jpt.distributions.multivariate
© Copyright 2021, Mareike Picklum, Daniel Nyga.
Classes
Extension of |
Module Contents
- class jpt.distributions.multivariate.MultiVariateGaussian(mean=None, cov=None, data=None, ignore=-6000000)
Bases:
jpt.distributions.univariate.GaussianExtension of
dnutils.stats.GaussianA Multivariate Gaussian distribution that can be incrementally updated with new samples
- ignore = -6000000
- cdf(intervals)
Computes the CDF for a multivariate normal distribution.
- Parameters:
intervals (list of matcalo.utils.utils.Interval) – the boundaries of the integral
- pdf()
- property mvg
Computes the multivariate Gaussian distribution.
- property dim
Returns the dimension of the distribution.
- property cov_
Returns the covariance matrix for prettyprinting (precision .2).
- property mean_
Returns the mean vector for prettyprinting (precision .2).
- conditional(evidence)
Returns a distribution conditioning on the variables in
evidencefollowing the calculations described in Conditional distributions, i.e., after determining the partitions of \(\mu\), i.e. \(\mu_{1}\) and \(\mu_{2}\) as well as the partitions of \(\Sigma\), i.e. \(\Sigma_{11}, \Sigma_{12}, \Sigma_{21} \text{ and } \Sigma_{22}\), we calculate the multivariate normal \(N(\overline\mu,\overline\Sigma)\) using(1)\[\overline\mu = \mu_{1} + \Sigma_{12}\Sigma_{22}^{-1}(a-\mu_{2})\](2)\[\overline\Sigma = \Sigma_{11} + \Sigma_{12}\Sigma_{22}^{-1}\Sigma_{21}\]- Parameters:
evidence (dict) – the variables the returned distribution conditions on (mapping indices to values or Intervals of values)
- plot(engine=None, **kwargs) Any
Plots the distribution using the given engine.
- Parameters:
engine – Can be either one of
["plotly", "matplotlib"], or an instance of a rendering engine subclassingDistributionRendering.kwargs – The keyword arguments to pass to the engine as defined in the
.plot_multivariate()function ofDistributionRenderingor its respective subclass defined byengine.
- Returns:
the figure object of the plotting engine