kosmos.ml.datasets.banknote_dataset

Classes

class BanknoteDataset(*, min_max_scaler: bool = True)

Bases: kosmos.ml.datasets.dataset.SLDataset

Banknote authentication dataset for binary classification.

Notes

• Number of instances: 1372

• Number of features: 4 numeric

• Classes: 2 (slightly imbalanced; 762 real, 610 forged)

References

• UCI Machine Learning Repository — Banknote authentication dataset: https://archive.ics.uci.edu/dataset/267/banknote+authentication

Initialize the dataset.

Parameters:

min_max_scaler (bool) – Whether to apply min-max scaling to the features.

Properties

property class_names

0 = Genuine, 1 = Forged.

Type:

Return human-readable class labels

property input_dimension

Number of feature columns.

property output_dim

Number of distinct classes.