Updated GraphAcademy Course: Using a Machine Learning Workflow for Link Prediction


Learn about this updated GraphAcademy course on ML link prediction


We have updated a course in our catalog of free online coursesUsing a Machine Learning Workflow for Link Prediction.

This course is intended for experienced Cypher and Python developers and data scientists who want to learn how to apply graph algorithms from the Neo4j Graph Data Science™ Library using a machine learning (ML) workflow.

Note that this course is an update to the course, Data Science with Neo4j 3.5. This course uses Neo4j 4.0 in a Neo4j Desktop environment, as well as the Neo4j Graph Data Science Library. You execute some Cypher code in Neo4j Browser, but most of the hands-on coding uses Jupyter notebooks that you run on your local system.

If you perform the hands-on exercises in this course, it should take you about four hours to complete.

Here are the lessons of this course:

Setting Up Your Development Environment


This lesson shows you the steps for setting up your system for performing the hands-on exercises of the course. You will:

    • Install Neo4j Desktop
    • Create a Neo4j 4.0 database instance
    • Install the APOC and GDSL plugins
    • Modify the memory configuration for your Neo4j instance
    • Set up a Jupyter notebook on your system
    • Download the course notebooks
    • Load the data for the exercises

Exploratory Data Analysis


In this lesson you will explore the dataset, by:

    • Querying the database for its schema
    • Writing Python code to use matplotlib to display a chart about the schema
    • Writing Python code to use pandas and matplotlib to display a histogram describing the data in the dataset

Recommendations


In this lesson, you will build a recommendation engine for authors in the dataset. You will:

    • Find potential collaborators for an author
    • Find relevant papers about a topic for an author

Predictions


In this lesson, you will learn how to build a ML classifier to predict co-authorships in the citation graph. At the end of this lesson, you will be able to:

    • Describe what link prediction is
    • Use the link prediction graph algorithms in the Neo4j Graph Data Science Library
    • Understand the challenges when building ML models on graph data
    • Build a link prediction classifier using scikit-learn with features derived from the Neo4j Graph Data Science Library

Ready to get started with a deeper dive into Using a Machine Learning Workflow for LInk Prediction ?

Enroll Today
https://development.neo4j.dev/graphacademy/online-training/gds-data-science/?ref=blog