XCSF learning classifier system: rule-based evolutionary machine learning

License: GNU General Public License v3 (GPLv3) (GPL-3.0)

Tags divide and conquer, evolutionary algorithm, genetic programming, learning classifier system, least squares, machine learning, neural networks, neuroevolution, reinforcement learning, rule-based, supervised learning, stochastic gradient descent, XCS, XCSF

Requires: Python >=3.8

Project description

XCSF learning classifier system

An implementation of the XCSF learning classifier system that can be built as a stand-alone binary or as a Python library. XCSF is an accuracy-based online evolutionary machine learning system with locally approximating functions that compute classifier payoff prediction directly from the input state. It can be seen as a generalisation of XCS where the prediction is a scalar value. XCSF attempts to find solutions that are accurate and maximally general over the global input space, similar to most machine learning techniques. However, it maintains the additional power to adaptively subdivide the input space into simpler local approximations.

See the project wiki for details on features, how to build, run, and use as a Python library.

Project details

License: GNU General Public License v3 (GPLv3) (GPL-3.0)

Maintainer: Richard Preen

Requires: Python >=3.8

Release history Release notifications | RSS feed

This version

1.2.5

Oct 3, 2022

1.2.4

Oct 1, 2022

1.2.3

Sep 23, 2022

1.2.2

Sep 20, 2022

1.2.1

Sep 3, 2022

1.2.0

Sep 3, 2022

1.1.6

Dec 27, 2021

1.1.5

Dec 27, 2021

1.1.4

Dec 12, 2021

1.1.3.post1

Dec 7, 2021

1.1.3

Dec 4, 2021

1.1.2.post2

Dec 4, 2021

1.1.2

Nov 30, 2021

Download files

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

Source Distribution

xcsf-1.2.5.tar.gz (5.7 MB view hashes)

Uploaded Oct 3, 2022 source

Built Distributions

xcsf-1.2.5-pp39-pypy39_pp73-win_amd64.whl (629.1 kB view hashes)

Uploaded Oct 3, 2022 pp39

xcsf-1.2.5-pp39-pypy39_pp73-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (438.5 kB view hashes)

Uploaded Oct 3, 2022 pp39

xcsf-1.2.5-pp39-pypy39_pp73-macosx_10_9_x86_64.whl (537.2 kB view hashes)

Uploaded Oct 3, 2022 pp39

xcsf-1.2.5-pp38-pypy38_pp73-win_amd64.whl (629.3 kB view hashes)

Uploaded Oct 3, 2022 pp38

xcsf-1.2.5-pp38-pypy38_pp73-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (438.4 kB view hashes)

Uploaded Oct 3, 2022 pp38

xcsf-1.2.5-pp38-pypy38_pp73-macosx_10_9_x86_64.whl (537.2 kB view hashes)

Uploaded Oct 3, 2022 pp38

xcsf-1.2.5-cp311-cp311-win_amd64.whl (631.1 kB view hashes)

Uploaded Oct 3, 2022 cp311

xcsf-1.2.5-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (439.3 kB view hashes)

Uploaded Oct 3, 2022 cp311

xcsf-1.2.5-cp311-cp311-macosx_10_9_x86_64.whl (538.7 kB view hashes)

Uploaded Oct 3, 2022 cp311

xcsf-1.2.5-cp310-cp310-win_amd64.whl (631.1 kB view hashes)

Uploaded Oct 3, 2022 cp310

xcsf-1.2.5-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (439.4 kB view hashes)

Uploaded Oct 3, 2022 cp310

xcsf-1.2.5-cp310-cp310-macosx_10_9_x86_64.whl (538.5 kB view hashes)

Uploaded Oct 3, 2022 cp310

xcsf-1.2.5-cp39-cp39-win_amd64.whl (631.2 kB view hashes)

Uploaded Oct 3, 2022 cp39

xcsf-1.2.5-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (439.6 kB view hashes)

Uploaded Oct 3, 2022 cp39

xcsf-1.2.5-cp39-cp39-macosx_10_9_x86_64.whl (538.6 kB view hashes)

Uploaded Oct 3, 2022 cp39

xcsf-1.2.5-cp38-cp38-win_amd64.whl (631.3 kB view hashes)

Uploaded Oct 3, 2022 cp38

xcsf-1.2.5-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (439.2 kB view hashes)

Uploaded Oct 3, 2022 cp38

xcsf-1.2.5-cp38-cp38-macosx_10_9_x86_64.whl (538.5 kB view hashes)

Uploaded Oct 3, 2022 cp38

Hashes for xcsf-1.2.5.tar.gz

Hashes for xcsf-1.2.5.tar.gz
Algorithm	Hash digest
SHA256	`dfd102e18cb688ef26985c479dfc6e182e9b4df3552889f420bca71387350cc9`
MD5	`31b00319584696787db7fcf878b99dc2`
BLAKE2b-256	`6a18cc2bc3d2aa04c9376b3ad290a3ce5691665d57b66091c5bd6072042a8120`

