.. _auto_mathmodel_library_predict:

*PREDICT FROM LIBRARY MATHMODEL*
================================

Loads a saved math model from the d3VIEW model library and runs inference on a supplied dataset, returning predictions and associated metadata. Use this worker when you want to apply a previously trained and stored ML model to new input data without retraining.

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

Tagged: ``inference``, ``library``, ``lucy``, ``mathmodel``, ``ml``, ``predict``, ``prediction``.

Inputs
------

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

   * - Label
     - ID
     - Type
     - Default
     - Required
     - Description
   * - Mathmodel
     - mathmodel_id
     - remote_lookup
     - —
     - 
     - Remote lookup reference to the saved math model in the d3VIEW library; select the target model whose serialized file will be loaded for inference.
   * - Dataset
     - dataset
     - dataset
     - —
     - ✓
     - Tabular input dataset containing the feature columns required by the selected model; schema is validated against the chosen math model — all required feature columns must be present.

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 traceability and downstream wiring.
   * - LUCY JSON
     - lucy_json
     - json
     - Raw LUCY ML JSON envelope returned by the inference engine, containing full response payload including stdout, metadata, and per-item results.
   * - Meta Info
     - meta_info
     - dataset
     - Dataset summarising run-level metadata (e.g., model name, version, prediction timestamp) produced by the LUCY wrapper.
   * - Predicted Dataset
     - dataset
     - dataset
     - Output dataset of predicted values keyed by the original row IDs from the input dataset; each row corresponds to one input observation with its model-generated prediction appended.

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

- ai_ml.model_selection
- 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_library_predict</code>. Schema hash: <code>99c90915b189</code>. Hand-curated docs in <code>workerexamples/</code> override this page when present.
   </p>