:py:mod:`kosmos.ml.datasets.income_dataset`
===========================================

.. py:module:: kosmos.ml.datasets.income_dataset







Classes
-------

.. py:class:: IncomeDataset(*, min_max_scaler: bool = True)

   Bases: :py:class:`kosmos.ml.datasets.dataset.SLDataset`

   Adult Income (Census) dataset — binary classification (>50K vs <=50K).

   .. admonition:: Notes

      - Instances: 48,842 (32,561 train + 16,281 test)
      - Features: 14 (Mix numerical and categorical), after One-Hot-Decision more columns
      - Classes: 2 (imbalanced; ~24% >50K, ~76% <=50K)

   .. admonition:: References

      - UCI ML Repository — Adult
        https://archive.ics.uci.edu/ml/machine-learning-databases/adult/

   Initialize the dataset.

   :param min_max_scaler: Whether to apply min-max scaling to the features.
   :type min_max_scaler: bool




   |

   .. rubric:: Properties

   .. py:property:: class_names

      0 -> <=50K, 1 -> >50K.

      :type: Return human-readable class labels

   .. py:property:: input_dimension

      Number of feature columns.

   .. py:property:: output_dim

      Number of distinct classes.