book

Graph Algorithms for Data Science

Name: Graph Algorithms for Data Science
Author: Tomaz Bratanic
ISBN: 9781617299469

by Tomaz Bratanic

February 2024

Intermediate to advanced

352 pages

9h 52m

English

Manning Publications

Read now

Unlock full access

inside front cover
Graph Algorithms for Data Science
Copyright
contents
front matter
forewordprefaceacknowledgmentsabout this bookWho should read this bookHow this book is organizedAbout the codeliveBook discussion forumabout the authorabout the cover illustration
Part 1 Introduction to graphs
1 Graphs and network science: An introduction
1.1 Understanding data through relationships1.2 How to spot a graph-shaped problem1.2.1 Self-referencing relationships1.2.2 Pathfinding networks1.2.3 Bipartite graphs1.2.4 Complex networksSummary
2 Representing network structure: Designing your first graph model
2.1 Graph terminology2.1.1 Directed vs. undirected graph2.1.2 Weighted vs. unweighted graphs2.1.3 Bipartite vs. monopartite graphs2.1.4 Multigraph vs. simple graph2.1.5 A complete graph2.2 Network representations2.2.1 Labeled-property graph model2.3 Designing your first labeled-property graph model2.3.1 Follower network2.3.2 User-tweet network2.3.3 Retweet network2.3.4 Representing graph schema2.4 Extracting knowledge from text2.4.1 Links2.4.2 Hashtags2.4.3 Mentions2.4.4 Final Twitter social network schemaSummary
Part 2 Network analysis
3 Your first steps with Cypher query language
3.1 Cypher query language clauses3.1.1 CREATE clause3.1.2 MATCH clause3.1.3 WITH clause3.1.4 SET clause3.1.5 REMOVE clause3.1.6 DELETE clause3.1.7 MERGE clause3.2 Importing CSV files with Cypher3.2.1 Clean up the database3.2.2 Twitter graph model3.2.3 Unique constraints3.2.4 LOAD CSV clause3.2.5 Importing the Twitter social network3.3 Solutions to exercisesSummary

4 Exploratory graph analysis
4.1 Exploring the Twitter network4.2 Aggregating data with Cypher query language4.2.1 Time aggregations4.3 Filtering graph patterns4.4 Counting subqueries4.5 Multiple aggregations in sequence4.6 Solutions to exercisesSummary
5 Introduction to social network analysis
5.1 Follower network5.1.1 Node degree distribution5.2 Introduction to the Neo4j Graph Data Science library5.2.1 Graph catalog and native projection5.3 Network characterization5.3.1 Weakly connected component algorithm5.3.2 Strongly connected components algorithm5.3.3 Local clustering coefficient5.4 Identifying central nodes5.4.1 PageRank algorithm5.4.2 Personalized PageRank algorithm5.4.3 Dropping the named graph5.5 Solutions to exercisesSummary
6 Projecting monopartite networks
6.1 Translating an indirect multihop path into a direct relationship6.1.1 Cypher projection6.2 Retweet network characterization6.2.1 Degree centrality6.2.2 Weakly connected components6.3 Identifying the most influential content creators6.3.1 Excluding self-loops6.3.2 Weighted PageRank variant6.3.3 Dropping the projected in-memory graph6.4 Solutions to exercisesSummary
7 Inferring co-occurrence networks based on bipartite networks
7.1 Extracting hashtags from tweets7.2 Constructing the co-occurrence network7.2.1 Jaccard similarity coefficient7.2.2 Node similarity algorithm7.3 Characterization of the co-occurrence network7.3.1 Node degree centrality7.3.2 Weakly connected components7.4 Community detection with the label propagation algorithm7.5 Identifying community representatives with PageRank7.5.1 Dropping the projected in-memory graphs7.6 Solutions to exercisesSummary
8 Constructing a nearest neighbor similarity network
8.1 Feature extraction8.1.1 Motifs and graphlets8.1.2 Betweenness centrality8.1.3 Closeness centrality8.2 Constructing the nearest neighbor graph8.2.1 Evaluating features8.2.2 Inferring the similarity network8.3 User segmentation with the community detection algorithm8.4 Solutions to exercisesSummary
Part 3 Graph machine learning
9 Node embeddings and classification
9.1 Node embedding models9.1.1 Homophily vs. structural roles approach9.1.2 Inductive vs. transductive embedding models9.2 Node classification task9.2.1 Defining a connection to a Neo4j database9.2.2 Importing a Twitch dataset9.3 The node2vec algorithm9.3.1 The word2vec algorithm9.3.2 Random walks9.3.3 Calculate node2vec embeddings9.3.4 Evaluating node embeddings9.3.5 Training a classification model9.3.6 Evaluating predictions9.4 Solutions to exercisesSummary
10 Link prediction
10.1 Link prediction workflow10.2 Dataset split10.2.1 Time-based split10.2.2 Random split10.2.3 Negative samples10.3 Network feature engineering10.3.1 Network distance10.3.2 Preferential attachment10.3.3 Common neighbors10.3.4 Adamic-Adar index10.3.5 Clustering coefficient of common neighbors10.4 Link prediction classification model10.4.1 Missing values10.4.2 Training the model10.4.3 Evaluating the model10.5 Solutions to exercisesSummary
11 Knowledge graph completion
11.1 Knowledge graph embedding model11.1.1 Triple11.1.2 TransE11.1.3 TransE limitations11.2 Knowledge graph completion11.2.1 Hetionet11.2.2 Dataset split11.2.3 Train a PairRE model11.2.4 Drug application predictions11.2.5 Explaining predictions11.3 Solutions to exercisesSummary
12 Constructing a graph using natural language processing techniques
12.1 Coreference resolution12.2 Named entity recognition12.2.1 Entity linking12.3 Relation extraction12.4 Implementation of information extraction pipeline12.4.1 SpaCy12.4.2 Corefence resolution12.4.3 End-to-end relation extraction12.4.4 Entity linking12.4.5 External data enrichment12.5 Solutions to exercisesSummary
Appendix. The Neo4j environment
A.1 Cypher query languageA.2 Neo4j installationA.2.1 Neo4j Desktop installationA.2.2 Neo4j Docker installationA.2.3 Neo4j AuraA.3 Neo4j Browser configuration
references
index

