https://github.com/neo4j-examples/link-prediction
This repository contains both Jupyter notebooks for solving a link prediction problem using Neo4j’s Graph Data Science Library and scikit-learn.
https://github.com/neo4j-examples/link-prediction
Last synced: 1 day ago
JSON representation
This repository contains both Jupyter notebooks for solving a link prediction problem using Neo4j’s Graph Data Science Library and scikit-learn.
- Host: GitHub
- URL: https://github.com/neo4j-examples/link-prediction
- Owner: neo4j-examples
- Created: 2020-08-18T12:37:25.000Z (almost 5 years ago)
- Default Branch: master
- Last Pushed: 2020-09-22T14:52:21.000Z (almost 5 years ago)
- Last Synced: 2025-05-08T01:44:19.960Z (about 2 months ago)
- Language: Jupyter Notebook
- Homepage:
- Size: 14.9 MB
- Stars: 17
- Watchers: 7
- Forks: 9
- Open Issues: 1
-
Metadata Files:
- Readme: README.adoc
Awesome Lists containing this project
README
= Link Prediction with Neo4j's Graph Data Science Library
This repository contains both Jupyter notebooks for solving a link prediction problem using Neo4j's Graph Data Science Library and scikit-learn.
The associated developer guide for this repository can be found at https://neo4j.com/developer/graph-data-science/link-prediction/scikit-learn/[neo4j.com/developer/graph-data-science/link-prediction/scikit-learn/^]
== Running the examples
You can run the examples by following the instructions below:
=== Download code from GitHub
[source, bash]
----
git clone https://github.com/neo4j-examples/link-prediction.git
cd link-prediction
----
=== Launch Neo4j and Jupyter Notebooks
You can launch the notebooks and Neo4j by using the following command:
[source,bash]
----
docker-compose up
----
This will spin up a Neo4j server and Jupyter session.
The terminal output will look a bit like this:
[source, text]
----
...
link-prediction-jupyter | [I 05:11:37.148 NotebookApp] The Jupyter Notebook is running at:
link-prediction-jupyter | [I 05:11:37.148 NotebookApp] http://5bf4a4a75310:8888/?token=06ce9ad89428f765734540f3f283cc0d3ad5b1fe0c51746a
link-prediction-jupyter | [I 05:11:37.148 NotebookApp] or http://127.0.0.1:8888/?token=06ce9ad89428f765734540f3f283cc0d3ad5b1fe0c51746a
link-prediction-jupyter | [I 05:11:37.148 NotebookApp] Use Control-C to stop this server and shut down all kernels (twice to skip confirmation).
link-prediction-jupyter | To access the notebook, open this file in a browser:
link-prediction-jupyter | file:///home/jovyan/.local/share/jupyter/runtime/nbserver-6-open.html
link-prediction-jupyter | Or copy and paste one of these URLs:
link-prediction-jupyter | http://5bf4a4a75310:8888/?token=06ce9ad89428f765734540f3f283cc0d3ad5b1fe0c51746a
link-prediction-jupyter | or http://127.0.0.1:8888/?token=06ce9ad89428f765734540f3f283cc0d3ad5b1fe0c51746a
...
link-prediction-neo4j | Starting Neo4j.
link-prediction-neo4j | 2020-08-20 05:11:44.729+0000 INFO ======== Neo4j 4.0.6 ========
link-prediction-neo4j | 2020-08-20 05:11:44.734+0000 INFO Starting...
...
link-prediction-neo4j | 2020-08-20 05:11:56.135+0000 INFO Remote interface available at http://localhost:7474/
----
* The Jupyter notebook is available at http://localhost:8888. You'll need to enter the token from the output the first time that you launch it.
* Neo4j is available at http://localhost:7474/
== Viewing online
If you want to view the notebooks online, you can find them in the following locations:
* https://github.com/neo4j-examples/link-prediction/blob/master/notebooks/00_Environment.ipynb[Setup environment]
* https://github.com/neo4j-examples/link-prediction/blob/master/notebooks/01_DataLoading.ipynb[Load data]
* https://github.com/neo4j-examples/link-prediction/blob/master/notebooks/02_Co-Author_Graph.ipynb[Create co-author graph]
* https://github.com/neo4j-examples/link-prediction/blob/master/notebooks/03_Train_Test_Split.ipynb[Create Train/Test datasets]
* https://github.com/neo4j-examples/link-prediction/blob/master/notebooks/04_Model_Feature_Engineering.ipynb[Graph Feature Engineering]
* https://github.com/neo4j-examples/link-prediction/blob/master/notebooks/05_Train_Evaluate_Model.ipynb[Train and Evaluate model]
* https://github.com/neo4j-examples/link-prediction/blob/master/notebooks/06_SageMaker.ipynb[Train and Evaluate model using AWS Sagemaker Autopilot]