11.3.1.4. astroML.linear_model.NadarayaWatson

class astroML.linear_model.NadarayaWatson(kernel='gaussian', h=None, **kwargs)

Nadaraya-Watson Kernel Regression

This is basically a gaussian-weighted moving average of points

Parameters

kernelstring

kernel is either “gaussian”, or one of the kernels available in sklearn.metrics.pairwise.

hfloat or array_like

width of kernel. If array, its length must be the number of dimensions in the training data

Additional keyword arguments are passed to the kernel.

Methods

fit
predict

__init__(kernel='gaussian', h=None, **kwargs)

Initialize self. See help(type(self)) for accurate signature.