image-match/python/py/Lib/site-packages/scipy/signal/_savitzky_golay.py

from scipy._lib._util import float_factorial
from scipy._lib.array_api_compat import numpy as np_compat
from scipy._lib._array_api import array_namespace, xp_swapaxes, xp_device
import scipy._lib.array_api_extra as xpx

from scipy.ndimage import convolve1d  # type: ignore[attr-defined]
from scipy.signal import _polyutils as _pu
from ._arraytools import axis_slice


def savgol_coeffs(window_length, polyorder, deriv=0, delta=1.0, pos=None,
                  use="conv", *, xp=None, device=None):
    """Compute the coefficients for a 1-D Savitzky-Golay FIR filter.

    Parameters
    ----------
    window_length : int
        The length of the filter window (i.e., the number of coefficients).
    polyorder : int
        The order of the polynomial used to fit the samples.
        `polyorder` must be less than `window_length`.
    deriv : int, optional
        The order of the derivative to compute. This must be a
        nonnegative integer. The default is 0, which means to filter
        the data without differentiating.
    delta : float, optional
        The spacing of the samples to which the filter will be applied.
        This is only used if deriv > 0.
    pos : int or None, optional
        If pos is not None, it specifies evaluation position within the
        window. The default is the middle of the window.
    use : str, optional
        Either 'conv' or 'dot'. This argument chooses the order of the
        coefficients. The default is 'conv', which means that the
        coefficients are ordered to be used in a convolution. With
        use='dot', the order is reversed, so the filter is applied by
        dotting the coefficients with the data set.

    Returns
    -------
    coeffs : 1-D ndarray
        The filter coefficients.

    See Also
    --------
    savgol_filter

    Notes
    -----
    .. versionadded:: 0.14.0

    References
    ----------
    A. Savitzky, M. J. E. Golay, Smoothing and Differentiation of Data by
    Simplified Least Squares Procedures. Analytical Chemistry, 1964, 36 (8),
    pp 1627-1639.
    Jianwen Luo, Kui Ying, and Jing Bai. 2005. Savitzky-Golay smoothing and
    differentiation filter for even number data. Signal Process.
    85, 7 (July 2005), 1429-1434.

    Examples
    --------
    >>> import numpy as np
    >>> from scipy.signal import savgol_coeffs
    >>> savgol_coeffs(5, 2)
    array([-0.08571429,  0.34285714,  0.48571429,  0.34285714, -0.08571429])
    >>> savgol_coeffs(5, 2, deriv=1)
    array([ 2.00000000e-01,  1.00000000e-01,  2.07548111e-16, -1.00000000e-01,
           -2.00000000e-01])

    Note that use='dot' simply reverses the coefficients.

    >>> savgol_coeffs(5, 2, pos=3)
    array([ 0.25714286,  0.37142857,  0.34285714,  0.17142857, -0.14285714])
    >>> savgol_coeffs(5, 2, pos=3, use='dot')
    array([-0.14285714,  0.17142857,  0.34285714,  0.37142857,  0.25714286])
    >>> savgol_coeffs(4, 2, pos=3, deriv=1, use='dot')
    array([0.45,  -0.85,  -0.65,  1.05])

    `x` contains data from the parabola x = t**2, sampled at
    t = -1, 0, 1, 2, 3.  `c` holds the coefficients that will compute the
    derivative at the last position.  When dotted with `x` the result should
    be 6.

    >>> x = np.array([1, 0, 1, 4, 9])
    >>> c = savgol_coeffs(5, 2, pos=4, deriv=1, use='dot')
    >>> c.dot(x)
    6.0
    """

    # An alternative method for finding the coefficients when deriv=0 is
    #    t = np.arange(window_length)
    #    unit = (t == pos).astype(int)
    #    coeffs = np.polyval(np.polyfit(t, unit, polyorder), t)
    # The method implemented here is faster.

    # To recreate the table of sample coefficients shown in the chapter on
    # the Savitzy-Golay filter in the Numerical Recipes book, use
    #    window_length = nL + nR + 1
    #    pos = nL + 1
    #    c = savgol_coeffs(window_length, M, pos=pos, use='dot')

    if polyorder >= window_length:
        raise ValueError("polyorder must be less than window_length.")

    halflen, rem = divmod(window_length, 2)

    if pos is None:
        if rem == 0:
            pos = halflen - 0.5
        else:
            pos = halflen

    if not (0 <= pos < window_length):
        raise ValueError("pos must be nonnegative and less than "
                         "window_length.")

    if use not in ['conv', 'dot']:
        raise ValueError("`use` must be 'conv' or 'dot'")

    # cf windows/_windows.py
    xp = np_compat if xp is None else array_namespace(xp.empty(0))

    if deriv > polyorder:
        coeffs = xp.zeros(window_length, dtype=xp.float64, device=device)
        return coeffs

