xarray_coarsened_polyfit

PlasmaCalcs.tools.xarray_tools.xarray_sci.xarray_coarsened_polyfit(array, coord, degree, window_len, *, dim_coarse='window', keep_coord='middle', assign_coarse_coords=True, boundary=UNSET, side=UNSET, stride=UNSET, fill_value=UNSET, keep_attrs=UNSET, **kw_polyfit)

returns result of coarsening array, then polyfitting along the fine dimension, in each window.

E.g., make windows of length 10 along ‘t’, then polyfit each window along ‘t’,

then concat the results from each window, along dim_coarse (default: ‘window’).

coord: str

coordinate to polyfit along.

degree: int

degree of polynomial to fit.

window_len: int or None

length of window to coarsen over.

None –> polyfit without coarsening; equivalent to window_len = len(array.coords[coord])

dim_coarse: str, default ‘window’

name of coarse dimension; the i’th value here corresponds to the i’th window.

keep_coord: False or str in (‘left’, ‘right’, ‘middle’)

along the dim_coarse dimension, also provide some of the original coord values.

‘left’ –> provide the left-most value in each window.

‘middle’ –> provide the middle value in each window.

‘right’ –> provide the right-most value in each window.

False –> don’t provide any of the original coord values.

if not False, result will swap dims such that coord is a dimension instead of dim_coarse.

assign_coarse_coords: bool or coords

coords to assign along the dim_coarse dimension.

True –> use np.arange.

False –> don’t assign coords.

boundary, side: UNSET or value

if provided (not UNSET), pass this value to coarsen().

stride, fill_value, keep_attrs: UNSET or value

if provided (not UNSET), pass this value to construct().

additional **kw are passed to polyfit.

Docs for xr.DataArray.polyfit copied below:

——————————————-

Least squares polynomial fit.

This replicates the behaviour of numpy.polyfit but differs by skipping

invalid values when skipna = True.

Parameters

———-

dim : Hashable

Coordinate along which to fit the polynomials.

deg : int

Degree of the fitting polynomial.

skipna : bool or None, optional

If True, removes all invalid values before fitting each 1D slices of the array.

Default is True if data is stored in a dask.array or if there is any

invalid values, False otherwise.

rcond : float or None, optional

Relative condition number to the fit.

w : Hashable, array-like or None, optional

Weights to apply to the y-coordinate of the sample points.

Can be an array-like object or the name of a coordinate in the dataset.

full : bool, default: False

Whether to return the residuals, matrix rank and singular values in addition

to the coefficients.

cov : bool or “unscaled”, default: False

Whether to return to the covariance matrix in addition to the coefficients.

The matrix is not scaled if cov='unscaled'.

Returns

——-

polyfit_results : Dataset

A single dataset which contains:

polyfit_coefficients

The coefficients of the best fit.

polyfit_residuals

The residuals of the least-square computation (only included if full=True).

When the matrix rank is deficient, np.nan is returned.

[dim]_matrix_rank

The effective rank of the scaled Vandermonde coefficient matrix (only included if full=True)

[dim]_singular_value

The singular values of the scaled Vandermonde coefficient matrix (only included if full=True)

polyfit_covariance

The covariance matrix of the polynomial coefficient estimates (only included if full=False and cov=True)

See Also

——–

numpy.polyfit

numpy.polyval

xarray.polyval

DataArray.curvefit