..
  ## AUTOGENERATED TITLE START

.. _alg-enmapbox-fitspectralanglemapper:

***********************
Fit SpectralAngleMapper
***********************

..
  ## AUTOGENERATED TITLE END

..
  ## AUTOGENERATED DESCRIPTION START

Spectral Angle Mapper \(SAM\).
`Samples <https://enmap-box.readthedocs.io/en/latest/general/glossary.html#term-sample>`_ are first normalizes to the unit sphere and then classified using nearest neighbour.
See `Docs Center > Using ENVI > Spectral Angle Mapper <https://www.nv5geospatialsoftware.com/docs/SpectralAngleMapper.html>`_ for a more details description.

..
  ## AUTOGENERATED DESCRIPTION END

The Spectral Angle Mapper (SAM) classifier works by comparing the spectral angles between the spectral signature of a pixel and reference spectral signatures for various classes. SAM is advantageous for hyperspectral image classification because it takes into account the spectral information across many narrow wavelength bands, allowing it to capture subtle differences in spectral signatures.It is particularly useful in scenarios where different materials or land cover types have similar spectral shapes but differ in their angles in hyperspectral space.

Usage:

1. Start the algorithm from the Processing Toolbox panel.

2. Select a training dataset or create one by clicking the processing algorithm icon, then click :guilabel:`run`.

    .. figure:: ../../processing_algorithms/classification/img/fitspectralangle_interface.png
       :align: center

..
  ## AUTOGENERATED PARAMETERS START

**Parameters**

:guilabel:`Classifier` [string]
    Scikit-learn python code. See `Normalizer <https://scikit-learn.org/stable/modules/generated/sklearn.preprocessing.Normalizer.html>`_, `KNeighborsClassifier <https://scikit-learn.org/stable/modules/generated/sklearn.neighbors.KNeighborsClassifier.html>`_ for information on different parameters.
    Default::

        from sklearn.pipeline import make_pipeline
        from sklearn.preprocessing import Normalizer
        from sklearn.neighbors import KNeighborsClassifier

        classifier = make_pipeline\(Normalizer\(\), KNeighborsClassifier\(n_neighbors=1\)\)

:guilabel:`Training dataset` [file]
    `Training dataset <https://enmap-box.readthedocs.io/en/latest/general/glossary.html#term-training-dataset>`_ `pickle file <https://enmap-box.readthedocs.io/en/latest/general/glossary.html#term-pickle-file>`_ used for fitting the `classifier <https://enmap-box.readthedocs.io/en/latest/general/glossary.html#term-classifier>`_. If not specified, an unfitted classifier is created.

**Outputs**

:guilabel:`Output classifier` [fileDestination]
    `Pickle file <https://enmap-box.readthedocs.io/en/latest/general/glossary.html#term-pickle-file>`_ destination.

..
  ## AUTOGENERATED PARAMETERS END

..
  ## AUTOGENERATED COMMAND USAGE START

**Command-line usage**

``>qgis_process help enmapbox:fitspectralanglemapper``::

    ----------------
    Arguments
    ----------------

    classifier: Classifier
        Default value:    from sklearn.pipeline import make_pipeline
    from sklearn.preprocessing import Normalizer
    from sklearn.neighbors import KNeighborsClassifier

    classifier = make_pipeline(Normalizer(), KNeighborsClassifier(n_neighbors=1))
        Argument type:    string
        Acceptable values:
            - String value
            - field:FIELD_NAME to use a data defined value taken from the FIELD_NAME field
            - expression:SOME EXPRESSION to use a data defined value calculated using a custom QGIS expression
    dataset: Training dataset (optional)
        Argument type:    file
        Acceptable values:
            - Path to a file
    outputClassifier: Output classifier
        Argument type:    fileDestination
        Acceptable values:
            - Path for new file

    ----------------
    Outputs
    ----------------

    outputClassifier: <outputFile>
        Output classifier

..
  ## AUTOGENERATED COMMAND USAGE END