pomegranate is a Python package that implements fast and flexible probabilistic models ranging from individual probability distributions to compositional models such as Bayesian networks and hidden …

pomegranate is a python package which implements fast, efficient, and extremely flexible probabilistic models ranging from probability distributions to Bayesian networks to mixtures of hidden Markov …

pomegranate has a minimal core API that is made possible because all models are treated as probability distributions regardless of their complexity. This point is repeated throughout the documentation …

In pomegranate, this is done using the loopy belief propagation algorithm, sometimes also called the “sum-product” algorithm. This algorithm is run on a factor graph, which is constructed in the backend.

There are two ways to initialize an HMM using pomegranate. The first is to explicitly pass a list of distributions, a dense transition matrix, and optionally start and end probabilities.

Because pomegranate recently moved to a PyTorch backend, the most complicated installation step now is likely installing that and its CUDA dependencies. Please see the PyTorch documentation for …

Many data science tasks require fitting a distribution to data or generating samples under a distribution. pomegranate has a large library of both univariate and multivariate distributions which can be used …

In this tutorial we’ll explore how to do mixture modeling in pomegranate, compare against scikit-learn’s implementation of Gaussian mixture models, and explore more complex types of mixture modeling …

The requirements for pomegranate can be found in the requirements.txt file in the repository, and include numpy, scipy, networkx (below v2.0), joblib, cupy (if using a GPU), and cython (if building …

A key difference between distributions in pomegranate v1.0.0 and those in previous versions of pomegranate is that those in previous versions were usually univariate, in that one object represents …