sperlea
/
microbiome_ML_benchmark
1
1
Fork 0
Code Issues 4 Pull Requests Projects Releases Wiki Activity
The code (and datasets) written for and used in the microbiome ML benchmark paper we're writing. The goal is to have this in the form of an actionable python package as soon as we're done.
You can not select more than 25 topics Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
16 Commits
7 Branches
0 Tags
233 MiB
Branch: devel
Branches Tags
${ item.name }
Create tag ${ searchTerm }
Create branch ${ searchTerm }
from 'devel'
${ noResults }
Theodor Sperlea 47f3e77e58
Merge branch 'devel' into feature/datasets 		4 months ago
mbmbm initial commit for filters 6 months ago
tests finish poetry setup 11 months ago
INSTALL.md finish poetry setup 11 months ago
LICENCE initial commit 1 year ago
README.md add methods dataset doc 11 months ago
__init__.py initial commit 1 year ago
poetry.lock update pyproject.toml 8 months ago
pyproject.toml update pyproject.toml 8 months ago
requirements.txt initial commit 1 year ago

README.md

Benchmark of Supervised ML methods for the analysis of envicronmental microbiomes and a python package that is not named yet

Installation

See Instructions.

Organizational matters

Contribute to this Repository

Please coordinate contributions with Henning Schröder (henning.schroeder@planet-ai.de) or Theodor Sperlea (theodor.sperlea@io-warnemuende.de).

Branch structure

  • master: contains releases, merges only from devel (restricted access, merge allowed by Theo and Henning)
  • devel: development branch (restricted access, merge allowed by members)

Contribute a feature

  1. Create a branch based on the current devel branch with name scheme feature/coolstuff
  2. Do cool stuff and use descriptive commit messages
  3. Make a pull request into the devel branch and add a reviewer as well as a short description
  4. The merge is done by the reviewer (for quality control ;))

Methdods

see here

Datasets

see here

TODO

  • [Issue #1] Decide on a set of datasets that fit the scope (this will lead to decisions such as test/train, 10fold-cv or loocv)
  • [Issue #2] Decide on sets of methods that fit the scope
  • [Issue #5] implement everyhting with an eye on open publication
  • [Issue #3] Decide on a Licence
  • [Issue #4] write pyproject.toml for metadata and make ready for PIP# Benchmark of Supervised ML methods for the analysis of envicronmental microbiomes and a python package that is not named yet