.. DO NOT EDIT.
.. THIS FILE WAS AUTOMATICALLY GENERATED BY SPHINX-GALLERY.
.. TO MAKE CHANGES, EDIT THE SOURCE PYTHON FILE:
.. "_examples/00_basic_simai_ex/01-build_model.py"
.. LINE NUMBERS ARE GIVEN BELOW.

.. only:: html

    .. note::
        :class: sphx-glr-download-link-note

        :ref:`Go to the end <sphx_glr_download__examples_00_basic_simai_ex_01-build_model.py>`
        to download the full example code.

.. rst-class:: sphx-glr-example-title

.. _sphx_glr__examples_00_basic_simai_ex_01-build_model.py:

.. _ref_basic_build_model:

Building a SimAI Model
============================================

This example demonstrates how to configure a SimAI model with inputs, outputs, global coefficients,
and domain of analysis, then start the model training process.

Before you begin
-------------------------------------------

- Complete ":ref:`ref_basic_create_project_upload_data`" to create a project with training data.
- Ensure all training data in your project are ready (processed successfully).
- Know the names of surfaces and boundary conditions in your training data.
- Determine which global coefficients you want to calculate.

.. GENERATED FROM PYTHON SOURCE LINES 42-44

Import necessary libraries
-------------------------------------------

.. GENERATED FROM PYTHON SOURCE LINES 44-54

.. code-block:: Python


    import ansys.simai.core as asc
    from ansys.simai.core.data.model_configuration import (
        DomainOfAnalysis,
        GlobalCoefficientDefinition,
        ModelConfiguration,
        ModelInput,
        ModelOutput,
    )


.. GENERATED FROM PYTHON SOURCE LINES 55-58

Configure your settings
-------------------------------------------
Update these variables with your specific settings:

.. GENERATED FROM PYTHON SOURCE LINES 58-62

.. code-block:: Python


    ORGANIZATION_NAME = "<your_organization>"  # Replace with your organization name
    PROJECT_NAME = "<your_project_name>"  # Replace with your project name


.. GENERATED FROM PYTHON SOURCE LINES 63-66

Initialize the client and get the project
-------------------------------------------
Connect to SimAI:

.. GENERATED FROM PYTHON SOURCE LINES 66-69

.. code-block:: Python


    simai_client = asc.SimAIClient(organization=ORGANIZATION_NAME)


.. GENERATED FROM PYTHON SOURCE LINES 70-71

Retrieve the project by name:

.. GENERATED FROM PYTHON SOURCE LINES 71-75

.. code-block:: Python


    project = simai_client.projects.get(name=PROJECT_NAME)
    print(f"Using existing project: {PROJECT_NAME}")


.. GENERATED FROM PYTHON SOURCE LINES 76-80

Configure model inputs
-------------------------------------------
Define which surfaces and boundary conditions the model will use as inputs.
Replace the placeholder names with the actual names from your training data:

.. GENERATED FROM PYTHON SOURCE LINES 80-86

.. code-block:: Python


    model_input = ModelInput(
        surface=["<your_surface_name>"],  # List of surface names to use as input
        boundary_conditions=["<your_BC_name>"],  # List of boundary condition names
    )


.. GENERATED FROM PYTHON SOURCE LINES 87-91

Configure model outputs
-------------------------------------------
Define which surfaces the model will predict.
These are typically the same surfaces as the inputs, but you can specify different ones:

.. GENERATED FROM PYTHON SOURCE LINES 91-96

.. code-block:: Python


    model_output = ModelOutput(
        surface=["<your_surface_name>"],  # List of surface names to predict
    )


.. GENERATED FROM PYTHON SOURCE LINES 97-107

Define global coefficients
-------------------------------------------

Global coefficients are scalar values calculated from the prediction results.
They can be used to extract key performance indicators from your simulations.

In this example, we calculate the integral of a field called "Photometric".
You can define multiple global coefficients with different formulas.

Available locations: ``"points"`` or ``"cells"``.

