scipy.interpolate.NdBSpline.
design_matrix#
- classmethod NdBSpline.design_matrix(xvals, t, k, extrapolate=True)[source]#
Construct the design matrix as a CSR format sparse array.
- Parameters:
- xvalsndarray, shape(npts, ndim)
Data points.
xvals[j, :]gives thej-th data point as anndim-dimensional array.- ttuple of 1D ndarrays, length-ndim
Knot vectors in directions 1, 2, … ndim,
- kint
B-spline degree.
- extrapolatebool, optional
Whether to extrapolate out-of-bounds values of raise a ValueError
- Returns:
- design_matrixa CSR array
Each row of the design matrix corresponds to a value in xvals and contains values of b-spline basis elements which are non-zero at this value.