arrakis.utils.fitting
=====================

.. py:module:: arrakis.utils.fitting

.. autoapi-nested-parse::

   Fitting utilities

   ..
       !! processed by numpydoc !!


Functions
---------

.. autoapisummary::

   arrakis.utils.fitting.best_aic_func
   arrakis.utils.fitting.chi_squared
   arrakis.utils.fitting.curved_power_law
   arrakis.utils.fitting.fit_pl
   arrakis.utils.fitting.fitted_mean
   arrakis.utils.fitting.fitted_std
   arrakis.utils.fitting.flat_power_law
   arrakis.utils.fitting.power_law


Module Contents
---------------

.. py:function:: best_aic_func(aics: numpy.ndarray, n_param: numpy.ndarray) -> tuple[float, int, int]

   
   Find the best AIC for a set of AICs using Occam's razor.
















   ..
       !! processed by numpydoc !!

.. py:function:: chi_squared(model: numpy.ndarray, data: numpy.ndarray, error: numpy.ndarray) -> float

   
   Calculate chi squared.

   :Parameters: * **model** (*np.ndarray*) -- Model flux.
                * **data** (*np.ndarray*) -- Data flux.
                * **error** (*np.ndarray*) -- Data error.

   :returns: Chi squared.
   :rtype: np.ndarray















   ..
       !! processed by numpydoc !!

.. py:function:: curved_power_law(nu: numpy.ndarray, norm: float, alpha: float, beta: float, ref_nu: float) -> numpy.ndarray

   
   A curved power law model.

   :Parameters: * **nu** (*np.ndarray*) -- Frequency array.
                * **norm** (*float*) -- Reference flux.
                * **alpha** (*float*) -- Spectral index.
                * **beta** (*float*) -- Spectral curvature.
                * **ref_nu** (*float*) -- Reference frequency.

   :returns: Model flux.
   :rtype: np.ndarray















   ..
       !! processed by numpydoc !!

.. py:function:: fit_pl(freq: numpy.ndarray, flux: numpy.ndarray, fluxerr: numpy.ndarray, nterms: int) -> dict

   
   Perform a power law fit to a spectrum.

   :Parameters: * **freq** (*np.ndarray*) -- Frequency array.
                * **flux** (*np.ndarray*) -- Flux array.
                * **fluxerr** (*np.ndarray*) -- Error array.
                * **nterms** (*int*) -- Number of terms to use in the fit.

   :returns: Best fit parameters.
   :rtype: dict















   ..
       !! processed by numpydoc !!

.. py:function:: fitted_mean(data: numpy.ndarray, axis: int | None = None) -> float

   
   Calculate the mean of a distribution.

   :Parameters: **data** (*np.ndarray*) -- Data array.

   :returns: Mean.
   :rtype: float















   ..
       !! processed by numpydoc !!

.. py:function:: fitted_std(data: numpy.ndarray, axis: int | None = None) -> float

   
   Calculate the standard deviation of a distribution.

   :Parameters: **data** (*np.ndarray*) -- Data array.

   :returns: Standard deviation.
   :rtype: float















   ..
       !! processed by numpydoc !!

.. py:function:: flat_power_law(nu: numpy.ndarray, norm: float, ref_nu: float) -> numpy.ndarray

   
   A flat power law model.

   :Parameters: * **nu** (*np.ndarray*) -- Frequency array.
                * **norm** (*float*) -- Reference flux.
                * **ref_nu** (*float*) -- Reference frequency.

   :returns: Model flux.
   :rtype: np.ndarray















   ..
       !! processed by numpydoc !!

.. py:function:: power_law(nu: numpy.ndarray, norm: float, alpha: float, ref_nu: float) -> numpy.ndarray

   
   A power law model.

   :Parameters: * **nu** (*np.ndarray*) -- Frequency array.
                * **norm** (*float*) -- Reference flux.
                * **alpha** (*float*) -- Spectral index.
                * **ref_nu** (*float*) -- Reference frequency.

   :returns: Model flux.
   :rtype: np.ndarray















   ..
       !! processed by numpydoc !!