Inhoudsopgave:
|
Practical approaches to leveraging graph data science to solve real-world challenges. \nKey Features \nâ Explore the fundamentals of graph data science, its importance, and applications. \nâ Learn how to set up Python and Neo4j environments for graph data analysis. \nâ Discover techniques to visualize complex graph networks for better understanding. \nBook Description \nGraph Data Science with Python and Neo4j is your ultimate guide to unleashing the potential of graph data science by blending Python's robust capabilities with Neo4j's innovative graph database technology. From fundamental concepts to advanced analytics and machine learning techniques, you'll learn how to leverage interconnected data to drive actionable insights. Beyond theory, this book focuses on practical application, providing you with the hands-on skills needed to tackle real-world challenges. \n\nYou'll explore cutting-edge integrations with Large Language Models (LLMs) like ChatGPT to build advanced recommendation systems. With intuitive frameworks and interconnected data strategies, you'll elevate your analytical prowess. \n\nThis book offers a straightforward approach to mastering graph data science. With detailed explanations, real-world examples, and a dedicated GitHub repository filled with code examples, this book is an indispensable resource for anyone seeking to enhance their data practices with graph technology. Join us on this transformative journey across various industries, and unlock new, actionable insights from your data. \nWhat you will learn \nâ Set up and utilize Python and Neo4j environments effectively for graph analysis. \nâ Import and manipulate data within the Neo4j graph database using Cypher Query Language. \nâ Visualize complex graph networks to gain insights into data relationships and patterns. \nâ Enhance data analysis by integrating ChatGPT for context-rich data enrichment. \nâ Explore advanced topics including Neo4j vector indexing and Retrieval-Augmented Generation (RAG). \nâ Develop recommendation engines leveraging graph embeddings for personalized suggestions. \nâ Build and deploy recommendation systems and fraud detection models using graph techniques. \nâ Gain insights into the future trends and advancements shaping the field of graph data science. \nTable of Contents \n1. Introduction to Graph Data Science \n2. Getting Started with Python and Neo4j \n3. Import Data into the Neo4j Graph Database \n4. Cypher Query Language \n5. Visualizing Graph Networks \n6. Enriching Neo4j Data with ChatGPT \n7. Neo4j Vector Index and Retrieval-Augmented Generation (RAG) \n8. Graph Algorithms in Neo4j \n9. Recommendation Engines Using Embeddings \n10. Fraud Detection \nCLOSING SUMMARY \nThe Future of Graph Data Science \nIndex \nAbout the Author \nTimothy (Tim) Eastridge is an A.I. consultant known for his innovation and thought leadership in integrating knowledge graphs with Generative AI and Large Language Models (LLMs). His expertise in extracting actionable insights from complex datasets positions him as a leader in transforming data into understandable formats. Timâs innovative solutions have resulted in billions of dollars of suspicious activity reports (SARs) for a major bank related to the Paycheck Protection Program (PPP). He continues this work as a consultant to the Pandemic Response Accountability Committee (PRAC), leading the team in the identification, prioritization, and indictment of fraudsters using a combination of unsupervised machine learning and recommendation systems. |
nl
en