jax.scipy.stats.gaussian_kde#

class jax.scipy.stats.gaussian_kde(dataset, bw_method=None, weights=None)[source]#

Gaussian Kernel Density Estimator

JAX implementation of scipy.stats.gaussian_kde.

Parameters:

  • dataset (Any) – arraylike, real-valued. Data from which to estimate the distribution. If 1D, shape is (n_data,). If 2D, shape is (n_dimensions, n_data).

  • bw_method – string, scalar, or callable. Either “scott”, “silverman”, a scalar value, or a callable function which takes self as a parameter.

  • weights (Any) – arraylike, optional. Weights of the same shape as the dataset.

__init__(dataset, bw_method=None, weights=None)[source]#

Methods

__init__(dataset[, bw_method, weights])

evaluate(points)

Evaluate the Gaussian KDE on the given points.

integrate_box(low_bounds, high_bounds[, maxpts])

This method is not implemented in the JAX interface.

integrate_box_1d(low, high)

Integrate the distribution over the given limits.

integrate_gaussian(mean, cov)

Integrate the distribution weighted by a Gaussian.

integrate_kde(other)

Integrate the product of two Gaussian KDE distributions.

logpdf(x)

Log probability density function

pdf(x)

Probability density function

resample(key[, shape])

Randomly sample a dataset from the estimated pdf

set_bandwidth([bw_method])

This method is not implemented in the JAX interface.

tree_flatten()

tree_unflatten(aux_data, children)

Attributes

d

n

neff

dataset

weights

covariance

inv_cov