Graph Data Science with Neo4j

6

Building a Machine Learning Model with Graph Features

So far, we have explored how to build and understand a graph dataset. We have computed some key metrics, such as the degree distribution. Using unsupervised algorithms, such as community detection, we have also better-identified graph structures. Finally, the graph visualization tools have enabled us to see the content of the dataset, and visually identify some aspects of the graph. Now, it is time to start applying this knowledge to build a machine learning (ML) model. In this chapter, we will introduce the Python client for the Graph Data Science (GDS) library, by allowing it to run graph algorithms directly from Python, without writing any Cypher. After computing and extracting our features ...