Content preview from Graph Algorithms for Data Science

9 Node embeddings and classification

This chapter covers

Introducing node embedding models
Presenting the difference between transductive and inductive models
Examining the difference between structural roles and homophily-based embeddings
Introducing the node2vec algorithm
Using node2vec embeddings in a downstream machine learning task

In the previous chapter, you used a vector to represent each node in the network. The vectors were handcrafted based on the features you deemed essential. In this chapter, you will learn how to automatically generate node representation vectors using a node embedding model. Node embedding models fall under the dimensionality reduction category.

An example of feature engineering and dimensionality reduction ...

Become an O’Reilly member and get unlimited access to this title plus top books and audiobooks from O’Reilly and nearly 200 top publishers, thousands of courses curated by job role, 150+ live events each month,
and much more.

Read now

Unlock full access

More than 5,000 organizations count on O’Reilly

O’Reilly covers everything we've got, with content to help us build a world-class technology community, upgrade the capabilities and competencies of our teams, and improve overall team performance as well as their engagement.

Julian F.

Head of Cybersecurity

I wanted to learn C and C++, but it didn't click for me until I picked up an O'Reilly book. When I went on the O’Reilly platform, I was astonished to find all the books there, plus live events and sandboxes so you could play around with the technology.

Addison B.

Field Engineer

I’ve been on the O’Reilly platform for more than eight years. I use a couple of learning platforms, but I'm on O'Reilly more than anybody else. When you're there, you start learning. I'm never disappointed.

Amir M.

Data Platform Tech Lead

I'm always learning. So when I got on to O'Reilly, I was like a kid in a candy store. There are playlists. There are answers. There's on-demand training. It's worth its weight in gold, in terms of what it allows me to do.

Mark W.

Embedded Software Engineer

Publisher Resources

ISBN: 9781617299469Publisher Support Publisher Website

Cloud Computing

Data Engineering

Data Science

AI & ML

Programming Languages

Software Architecture

IT/Ops

Security

Design

Business

Soft Skills

Graph Algorithms for Data Science

by Tomaz Bratanic

9 Node embeddings and classification

Become an O’Reilly member and get unlimited access to this title plus top books and audiobooks from O’Reilly and nearly 200 top publishers, thousands of courses curated by job role, 150+ live events each month,
and much more.