draw different colors to show edges' importance
Project description
Introduction
gnnex is to explain the complex GCN model, it shows by drawing the most important edges in whole networks.
Absolutely, there are many different basic GCN models, so you can define your own model.
By rewriting graph.py to define your own GCN Model and rewriting train.py to train your own GCN modeland generate the WEIGHT matrix.
At last, draw the important edges according to WEIGHT matrix above.
Installed
keras==2.3.1
numpy==1.17.2
pandas==0.25.3
matplotlib==3.1.1
scipy==1.3.2
networkx==2.2
seaborn==0.9.0
Usage
pip install gnnex
Basic Model
You should define your own model according to your task to be resolved. By rewriting graph.py to define model and rewriting train.py to train your own model.
Project details
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
File details
Details for the file gnnex-1.0.3.tar.gz
.
File metadata
- Download URL: gnnex-1.0.3.tar.gz
- Upload date:
- Size: 5.2 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/2.0.0 pkginfo/1.5.0.1 requests/2.21.0 setuptools/41.0.1 requests-toolbelt/0.9.1 tqdm/4.31.1 CPython/3.7.3
File hashes
Algorithm | Hash digest | |
---|---|---|
SHA256 | f6715c7b1e12233043955795180b76214e15d0be517d4519365b410d9d1acc4f |
|
MD5 | 8b79bae9d28bcc36a64fce0aa68fc1d6 |
|
BLAKE2b-256 | c76d4a2f9cee9cc822d205519ee47b30f03773800858abe48f412240d23e26e1 |
File details
Details for the file gnnex-1.0.3-py3-none-any.whl
.
File metadata
- Download URL: gnnex-1.0.3-py3-none-any.whl
- Upload date:
- Size: 6.8 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/2.0.0 pkginfo/1.5.0.1 requests/2.21.0 setuptools/41.0.1 requests-toolbelt/0.9.1 tqdm/4.31.1 CPython/3.7.3
File hashes
Algorithm | Hash digest | |
---|---|---|
SHA256 | 23d20e614ee214446ffc09724f6000fffa3a1d623bf09984201fe89eaa0600d9 |
|
MD5 | 130314801e2c29b58547f39604ccbe0d |
|
BLAKE2b-256 | b5690c6b769dea9ec93b409cb1aa7c9781d45c713b268a5a329d354037d9a289 |