Skip to main content
This is a pre-production deployment of Warehouse. Changes made here affect the production instance of PyPI (
Help us improve Python packaging - Donate today!

Reblocking analysis tools for correlated data

Project Description

pyblock is a python module for performing a reblocking analysis on serially-correlated data.

The algorithms implemented in pyblock are not new; please see the documentation for references.

pyblock is compatible with (and tested on!) python 2.7 and python 3.3-3.4 and should work on any other version supported by pandas.


Documentation and a simple tutorial can be found in the docs subdirectory and on readthedocs.


pyblock can be used simply by adding to $PYTHONPATH. Alternatively, it can be installed using distutils by running:

$ pip install /path/to/pyblock

where /path/to/ is the (relative or absolute) path to the directory containing pyblock. To install an editable version (useful for development work) do:

$ pip install -e /path/to/pyblock

pyblock can also be installed from PyPI:

$ pip install pyblock

pyblock requires numpy and (optionally) pandas and matplotlib. Please see the documentation for more details.


Modified BSD license; see LICENSE for more details.

Please cite pyblock, James Spencer, if used to analyse data for an academic publication.


James Spencer, Imperial College London


Contributions are extremely welcome, either by raising an issue or contributing code. For code contributions, please try to follow the following points:

  1. Divide commits into logical units (e.g. don’t mix feature development with refactoring).
  2. Ensure all existing tests pass.
  3. Create tests for new functionality. I aim for complete test coverage. (Currently the only function not tested is one that creates plots.)
  4. Write nice git commit messages (see Tim Pope’s advice.)
  5. Send a pull request!


Will Vigor (Imperial College London) pointed out and wrote an early implementation of the algorithm to detect the optimal reblock length.

Tom Poole (Imperial College London) contributed code to handle weighted averages.

The HANDE FCIQMC/CCMC development team made several helpful comments and suggestions.

Release History

This version
History Node


History Node


Download Files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

File Name & Hash SHA256 Hash Help Version File Type Upload Date
(15.7 kB) Copy SHA256 Hash SHA256
Source Jan 31, 2016

Supported By

WebFaction WebFaction Technical Writing Elastic Elastic Search Pingdom Pingdom Monitoring Dyn Dyn DNS Sentry Sentry Error Logging CloudAMQP CloudAMQP RabbitMQ Heroku Heroku PaaS Kabu Creative Kabu Creative UX & Design Fastly Fastly CDN DigiCert DigiCert EV Certificate Rackspace Rackspace Cloud Servers DreamHost DreamHost Log Hosting