Implementation of polyfit and polyval

doc/api.rst

@@ -30,6 +30,7 @@ Top-level functions
    zeros_like
    ones_like
    dot
+   polyval
    map_blocks
    show_versions
    set_options
@@ -172,6 +173,7 @@ Computation
    Dataset.quantile
    Dataset.differentiate
    Dataset.integrate
+   Dataset.polyfit
 
 **Aggregation**:
 :py:attr:`~Dataset.all`
@@ -352,6 +354,7 @@ Computation
    DataArray.quantile
    DataArray.differentiate
    DataArray.integrate
+   DataArray.polyfit
    DataArray.str
 
 **Aggregation**:

doc/computation.rst

@@ -401,6 +401,32 @@ trapezoidal rule using their coordinates,
     and integration along multidimensional coordinate are not supported.
 
 
+.. _compute.polyfit:
+
+Fitting polynomials
+===================
+
+Xarray objects provide an interface for performing linear or polynomial regressions
+using the least-squares method. :py:meth:`~xarray.DataArray.polyfit` computes the
+best fitting coefficients along a given dimension and for a given order,
+
+.. ipython:: python
+
+    x = xr.DataArray(np.arange(10), dims=['x'], name='x')
+    a = xr.DataArray(3 + 4 * x, dims=['x'], coords={'x': x})
+    out = a.polyfit(dim='x', deg=1, full=True)
+    out
+
+The method outputs a dataset containing the coefficients (and more if `full=True`).
+The inverse operation is done with :py:meth:`~xarray.polyval`,
+
+.. ipython:: python
+
+    xr.polyval(coord=x, coeffs=out.polyfit_coefficients)
+
+.. note::
+    These methods replicate the behaviour of :py:func:`numpy.polyfit` and :py:func:`numpy.polyval`.
+
 .. _compute.broadcasting:
 
 Broadcasting by dimension name

doc/whats-new.rst

@@ -24,6 +24,8 @@ Breaking changes
 
 New Features
 ~~~~~~~~~~~~
+- Added :py:meth:`DataArray.polyfit` and :py:func:`xarray.polyval` for fitting polynomials. (:issue:`3349`)
+  By `Pascal Bourgault <https://github.com/aulemahal>`_.
 - Control over attributes of result in :py:func:`merge`, :py:func:`concat`,
   :py:func:`combine_by_coords` and :py:func:`combine_nested` using
   combine_attrs keyword argument. (:issue:`3865`, :pull:`3877`)

xarray/__init__.py

@@ -17,7 +17,7 @@
 from .core.alignment import align, broadcast
 from .core.combine import auto_combine, combine_by_coords, combine_nested
 from .core.common import ALL_DIMS, full_like, ones_like, zeros_like
-from .core.computation import apply_ufunc, dot, where
+from .core.computation import apply_ufunc, dot, polyval, where
 from .core.concat import concat
 from .core.dataarray import DataArray
 from .core.dataset import Dataset
@@ -65,6 +65,7 @@
     "open_mfdataset",
     "open_rasterio",
     "open_zarr",
+    "polyval",
     "register_dataarray_accessor",
     "register_dataset_accessor",
     "save_mfdataset",

xarray/core/computation.py

@@ -1306,3 +1306,35 @@ def where(cond, x, y):
         dataset_join="exact",
         dask="allowed",
     )
+
+
+def polyval(coord, coeffs, degree_dim="degree"):
+    """Evaluate a polynomial at specific values
+
+    Parameters
+    ----------
+    coord : DataArray
+        The 1D coordinate along which to evaluate the polynomial.
+    coeffs : DataArray
+        Coefficients of the polynomials.
+    degree_dim : str, default "degree"
+        Name of the polynomial degree dimension in `coeffs`.
+
+    See also
+    --------
+    xarray.DataArray.polyfit
+    numpy.polyval
+    """
+    from .dataarray import DataArray
+    from .missing import get_clean_interp_index
+
+    x = get_clean_interp_index(coord, coord.name)
+
+    deg_coord = coeffs[degree_dim]
+
+    lhs = DataArray(
+        np.vander(x, int(deg_coord.max()) + 1),
+        dims=(coord.name, degree_dim),
+        coords={coord.name: coord, degree_dim: np.arange(deg_coord.max() + 1)[::-1]},
+    )
+    return (lhs * coeffs).sum(degree_dim)

xarray/core/dask_array_ops.py

@@ -95,3 +95,30 @@ def func(x, window, axis=-1):
     # crop boundary.
     index = (slice(None),) * axis + (slice(drop_size, drop_size + orig_shape[axis]),)
     return out[index]
+
+
+def least_squares(lhs, rhs, rcond=None, skipna=False):
+    import dask.array as da
+
+    lhs_da = da.from_array(lhs, chunks=(rhs.chunks[0], lhs.shape[1]))
+    if skipna:
+        added_dim = rhs.ndim == 1
+        if added_dim:
+            rhs = rhs.reshape(rhs.shape[0], 1)
+        results = da.apply_along_axis(
+            nputils._nanpolyfit_1d,
+            0,
+            rhs,
+            lhs_da,
+            dtype=float,
+            shape=(lhs.shape[1] + 1,),
+            rcond=rcond,
+        )
+        coeffs = results[:-1, ...]
+        residuals = results[-1, ...]
+        if added_dim:
+            coeffs = coeffs.reshape(coeffs.shape[0])
+            residuals = residuals.reshape(residuals.shape[0])
+    else:
+        coeffs, residuals, _, _ = da.linalg.lstsq(lhs_da, rhs)
+    return coeffs, residuals

xarray/core/dataarray.py

@@ -3275,6 +3275,68 @@ def map_blocks(
 
         return map_blocks(func, self, args, kwargs)
 
+    def polyfit(
+        self,
+        dim: Hashable,
+        deg: int,
+        skipna: bool = None,
+        rcond: float = None,
+        w: Union[Hashable, Any] = None,
+        full: bool = False,
+        cov: bool = False,
+    ):
+        """
+        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, 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, optional
+            Relative condition number to the fit.
+        w : Union[Hashable, Any], 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, optional
+            Whether to return the residuals, matrix rank and singular values in addition
+            to the coefficients.
+        cov : Union[bool, str], optional
+            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`)
+            [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
+        """
+        return self._to_temp_dataset().polyfit(
+            dim, deg, skipna=skipna, rcond=rcond, w=w, full=full, cov=cov
+        )
+
     def pad(
         self,
         pad_width: Mapping[Hashable, Union[int, Tuple[int, int]]] = None,