Module imodels.skrules.datasets

Expand source code
from .credit_data import load_credit_data

__all__ = ['load_credit_data']

Sub-modules

imodels.skrules.datasets.credit_data

default of credit card clients dataset …

Functions

def load_credit_data()
Expand source code
def load_credit_data():
    sk_data_dir = get_data_home()
    archive = RemoteFileMetadata(
        filename='default of credit card clients.xls',
        url='https://archive.ics.uci.edu/ml/machine-learning-databases/'
            '00350/default%20of%20credit%20card%20clients.xls',
        checksum=('30c6be3abd8dcfd3e6096c828bad8c2f'
                  '011238620f5369220bd60cfc82700933'))

    if not exists(join(sk_data_dir, archive.filename)):
        _fetch_remote(archive, dirname=sk_data_dir)

    data = pd.read_excel(join(sk_data_dir, archive.filename),
                         sheet_name='Data', header=1)

    dataset = Bunch(
        data=(data.drop('default payment next month', axis=1)),
        target=np.array(data['default payment next month'])
        )
    return dataset