.. _auto_mathmodel_predict:

*PREDICT FROM SAVED MATHMODEL*
==============================

Loads a previously saved math model (ML model persisted in the d3VIEW platform) and runs inference against a supplied dataset, returning predictions alongside LUCY ML diagnostics. Use this worker whenever a trained model needs to be applied to new input data within a workflow.

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

Tagged: ``inference``, ``lucy``, ``mathmodel``, ``ml``, ``predict``, ``scoring``.

Inputs
------

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

   * - Label
     - ID
     - Type
     - Default
     - Required
     - Description
   * - Mathmodel
     - mathmodel_id
     - remote_lookup
     - —
     - 
     - Reference to the saved math model to use for inference; selected via the remote lookup widget keyed to 'remote_lookup_mathmodels' — leave null to resolve dynamically from an upstream worker.
   * - Dataset
     - dataset
     - dataset
     - —
     - ✓
     - Input dataset whose rows will be scored; column schema must match the feature schema the math model was trained on (validated at runtime against mathmodel_id).

Outputs
-------

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

   * - Label
     - ID
     - Type
     - Description
   * - Mathmodel
     - mathmodel_id
     - integer
     - Integer identifier of the math model that was used for prediction, passed through for downstream traceability.
   * - LUCY JSON
     - lucy_json
     - json
     - Raw LUCY ML JSON response containing stdout, diagnostics, and the full inference payload; useful for debugging or extracting additional model metadata.
   * - Meta Info
     - meta_info
     - dataset
     - Dataset containing auxiliary metadata returned by the LUCY ML engine (e.g., model version, run statistics, feature importances if available).
   * - Predicted Dataset
     - dataset
     - dataset
     - Predicted dataset where each row from the input is annotated with its model-predicted value(s); row IDs are preserved from the input dataset.

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

- ai_ml.supervised.classification
- ai_ml.supervised.regression
- ai_ml.surrogate

.. raw:: html

   <hr style="margin-top:2em">
   <p style="font-size:11px;color:#888">
   Auto-generated from <code>platform</code> schema. Worker id: <code>mathmodel_predict</code>. Schema hash: <code>256726b51dac</code>. Hand-curated docs in <code>workerexamples/</code> override this page when present.
   </p>