.. _auto_dataset_bootstrap_sampling:

*DATASET BOOTSTRAP SAMPLING*
============================

Performs bootstrap resampling on a dataset to estimate statistical properties (mean, standard deviation, or raw samples) for selected columns with a configurable confidence interval. Use this worker when you need robust distributional estimates or confidence bounds from an existing tabular dataset without making parametric assumptions.

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

Classification: **process**.

Tagged: ``bootstrap``, ``confidence_interval``, ``mean``, ``monte_carlo``, ``resampling``, ``sampling``, ``standard_deviation``, ``statistics``.

Inputs
------

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

   * - Label
     - ID
     - Type
     - Default
     - Required
     - Description
   * - Dataset
     - dataset_1
     - dataset
     - —
     - 
     - Input tabular dataset to be bootstrap-resampled; must contain at least the columns specified in the 'columns' input.
   * - Columns
     - columns
     - scalar
     - —
     - ✓
     - One or more column names from dataset_1 on which bootstrap statistics will be computed; multi-select list populated dynamically from the connected dataset.
   * - Number of Samples
     - num_samples
     - scalar
     - 5000
     - 
     - Number of bootstrap resample iterations to draw; default is 5000 — increase for tighter confidence estimates, decrease to reduce runtime.
   * - Confidence Interval
     - conf_int
     - select
     - 90
     - 
     - Confidence interval level (%) used to compute lower and upper bounds on the bootstrapped statistic; choose 90, 95, or 99 (default 90).
   * - Stat Type
     - stat_type
     - select
     - mean
     - 
     - Statistic to compute across bootstrap samples: 'mean' (default), 'standard deviation', or 'samples' to return the raw resampled values.
   * - Track Raw Samples
     - track_raw
     - select
     - no
     - 
     - Whether to retain all raw bootstrap sample values in the output ('yes') or return only the aggregated statistic and confidence bounds ('no', default).
   * - Return Type
     - return_type
     - select
     - mean
     - 
     - 

Outputs
-------

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

   * - Label
     - ID
     - Type
     - Description
   * - Output
     - dataset_output
     - dataset
     - Output dataset containing the bootstrapped statistic (mean or std dev) and confidence-interval bounds for each selected column, or the full raw resampled values if track_raw is enabled.

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

- data.dataset.transform
- data.statistics
- design_exploration.reliability

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

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

.. 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_bootstrap_sampling</code>. Schema hash: <code>1a4be3a0bf7f</code>. Hand-curated docs in <code>workerexamples/</code> override this page when present.
   </p>