Hashes for xcsf-1.2.5-pp39-pypy39_pp73-win_amd64.whl

Hashes for xcsf-1.2.5-pp39-pypy39_pp73-win_amd64.whl
Algorithm	Hash digest
SHA256	`5c1ec912007f3c1650927739e045100fbe2e13a9730ce028c842c6ebafa6023a`
MD5	`b76a5052061668b823de2b34fa47265f`
BLAKE2b-256	`238a3268133cd932489ba664f2c2c1d20b26093429fbfa82baa1da777af4c6d5`

Hashes for xcsf-1.2.5-pp39-pypy39_pp73-manylinux_2_17_x86_64.manylinux2014_x86_64.whl

Hashes for xcsf-1.2.5-pp39-pypy39_pp73-manylinux_2_17_x86_64.manylinux2014_x86_64.whl
Algorithm	Hash digest
SHA256	`0a9c437e5c2591f2682dde8ae9f9334489f520cc3718de7cca86f2610df099fe`
MD5	`624b470ea8bf9e8f4961560ccc27d4dd`
BLAKE2b-256	`317ecad4731c65223b1bf58a59a484d2c2318efacb643d5ee7050db17005cd6b`

Hashes for xcsf-1.2.5-pp39-pypy39_pp73-macosx_10_9_x86_64.whl

Hashes for xcsf-1.2.5-pp39-pypy39_pp73-macosx_10_9_x86_64.whl
Algorithm	Hash digest
SHA256	`a0b5b14362b6884e463c61a938b5474da4accbad2b27dacc430f263cf8eb2a74`
MD5	`78afcb99a622ef7af1e05e8c43ca3c77`
BLAKE2b-256	`0881e02bcae825350a715101bf7e01c245991ceff546fb4182ead41d3b57a32b`

Hashes for xcsf-1.2.5-pp38-pypy38_pp73-win_amd64.whl

Hashes for xcsf-1.2.5-pp38-pypy38_pp73-win_amd64.whl
Algorithm	Hash digest
SHA256	`c773c305e3eaf35002d6b45953152deb0458cc0ba72aaab8200b8f04f75da292`
MD5	`817f099c43ca4cb3d77a70b3fd05a29c`
BLAKE2b-256	`23fa1e1c6761321e9a721f075034e47835c7859da205d29954a877f0bf94a0ed`

Hashes for xcsf-1.2.5-pp38-pypy38_pp73-manylinux_2_17_x86_64.manylinux2014_x86_64.whl

Hashes for xcsf-1.2.5-pp38-pypy38_pp73-manylinux_2_17_x86_64.manylinux2014_x86_64.whl
Algorithm	Hash digest
SHA256	`254e4798e78549bd0db4b02e26b64fead06ecbd24173745c12568e21a7f90602`
MD5	`dd0f70794689dfa62a048b99f4acce03`
BLAKE2b-256	`392d7c43b00e29126970691782d41fd720e7d58481ccb7d40512f6da8a19eb07`

Hashes for xcsf-1.2.5-pp38-pypy38_pp73-macosx_10_9_x86_64.whl

Hashes for xcsf-1.2.5-pp38-pypy38_pp73-macosx_10_9_x86_64.whl
Algorithm	Hash digest
SHA256	`7e694e05a99c67ad23fec1a9aa4184cf9f3e80934e2e24822a90b5ba6aa39ebd`
MD5	`a189b0b4a811c94056d4b2738f4f66cf`
BLAKE2b-256	`5e5942c054909366f7ec54b45c7a3449773d058b58901633fdde717e03c42936`

Hashes for xcsf-1.2.5-cp311-cp311-win_amd64.whl

Hashes for xcsf-1.2.5-cp311-cp311-win_amd64.whl
Algorithm	Hash digest
SHA256	`184abc6bad51b7e442109f9f3714e13a112ce95dc7caaf163482db85ad8b61e8`
MD5	`18d101d2c3b239b5c25d16d48fe36d53`
BLAKE2b-256	`ad14e2012755dea106da13daca569b61717e5fc6a8d8b37f803f56192c558e6c`

Hashes for xcsf-1.2.5-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl

Hashes for xcsf-1.2.5-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl
Algorithm	Hash digest
SHA256	`90cbe1a6c713970cedb0cd6043d88560719c65fdd41252ed22d1ff21b8f20bd7`
MD5	`1403098b9a96868112fafa60afdd72b9`
BLAKE2b-256	`6d8564d7f6877eb68fd627ea96032442bb488f3891a8d8a90b0fc2697640430c`

Hashes for xcsf-1.2.5-cp311-cp311-macosx_10_9_x86_64.whl

Hashes for xcsf-1.2.5-cp311-cp311-macosx_10_9_x86_64.whl
Algorithm	Hash digest
SHA256	`f61fc939fd72339025e5fc1a325893a8e6e1dd5321755f11b07b9c269eb44c1c`
MD5	`759c7ef25842af96d159e4fc1d53df0f`
BLAKE2b-256	`6c1c3a8fd57a54da4c4cc3bd85e54326d76acdcce4653f866ad9a6ce589f5596`

