHRTDX','STRKDX','EMPHDX','CHBRON','CHOLDX','CANCERDX','DIABDX',
                                 'JTPAIN','ARTHDX','ARTHTYPE','ASTHDX','ADHDADDX','PREGNT','WLKLIM',
                                 'ACTLIM','SOCLIM','COGLIM','DFHEAR42','DFSEE42', 'ADSMOK42', 'PHQ242',
                                 'EMPST','POVCAT','INSCOV'],
                 features_to_keep=['REGION','AGE','SEX','RACE','MARRY',

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):

'PHQ242','EMPST','POVCAT','INSCOV']] >= -1).all(1)]  #for all other categorical features, remove values < -1

    def utilization(row):
        return row['OBTOTV15'] + row['OPTOTV15'] + row['ERTOT15'] + row['IPNGTD15'] + row['HHTOTD15']

    df['TOTEXP15'] = df.apply(lambda row: utilization(row), axis=1)
    lessE = df['TOTEXP15'] < 10.0
    df.loc[lessE,'TOTEXP15'] = 0.0
    moreE = df['TOTEXP15'] >= 10.0
    df.loc[moreE,'TOTEXP15'] = 1.0

    df = df.rename(columns = {'TOTEXP15' : 'UTILIZATION'})
    return df


class MEPSDataset20(StandardDataset):
    """MEPS Dataset.

    See :file:`aif360/data/raw/meps/README.md`.
    """

    def __init__(self, label_name='UTILIZATION', favorable_classes=[1.0],
                 protected_attribute_names=['RACE'],
                 privileged_classes=[['White']],
                 instance_weights_name='PERWT15F',
                 categorical_features=['REGION','SEX','MARRY',
                                 'FTSTU','ACTDTY','HONRDC','RTHLTH','MNHLTH','HIBPDX','CHDDX','ANGIDX',
                                 'MIDX','OHRTDX','STRKDX','EMPHDX','CHBRON','CHOLDX','CANCERDX','DIABDX',
                                 'JTPAIN','ARTHDX','ARTHTYPE','ASTHDX','ADHDADDX','PREGNT','WLKLIM',
                                 'ACTLIM','SOCLIM','COGLIM','DFHEAR42','DFSEE42', 'ADSMOK42', 'PHQ242',
                                 'EMPST','POVCAT','INSCOV'],
                 features_to_keep=['REGION','AGE','SEX','RACE','MARRY',

import os

import pandas as pd

from aif360.datasets import StandardDataset


class BankDataset(StandardDataset):
    """Bank marketing Dataset.

    See :file:`aif360/data/raw/bank/README.md`.
    """

    def __init__(self, label_name='y', favorable_classes=['yes'],
                 protected_attribute_names=['age'],
                 privileged_classes=[lambda x: x >= 25],
                 instance_weights_name=None,
                 categorical_features=['job', 'marital', 'education', 'default',
                     'housing', 'loan', 'contact', 'month', 'day_of_week',
                     'poutcome'],
                 features_to_keep=[], features_to_drop=[],
                 na_values=["unknown"], custom_preprocessing=None,
                 metadata=None):
        """See :obj:`StandardDataset` for a description of the arguments.