Data

Tools

Indexes

Applications

Experiments

Open Source Science

https://github.com/bethgelab/decompose

Blind source separation based on the probabilistic tensor factorisation framework

https://github.com/bethgelab/decompose

Science Score: 10.0%

This score indicates how likely this project is to be science-related based on various indicators:

  • ○
    CITATION.cff file
  • ○
    codemeta.json file
  • ○
    .zenodo.json file
  • ○
    DOI references
  • ✓
    Academic publication links
    Links to: arxiv.org
  • ○
    Committers with academic emails
  • ○
    Institutional organization owner
  • ○
    JOSS paper metadata
  • ○
    Scientific vocabulary similarity
    Low similarity (8.4%) to scientific vocabulary

Keywords

blind-source-separation decompose tensor-factorization tensorflow
Last synced: 5 months ago · JSON representation

Repository

Blind source separation based on the probabilistic tensor factorisation framework

Basic Info
  • Host: GitHub
  • Owner: bethgelab
  • License: mit
  • Language: Python
  • Default Branch: master
  • Size: 269 KB
Statistics
  • Stars: 45
  • Watchers: 11
  • Forks: 11
  • Open Issues: 0
  • Releases: 0
Topics
blind-source-separation decompose tensor-factorization tensorflow
Created almost 8 years ago · Last pushed over 7 years ago
Metadata Files
Readme License

README.md

Decompose

Blind source separation based on the probabilistic tensor factorisation framework

Installation

Decompose demands python 3.6 and tensorflow 1.7. The newest github code of decompose can be installed using pip: bash pip3 install git+https://github.com/bethgelab/decompose

Quick start

Decompose provides an interface that is similar to the interface of scikit-learn:

```python import numpy as np from sklearn.datasets import makelowrank_matrix

from decompose.sklearn import DECOMPOSE from decompose.distributions.cenNormal import CenNormal

create a numpy array containing a synthetic low rank dataset

X = makelowrankmatrix(nsamples=1000, nfeatures=1000, effectiverank=3, tail_strength=0.5)

create an instance of a decompose model

model = DECOMPOSE(modelDirectory="/tmp/myNewModel", priors=[CenNormal(), CenNormal()], n_components=3)

train the model and transform the training data

U0 = model.fit_transform(X)

learned filter bank

U1 = model.components_

variance ratio of the sources

varianceRatio = model.varianceratio

reconstruction of the data

XHat = np.dot(U0.T, U1) ```

Publication

The publication linked to this repository is available on arXiv: [1803.08882] Trace your sources in large-scale data: one ring to find them all

Version

The repository is still in alpha stage and does not yet contain all the code used in the publication above. In the next days documentation and features will be added.

Owner

  • Name: Bethge Lab
  • Login: bethgelab
  • Kind: organization
  • Location: Tübingen

Perceiving Neural Networks

GitHub Events

Total
  • Watch event: 2
Last Year
  • Watch event: 2

Committers

Last synced: about 1 year ago

All Time
  • Total Commits: 73
  • Total Committers: 2
  • Avg Commits per committer: 36.5
  • Development Distribution Score (DDS): 0.014
Past Year
  • Commits: 0
  • Committers: 0
  • Avg Commits per committer: 0.0
  • Development Distribution Score (DDS): 0.0
Top Committers
Name Email Commits
Alexander Boettcher a****r@b****g 72
Jonas Rauber j****r 1
Committer Domains (Top 20 + Academic)
bethgelab.org: 1

Issues and Pull Requests

Last synced: 6 months ago

All Time
  • Total issues: 2
  • Total pull requests: 6
  • Average time to close issues: 4 days
  • Average time to close pull requests: 12 minutes
  • Total issue authors: 2
  • Total pull request authors: 1
  • Average comments per issue: 4.5
  • Average comments per pull request: 0.0
  • Merged pull requests: 6
  • Bot issues: 0
  • Bot pull requests: 0
Past Year
  • Issues: 0
  • Pull requests: 0
  • Average time to close issues: N/A
  • Average time to close pull requests: N/A
  • Issue authors: 0
  • Pull request authors: 0
  • Average comments per issue: 0
  • Average comments per pull request: 0
  • Merged pull requests: 0
  • Bot issues: 0
  • Bot pull requests: 0
View more stats
Top Authors
Issue Authors
  • vilim (1)
  • jenwallace (1)
Pull Request Authors
  • aboettcher (6)
Top Labels
Issue Labels
Pull Request Labels

Packages

  • Total packages: 1
  • Total downloads:
    • pypi 35 last-month
  • Total dependent packages: 0
  • Total dependent repositories: 2
  • Total versions: 1
  • Total maintainers: 1
pypi.org: decompose

Blind source separation based on the probabilistic tensor factorisation framework

  • Versions: 1
  • Dependent Packages: 0
  • Dependent Repositories: 2
  • Downloads: 35 Last month
Rankings
Stargazers count: 10.1%
Dependent packages count: 10.1%
Forks count: 10.5%
Dependent repos count: 11.5%
Average: 13.6%
Downloads: 26.0%
Maintainers (1)
aboettcher
Last synced: 6 months ago

Dependencies

setup.py pypi
  • mypy *
  • numpy *
  • tensorflow >=1.7