Biobjective Archive class with hypervolume indicator and uncrowded hypervolume improvement computation
Project description
Introduction
The Python class
moarchiving.BiobjectiveNondominatedSortedList
implements a bi-objective non-dominated archive with list
as parent class. It is heavily based on the bisect
module. It provides easy and fast access to the overall hypervolume, the contributing hypervolume of each element, and to the uncrowded hypervolume improvement of any given point in objective space.
Installation
Either via
pip install git+https://github.com/CMA-ES/moarchiving.git@master
or simply via
pip install moarchiving
The single file moarchiving.py
(from the moarchiving/
folder) can also be directly used by itself when copied in the current folder or in a path visible to Python (e.g. a path contained in sys.path
).
Details
moarchiving
uses the fractions.Fraction
type to avoid rounding errors when computing hypervolume differences, but its usage can also easily switched off by assigning the respective class attribute.
The Fraction
type may become prohibitively computationally expensive with increasing
precision.
Releases
- 0.5.3 fixed assertion error when not using
fractions.Fraction
- 0.5.2 first published version
Links
- Code on Github
- Documentation (possibly slightly outdated) in
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
Built Distribution
Hashes for moarchiving-0.5.3-py2.py3-none-any.whl
Algorithm | Hash digest | |
---|---|---|
SHA256 | 9da6e2479e28d1b48eb99d53b77dfd054a81126f1c9ce950a91ed77633542497 |
|
MD5 | 17ccf04c816d180f1e9fdb8b7edc2552 |
|
BLAKE2b-256 | 3079b54e747288892fbbc454287b67e8311c677d325c52dc17300ca35cbe6bf7 |