clophfit.fitting.pipeline
=========================

.. py:module:: clophfit.fitting.pipeline

.. autoapi-nested-parse::

   Pipeline orchestrators for fitting multistage workflows (e.g., FGLS).



Functions
---------

.. autoapisummary::

   clophfit.fitting.pipeline.fgls_plate_fit
   clophfit.fitting.pipeline.fit_plate


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

.. py:function:: fgls_plate_fit(datasets, sigma_floor, *, first_pass_method = 'huber', second_pass_method = 'lm', max_iter = 3, tol = 0.001)

   Run iterative Feasible Generalized Least Squares (FGLS) on a plate.

   1. First-pass fit (robust) on each well with existing ``y_errc``.
   2. Calibrate noise model from residuals, anchoring floor to *sigma_floor*.
   3. Re-apply calibrated weights, re-fit, re-calibrate — iterating until
      gain and alpha converge or *max_iter* is reached.
   4. Return final fits and the noise model from the last calibration.

   :param datasets: Plate datasets keyed by well name.
   :type datasets: dict[str, Dataset]
   :param sigma_floor: Known read-noise floor per label (e.g. from buffer wells).
   :type sigma_floor: dict[str, float]
   :param first_pass_method: Method for the first-pass fit (default ``"huber"``).
   :type first_pass_method: str
   :param second_pass_method: Method for subsequent passes (default ``"lm"``).
   :type second_pass_method: str
   :param max_iter: Maximum FGLS iterations (default 3).
   :type max_iter: int
   :param tol: Relative tolerance for gain/alpha convergence (default 1e-3).
   :type tol: float

   :returns: Final fit results keyed by well, and the converged (or last)
             calibrated noise model.
   :rtype: tuple[dict[str, FitResult[typing.Any]], PlateNoiseModel]


.. py:function:: fit_plate(datasets, method = '', **kwargs)

   Run a single-pass fit on an entire plate of datasets.

   :param datasets: A mapping of well keys (e.g. 'A01') to `Dataset` objects.
   :type datasets: dict[str, Dataset]
   :param method: The fitting method to use: 'lm' (default), 'huber', 'odr', or 'mcmc'.
                  Other methods supported by :func:`clophfit.fitting.core.fit_binding_glob`
                  may also be used.
   :type method: str
   :param \*\*kwargs: Additional keyword arguments passed to the specific fitting function.
   :type \*\*kwargs: typing.Any

   :returns: A dictionary mapping well keys to their corresponding `FitResult`.
   :rtype: dict[str, FitResult[typing.Any]]