.. _auto_dataset_bin_columns:

*BIN NUMERIC COLUMNS INTO EQUAL-WIDTH BINS*
===========================================

Bins the values of the selected numeric columns into a fixed number of equal-width bins, mapping each value to a bin number from 1 to N. Use it to discretize continuous features for analysis or ML. Choose to add the binned values as new columns or overwrite the originals.

When to use
-----------

Classification: **process**.

Tagged: ``bin``, ``binning``, ``discretize``, ``dataset``, ``columns``, ``ml``, ``transform``.

Inputs
------

.. list-table::
   :header-rows: 1
   :widths: 20 20 20 20 20 20

   * - Label
     - ID
     - Type
     - Default
     - Required
     - Description
   * - Dataset
     - dataset
     - dataset
     - —
     - 
     - Input dataset whose numeric columns will be binned.
   * - Columns
     - columns
     - scalar
     - —
     - ✓
     - Comma-separated names of the numeric columns to bin.
   * - Number of bins
     - num_bins
     - scalar
     - 5
     - 
     - Number of equal-width bins; each value is mapped to a bin number from 1 to N.
   * - Mode
     - mode
     - select
     - new
     - 
     - Add binned values as new <col>_bin columns, or overwrite the original column values.
   * - Label format
     - label_format
     - select
     - range
     - 
     - How each binned value is labelled: a nicely-rounded range, an indexed range, or a simple bin number.
   * - Round minimum
     - round_min
     - select
     - no
     - 
     - When Yes, the lowest bin starts at a nicely-rounded value near the data minimum (like the maximum is rounded up) instead of snapping down to a step multiple such as zero.
   * - Rating direction
     - rating_direction
     - select
     - none
     - 
     - Tag each bin with a quality rating from best to worst. Choose which end of the value range is best. Adds a <column>_rating column.
   * - Rating columns
     - rating_columns
     - scalar
     - —
     - 
     - Comma-separated subset of the columns above to rate. Leave blank to rate all binned columns.
   * - Rating style
     - rating_style
     - select
     - words
     - 
     - How each bin rating is displayed: words, letter grade, or stars.

Outputs
-------

.. list-table::
   :header-rows: 1
   :widths: 20 20 20 20

   * - Label
     - ID
     - Type
     - Description
   * - dataset_bin_columns_output_1
     - dataset_bin_columns_output_1
     - dataset
     - The dataset with the selected columns binned (as new _bin columns or overwritten).

Disciplines
-----------

- data.dataset.transform

Runnable example
----------------

A runnable example is registered for this worker. Open the example workflow on the d3VIEW canvas: `/api/workflow/example?id=dataset_bin_columns <https://www.d3view.com/api/workflow/example?id=dataset_bin_columns>`_

.. raw:: html

   <hr style="margin-top:2em">
   <p style="font-size:11px;color:#888">
   Auto-generated from <code>transformation</code> schema. Worker id: <code>dataset_bin_columns</code>. Schema hash: <code>a6d80fb3430d</code>. Hand-curated docs in <code>workerexamples/</code> override this page when present.
   </p>