    # Form the design matrix A. The columns of A are powers of the integers
    # from -pos to window_length - pos - 1. The powers (i.e., rows) range
    # from 0 to polyorder. (That is, A is a vandermonde matrix, but not
    # necessarily square.)
    x = xp.arange(-pos, window_length - pos, dtype=xp.float64, device=device)

    if use == "conv":
        # Reverse so that result can be used in a convolution.
        x = xp.flip(x)

    order = xp.reshape(
        xp.arange(polyorder + 1, dtype=xp.float64, device=device), (-1, 1)
    )
    A = x ** order

    # y determines which order derivative is returned.
    y = xp.zeros(polyorder + 1, dtype=xp.float64, device=device)
    # The coefficient assigned to y[deriv] scales the result to take into
    # account the order of the derivative and the sample spacing.
    y = xpx.at(y, deriv).set(float_factorial(deriv) / (delta ** deriv))

    # Find the least-squares solution of A*c = y
    coeffs, _, _, _ = _pu._lstsq(A, y, xp=xp)

    return coeffs


def _polyder(p, m, *, xp):
    """Differentiate polynomials represented with coefficients.

    p must be a 1-D or 2-D array.  In the 2-D case, each column gives
    the coefficients of a polynomial; the first row holds the coefficients
    associated with the highest power. m must be a nonnegative integer.
    (numpy.polyder doesn't handle the 2-D case.)
    """

    if m == 0:
        result = p
    else:
        n = p.shape[0]
        if n <= m:
            result = xp.zeros_like(p[:1, ...])
        else:
            dp = xp.asarray(p[:-m, ...], copy=True)
            for k in range(m):
                rng = xp.arange(
                    n - k - 1, m - k - 1, -1, dtype=p.dtype, device=xp_device(p)
                )
                dp *= xp.reshape(rng, (n - m,) + (1,) * (p.ndim - 1))
            result = dp
    return result


def _fit_edge(x, window_start, window_stop, interp_start, interp_stop,
              axis, polyorder, deriv, delta, y):
    """
    Given an N-d array `x` and the specification of a slice of `x` from
    `window_start` to `window_stop` along `axis`, create an interpolating
    polynomial of each 1-D slice, and evaluate that polynomial in the slice
    from `interp_start` to `interp_stop`. Put the result into the
    corresponding slice of `y`.
    """
    xp = array_namespace(x)

    # Get the edge into a (window_length, -1) array.
    x_edge = axis_slice(x, start=window_start, stop=window_stop, axis=axis)
    if axis == 0 or axis == -x.ndim:
        xx_edge = x_edge
        swapped = False
    else:
        xx_edge = xp_swapaxes(x_edge, axis, 0, xp)
        swapped = True
    xx_edge = xp.reshape(xx_edge, (xx_edge.shape[0], -1))

    # Fit the edges.  poly_coeffs has shape (polyorder + 1, -1),
    # where '-1' is the same as in xx_edge.
    poly_coeffs = _pu.polyfit(
        xp.arange(
            0, window_stop - window_start, dtype=x.dtype, device=xp_device(x)
        ), xx_edge, polyorder, xp=xp
    )

    if deriv > 0:
        poly_coeffs = _polyder(poly_coeffs, deriv, xp=xp)

    # Compute the interpolated values for the edge.
    i = xp.arange(
        interp_start - window_start, interp_stop - window_start,
        dtype=poly_coeffs.dtype, device=xp_device(poly_coeffs)
    )
    values = _pu.polyval(poly_coeffs, xp.reshape(i, (-1, 1)), xp=xp) / (delta ** deriv)

    # Now put the values into the appropriate slice of y.
    # First reshape values to match y.
    shp = list(y.shape)
    shp[0], shp[axis] = shp[axis], shp[0]
    values = xp.reshape(values, (interp_stop - interp_start, *shp[1:]))
    if swapped:
        values = xp_swapaxes(values, 0, axis, xp)
    # Get a view of the data to be replaced by values.
    y_slice = [slice(None)] * y.ndim
    y_slice[axis] = slice(interp_start, interp_stop)
    y = xpx.at(y, tuple(y_slice)).set(values)

    return y



def _fit_edges_polyfit(x, window_length, polyorder, deriv, delta, axis, y):
    """
    Use polynomial interpolation of x at the low and high ends of the axis
    to fill in the halflen values in y.

    This function just calls _fit_edge twice, once for each end of the axis.
    """
    halflen = window_length // 2
    y = _fit_edge(x, 0, window_length, 0, halflen, axis,
              polyorder, deriv, delta, y)
    n = x.shape[axis]
    y = _fit_edge(x, n - window_length, n, n - halflen, n, axis,
              polyorder, deriv, delta, y)

    return y


def savgol_filter(x, window_length, polyorder, deriv=0, delta=1.0,
                  axis=-1, mode='interp', cval=0.0):
    """ Apply a Savitzky-Golay filter to an array.

    This is a 1-D filter. If `x`  has dimension greater than 1, `axis`
    determines the axis along which the filter is applied.

