.. _auto_curves_reconstruct_from_prediction:

*USING PREDICTED VALUES FROM ML, RE-CONSTRUCT A CURVE BY INTERPOLATING FROM CURVES USED IN TRAINING*
====================================================================================================

Given a set of training curves and ML-predicted scalar values, reconstructs a new curve by interpolating across the training curve group at the predicted points. Use this worker to materialise a curve prediction produced by an upstream regression or surrogate model.

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

Classification: **process**.

Tagged: ``curve_group``, ``curve_reconstruction``, ``interpolation``, ``ml_prediction``, ``surrogate``, ``transformations``.

Inputs
------

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

   * - Label
     - ID
     - Type
     - Default
     - Required
     - Description
   * - Curve Group
     - curvegroup
     - vector
     - —
     - 
     - Collection of training curves (vector/curve-group format) from which the reconstructed curve is interpolated; must contain the curves that were used during ML model training.
   * - prediction_points
     - prediction_points
     - string
     - —
     - 
     - JSON-serialised or comma-separated string of ML-predicted scalar values (e.g. feature coordinates) that define the interpolation point within the training curve space; leave empty if not yet available from an upstream model.

Outputs
-------

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

   * - Label
     - ID
     - Type
     - Description
   * - curves_reconstruct_from_prediction_output_1
     - curves_reconstruct_from_prediction_output_1
     - vector
     - Reconstructed curve obtained by interpolating the training curve group at the supplied prediction points; format matches the input curve-group vector type.

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

- ai_ml.supervised.regression
- ai_ml.surrogate
- data.curve.pair
- data.curve.transform

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

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

.. raw:: html

   <hr style="margin-top:2em">
   <p style="font-size:11px;color:#888">
   Auto-generated from <code>transformation</code> schema. Worker id: <code>curves_reconstruct_from_prediction</code>. Schema hash: <code>8f1b94be9764</code>. Hand-curated docs in <code>workerexamples/</code> override this page when present.
   </p>