# Edge Prediction
Graph's edges classification by topological (and other) features with neural network.
## Installation
* Installation via pip:
```
pip install
```
* Installation with git:
```
git clone https://github.com/louzounlab/Edge-Prediction.git
```
## How to use?
```python
import networkx as nx
from EdgeClassifier.edge_classifier import EdgeClassifier
# Build networkx graph from edges list:
graph = nx.read_edgelist("./data/graph1.txt", delimiter=",", create_using=nx.DiGraph,
data=(("label", int), ("attribute1", float,)))
graph = nx.convert_node_labels_to_integers(graph)
# Build the classifier.
classifier = EdgeClassifier("./pkl", "./plots", verbose=True, gpu=False)
# Define parameters to the graph and to the model and execute.
classifier.build("graph5", graph, {
"lr": 0.001,
"batch_size": 64,
"epochs": 150
}, topological_features=None, data_features=["attribute1"])
```
This package classify graphs' edges by , graph edges classification by topological attributes
> Attention! This package uses non boost graph-measures, and that's might make the features calculation slower.
> If you would like to clac them in boost environment, follow the instruction here (link), and move th .pkl file to the pkl directory.
Raw data
{
"_id": null,
"home_page": "https://github.com/louzounlab/Edge-Prediction",
"name": "EdgeClassifier",
"maintainer": "Ziv Naim",
"docs_url": null,
"requires_python": ">=3.6.8",
"maintainer_email": "zivnaim3@gmail.com",
"keywords": "gpu,graph,edges,edge,classification,neural,networks",
"author": "Ziv Naim",
"author_email": "",
"download_url": "https://files.pythonhosted.org/packages/ea/d4/65440de656da4df059e03cd78ab4ad9ac2222647b0c0f749a9fefff01d29/EdgeClassifier-0.0.11.tar.gz",
"platform": null,
"description": "# Edge Prediction\r\nGraph's edges classification by topological (and other) features with neural network.\r\n\r\n## Installation\r\n* Installation via pip:\r\n```\r\npip install\r\n```\r\n* Installation with git:\r\n```\r\ngit clone https://github.com/louzounlab/Edge-Prediction.git\r\n```\r\n\r\n## How to use?\r\n```python\r\nimport networkx as nx\r\nfrom EdgeClassifier.edge_classifier import EdgeClassifier\r\n\r\n# Build networkx graph from edges list:\r\ngraph = nx.read_edgelist(\"./data/graph1.txt\", delimiter=\",\", create_using=nx.DiGraph,\r\n data=((\"label\", int), (\"attribute1\", float,)))\r\ngraph = nx.convert_node_labels_to_integers(graph)\r\n\r\n# Build the classifier.\r\nclassifier = EdgeClassifier(\"./pkl\", \"./plots\", verbose=True, gpu=False)\r\n\r\n# Define parameters to the graph and to the model and execute.\r\nclassifier.build(\"graph5\", graph, {\r\n \"lr\": 0.001,\r\n \"batch_size\": 64,\r\n \"epochs\": 150\r\n}, topological_features=None, data_features=[\"attribute1\"])\r\n\r\n```\r\n\r\n\r\n\r\nThis package classify graphs' edges by , graph edges classification by topological attributes\r\n\r\n> Attention! This package uses non boost graph-measures, and that's might make the features calculation slower. \r\n> If you would like to clac them in boost environment, follow the instruction here (link), and move th .pkl file to the pkl directory.\r\n",
"bugtrack_url": null,
"license": "MIT",
"summary": "A python package for classify edges of graph based on topological features and neural networks.",
"version": "0.0.11",
"split_keywords": [
"gpu",
"graph",
"edges",
"edge",
"classification",
"neural",
"networks"
],
"urls": [
{
"comment_text": "",
"digests": {
"md5": "8b1a11f92fd6cfcf9f03f93687b86e76",
"sha256": "fae8a053331ed570b833bed4104a954ba6d78670adde9d218c8d06165785217a"
},
"downloads": -1,
"filename": "EdgeClassifier-0.0.11-cp310-cp310-win_amd64.whl",
"has_sig": false,
"md5_digest": "8b1a11f92fd6cfcf9f03f93687b86e76",
"packagetype": "bdist_wheel",
"python_version": "cp310",
"requires_python": ">=3.6.8",
"size": 10165,
"upload_time": "2022-12-07T15:08:34",
"upload_time_iso_8601": "2022-12-07T15:08:34.240906Z",
"url": "https://files.pythonhosted.org/packages/7f/58/14f508d5c6d3deef42c6aac3e7870445066133bb73b425a470fdd3a0c411/EdgeClassifier-0.0.11-cp310-cp310-win_amd64.whl",
"yanked": false,
"yanked_reason": null
},
{
"comment_text": "",
"digests": {
"md5": "fdbf3048c2c68276a9c7e2fa1097294c",
"sha256": "4242a70fd771a9605cc0c25e70a1c0cc04983a3a00fb9bc203649f58dfafc353"
},
"downloads": -1,
"filename": "EdgeClassifier-0.0.11.tar.gz",
"has_sig": false,
"md5_digest": "fdbf3048c2c68276a9c7e2fa1097294c",
"packagetype": "sdist",
"python_version": "source",
"requires_python": ">=3.6.8",
"size": 8672,
"upload_time": "2022-12-07T15:08:36",
"upload_time_iso_8601": "2022-12-07T15:08:36.360939Z",
"url": "https://files.pythonhosted.org/packages/ea/d4/65440de656da4df059e03cd78ab4ad9ac2222647b0c0f749a9fefff01d29/EdgeClassifier-0.0.11.tar.gz",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2022-12-07 15:08:36",
"github": true,
"gitlab": false,
"bitbucket": false,
"github_user": "louzounlab",
"github_project": "Edge-Prediction",
"travis_ci": false,
"coveralls": false,
"github_actions": false,
"lcname": "edgeclassifier"
}
JSON