    Parameters
    ----------
    x : array_like
        The data to be filtered. If `x` is not a single or double precision
        floating point array, it will be converted to type ``numpy.float64``
        before filtering.
    window_length : int
        The length of the filter window (i.e., the number of coefficients).
        If `mode` is 'interp', `window_length` must be less than or equal
        to the size of `x`.
    polyorder : int
        The order of the polynomial used to fit the samples.
        `polyorder` must be less than `window_length`.
    deriv : int, optional
        The order of the derivative to compute. This must be a
        nonnegative integer. The default is 0, which means to filter
        the data without differentiating.
    delta : float, optional
        The spacing of the samples to which the filter will be applied.
        This is only used if deriv > 0. Default is 1.0.
    axis : int, optional
        The axis of the array `x` along which the filter is to be applied.
        Default is -1.
    mode : str, optional
        Must be 'mirror', 'constant', 'nearest', 'wrap' or 'interp'. This
        determines the type of extension to use for the padded signal to
        which the filter is applied.  When `mode` is 'constant', the padding
        value is given by `cval`.  See the Notes for more details on 'mirror',
        'constant', 'wrap', and 'nearest'.
        When the 'interp' mode is selected (the default), no extension
        is used.  Instead, a degree `polyorder` polynomial is fit to the
        last `window_length` values of the edges, and this polynomial is
        used to evaluate the last `window_length // 2` output values.
    cval : scalar, optional
        Value to fill past the edges of the input if `mode` is 'constant'.
        Default is 0.0.

    Returns
    -------
    y : ndarray, same shape as `x`
        The filtered data.

    See Also
    --------
    savgol_coeffs

    Notes
    -----
    Details on the `mode` options:

        'mirror':
            Repeats the values at the edges in reverse order. The value
            closest to the edge is not included.
        'nearest':
            The extension contains the nearest input value.
        'constant':
            The extension contains the value given by the `cval` argument.
        'wrap':
            The extension contains the values from the other end of the array.

    For example, if the input is [1, 2, 3, 4, 5, 6, 7, 8], and
    `window_length` is 7, the following shows the extended data for
    the various `mode` options (assuming `cval` is 0)::

        mode       |   Ext   |         Input          |   Ext
        -----------+---------+------------------------+---------
        'mirror'   | 4  3  2 | 1  2  3  4  5  6  7  8 | 7  6  5
        'nearest'  | 1  1  1 | 1  2  3  4  5  6  7  8 | 8  8  8
        'constant' | 0  0  0 | 1  2  3  4  5  6  7  8 | 0  0  0
        'wrap'     | 6  7  8 | 1  2  3  4  5  6  7  8 | 1  2  3

    .. versionadded:: 0.14.0

    Examples
    --------
    >>> import numpy as np
    >>> from scipy.signal import savgol_filter
    >>> np.set_printoptions(precision=2)  # For compact display.
    >>> x = np.array([2, 2, 5, 2, 1, 0, 1, 4, 9])

    Filter with a window length of 5 and a degree 2 polynomial.  Use
    the defaults for all other parameters.

    >>> savgol_filter(x, 5, 2)
    array([1.66, 3.17, 3.54, 2.86, 0.66, 0.17, 1.  , 4.  , 9.  ])

    Note that the last five values in x are samples of a parabola, so
    when mode='interp' (the default) is used with polyorder=2, the last
    three values are unchanged. Compare that to, for example,
    `mode='nearest'`:

    >>> savgol_filter(x, 5, 2, mode='nearest')
    array([1.74, 3.03, 3.54, 2.86, 0.66, 0.17, 1.  , 4.6 , 7.97])

    """
    if mode not in ["mirror", "constant", "nearest", "interp", "wrap"]:
        raise ValueError("mode must be 'mirror', 'constant', 'nearest' "
                         "'wrap' or 'interp'.")

    xp = array_namespace(x)
    x = xp.asarray(x)
    # Ensure that x is either single or double precision floating point.
    if x.dtype != xp.float64 and x.dtype != xp.float32:
        x = xp.astype(x, xp.float64)

    coeffs = savgol_coeffs(
        window_length, polyorder, deriv=deriv, delta=delta, xp=xp, device=xp_device(x)
    )

    if mode == "interp":
        if window_length > x.shape[axis]:
            raise ValueError("If mode is 'interp', window_length must be less "
                             "than or equal to the size of x.")

        # Do not pad. Instead, for the elements within `window_length // 2`
        # of the ends of the sequence, use the polynomial that is fitted to
        # the last `window_length` elements.
        y = convolve1d(x, coeffs, axis=axis, mode="constant")
        y = _fit_edges_polyfit(x, window_length, polyorder, deriv, delta, axis, y)
    else:
        # Any mode other than 'interp' is passed on to ndimage.convolve1d.
        y = convolve1d(x, coeffs, axis=axis, mode=mode, cval=cval)

    return y