.. GENERATED FROM PYTHON SOURCE LINES 107-116

.. code-block:: Python


    global_coefficients = [
        GlobalCoefficientDefinition(
            name="<your_global_coefficient_name>",  # Name for this global coefficient
            formula="integral(Photometric)",  # Formula to calculate the global coefficient value
            gc_location="points",  # Calculate at points (or at "cells")
        )
    ]


.. GENERATED FROM PYTHON SOURCE LINES 117-129

Define domain of analysis
-------------------------------------------
The domain of analysis specifies the spatial extent that the model will analyze.
Values can be specified as absolute dimensions or relative to minimum values.

Format: reference_type, min_value, max_value

- ``reference_type``: ``"relative_to_min"``, ``"relative_to_max"``, ``"relative_to_center``" or ``"absolute"``.
- ``min_value``: minimum dimension value.
- ``max_value``: maximum dimension value.

You can find appropriate values by analyzing your training data in the SimAI platform.

.. GENERATED FROM PYTHON SOURCE LINES 129-136

.. code-block:: Python


    doa = DomainOfAnalysis(
        length=("relative_to_min", 0.102, 1.219),  # Length bounds
        width=("relative_to_min", 0.102, 1.219),  # Width bounds
        height=("relative_to_min", 0.134, 1.61),  # Height bounds
    )


.. GENERATED FROM PYTHON SOURCE LINES 137-147

Create model configuration
-------------------------------------------
Combine all the configuration elements into a ModelConfiguration object.

Build presets determine the training duration:

- ``debug``: Quick training for testing.
- ``1_day``: Short training.
- ``2_days``: Standard training (recommended).
- ``7_days``: Maximum training for best accuracy.

.. GENERATED FROM PYTHON SOURCE LINES 147-159

.. code-block:: Python



    mdl_conf = ModelConfiguration(
        project=project,  # Project containing the training data
        build_preset="1_day",  # Duration of the build
        build_on_top=False,  # Start training from scratch
        input=model_input,  # Model input configuration
        output=model_output,  # Model output configuration
        global_coefficients=global_coefficients,  # Global coefficient definitions
        domain_of_analysis=doa,  # Domain of analysis bounds
    )


.. GENERATED FROM PYTHON SOURCE LINES 160-163

Verify and build the model
-------------------------------------------
Before building, check if the project meets all requirements for training:

.. GENERATED FROM PYTHON SOURCE LINES 163-177

.. code-block:: Python


    if project.is_trainable():
        print("Project is trainable. Starting model build...")
        new_model = simai_client.models.build(mdl_conf)
        print(f"Model build started with ID: {new_model.id}")
        print(
            "The model will take some time to train. You can monitor its progress in the SimAI platform."
        )
    else:
        print("Project is not trainable. Please check the following:")
        print("- All training data must be processed successfully.")
        print("- The project must have enough training data.")
        print("- All required surfaces and boundary conditions must exist in the training data.")


.. GENERATED FROM PYTHON SOURCE LINES 178-185

Next steps
-------------------------------------------
Once your model is trained, you can:

- Monitor the training progress in the SimAI platform.
- Run predictions on new geometries: :ref:`ref_basic_run_predictions`.
- Evaluate model performance using validation data.


.. _sphx_glr_download__examples_00_basic_simai_ex_01-build_model.py:

.. only:: html

  .. container:: sphx-glr-footer sphx-glr-footer-example

    .. container:: sphx-glr-download sphx-glr-download-jupyter

      :download:`Download Jupyter notebook: 01-build_model.ipynb <01-build_model.ipynb>`

    .. container:: sphx-glr-download sphx-glr-download-python

      :download:`Download Python source code: 01-build_model.py <01-build_model.py>`

    .. container:: sphx-glr-download sphx-glr-download-zip

      :download:`Download zipped: 01-build_model.zip <01-build_model.zip>`


.. only:: html

 .. rst-class:: sphx-glr-signature

    `Gallery generated by Sphinx-Gallery <https://sphinx-gallery.github.io>`_