Hierarchical Dirichlet-Hawkes process: generative model and inference algorithm
Clone or download
Fetching latest commit…
Cannot retrieve the latest commit at this time.
Permalink
Failed to load latest commit information.
docs
examples
hdhp
.gitignore
LICENSE
README.rst
environment.yml
readthedocs.yml
setup.cfg
setup.py

README.rst

hdhp : Simulation and inference for the hierarchical Dirichlet-Hawkes process

This is a Python implementation of the hierarchical Dirichlet-Hawkes process, that includes both the generation and the inference algorithm. For more details about this process and an application on Stack Overflow data, please see the pre-print publication on arXiv.

To cite this work, please use

Mavroforakis, C., Valera, I. and Rodriguez, M.G.,
Modeling the Dynamics of Online Learning Activity.
Proceedings of the 26th International Conference on World Wide Web.
ACM, 2017.

Main Features

  • Generative model for the hierarchical Dirichlet-Hawkes process
  • Inference algorithm based on sequential Monte-Carlo
  • Multi-threaded
  • Arbitrary choice of vocabulary
  • Plotting capabilities

Installation

You can install the hdhp package by executing the following command in a terminal.

pip install hdhp

Documentation

For instructions on how to use the package, consult its documentation.

Examples

You can find an example of how to use this package in the Jupyter notebooks under the directory examples.

Note that the code is distributed under the Open Source Initiative (ISC) license. For the exact terms of distribution, see the LICENSE.

Copyright (c) 2016, hdhp contributors
Charalampos Mavroforakis <cmav@bu.edu>,
Isabel Valera <ivalera@mpi-sws.org>,
Manuel Gomez-Rodriguez <manuelgr@mpi-sws.org>