Hashes for xcsf-1.2.5-cp310-cp310-win_amd64.whl

Hashes for xcsf-1.2.5-cp310-cp310-win_amd64.whl
Algorithm	Hash digest
SHA256	`3d701782cd3ddf69679536164146437415b924ac26917e8380500bdab9adc0e7`
MD5	`ec3d1f3ca8e878cee2f283937cc6c2c0`
BLAKE2b-256	`11a339db1bebd90afd5f3d8fc3e1b167f530244fba6ce05e19b8f0885b1e7d8c`

Hashes for xcsf-1.2.5-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl

Hashes for xcsf-1.2.5-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl
Algorithm	Hash digest
SHA256	`df17e89c512e496d16916e66fae62e4fd123200c9e856d7898b2dc67a6c6eeef`
MD5	`ce727e69d073d3686a8c1293a710788b`
BLAKE2b-256	`9b528be877cb7fc4890688e2cc60be542dbe89b6af733f7de7a87010d2dd9f60`

Hashes for xcsf-1.2.5-cp310-cp310-macosx_10_9_x86_64.whl

Hashes for xcsf-1.2.5-cp310-cp310-macosx_10_9_x86_64.whl
Algorithm	Hash digest
SHA256	`ffa7ff96389d04b14c44ff00b217e3284f3349c05de71176ad2d9efbf8fafe57`
MD5	`cfd0b220f3079bee14ca6280c3aab9c5`
BLAKE2b-256	`a4970be4396ae55321e6ec33776cd1eb1cf8dba260739838859c9bb93ea7526d`

Hashes for xcsf-1.2.5-cp39-cp39-win_amd64.whl

Hashes for xcsf-1.2.5-cp39-cp39-win_amd64.whl
Algorithm	Hash digest
SHA256	`a94eb66e33077dccc8e4a0506f57f93b723c581b9170ec603a1ebbf8b0d8017d`
MD5	`c70720b57aaa19e78bd88fc530aa54ad`
BLAKE2b-256	`4cd327ffb3f324297b06cf8fd658c595c84956a6f7e2e7500ebfceb735d21e75`

Hashes for xcsf-1.2.5-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl

Hashes for xcsf-1.2.5-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl
Algorithm	Hash digest
SHA256	`a5ef0dede95a03e0db51bbfd6fbb842aa62b4636bfcde006ba23105c520d1f91`
MD5	`c85cad51972bdf673bb695e7284cc95c`
BLAKE2b-256	`03a1a6f03dec275370cd446a6ed0a8e3d37d93ee21e39073c57a0c28392e4dd3`

Hashes for xcsf-1.2.5-cp39-cp39-macosx_10_9_x86_64.whl

Hashes for xcsf-1.2.5-cp39-cp39-macosx_10_9_x86_64.whl
Algorithm	Hash digest
SHA256	`665560523fcf8e98ddf08bdc5a83b470e3de4992639682abfc58d7aa1129d494`
MD5	`459cd075568448b4b1c7f2fd692f33c6`
BLAKE2b-256	`e882a300e925e49e4ba3f7b8cd9046656289ad861c2676d9661f78ad96d866ce`

Hashes for xcsf-1.2.5-cp38-cp38-win_amd64.whl

Hashes for xcsf-1.2.5-cp38-cp38-win_amd64.whl
Algorithm	Hash digest
SHA256	`1c247ac5f01ea3686c9308dd8c978b740327c76d17e37e589a5f4a37ba7738b7`
MD5	`e3fbb70b992bc85f58426416b213de11`
BLAKE2b-256	`b28aa093b400cebe54f070ecc5dacfa5cb9e83b15a0f4de5ad05ef1bc89f807e`

Hashes for xcsf-1.2.5-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl

Hashes for xcsf-1.2.5-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl
Algorithm	Hash digest
SHA256	`877ef483924f02241319f592285e423afba4b05dda15711a6f27af9430165933`
MD5	`bc5cef31a6c5a6f77c08701821bb9af5`
BLAKE2b-256	`f7fd6050cdde877a2175dd4d4adacfc3a81055617a8838a5979956feaadfb041`

Hashes for xcsf-1.2.5-cp38-cp38-macosx_10_9_x86_64.whl

Hashes for xcsf-1.2.5-cp38-cp38-macosx_10_9_x86_64.whl
Algorithm	Hash digest
SHA256	`70bcb860c571a1de122744cc67bd44eff4cdd3657aef9039716f9c590820b510`
MD5	`2073309761926884c2eb3dcb5828500c`
BLAKE2b-256	`ed3c898021e58af629fb3191454debeefb96e6ac7843185770946ca3c5d06004`