cancel
Showing results for 
Search instead for 
Did you mean: 

Custom node classification model

dragos
Node

Hi,

We're new to Neo4j and currently looking at using it for classifying nodes. Out of the box I see there are a few models as part of the GDS library (namely Logistic Regression and Random Forest) and we were wondering if there's any way to build our own custom classification model and add it to a pipeline?

Dragos.

1 ACCEPTED SOLUTION

PhaniD
Neo4j
Neo4j

Adding custom models to exisiting pipelines in GDS is not yet supported. However, it is very easy to use gds python client and integrate GDS (graphy features) into custom ML pipelines built in Python. 

View solution in original post

2 REPLIES 2

PhaniD
Neo4j
Neo4j

Adding custom models to exisiting pipelines in GDS is not yet supported. However, it is very easy to use gds python client and integrate GDS (graphy features) into custom ML pipelines built in Python. 

Do you have a specific classifier in mind?
At the moment we dont have a mechanism to discover new training methods but only check ours.
I certainly like the idea to have a discover mechanism so that people can write their custom classifier in Java.

If you like, you could also try implementing a classifier against our open-source codebase (https://github.com/neo4j/graph-data-science).

Nodes 2022
Nodes
NODES 2022, Neo4j Online Education Summit

On November 16 and 17 for 24 hours across all timezones, you’ll learn about best practices for beginners and experts alike.