Handbook of Graphs and Networks in People Analytics: With Examples in R and Python

Description

Handbook of Graphs and Networks in People Analytics: With Examples in R and Python covers the theory and practical implementation of graph methods in R and Python for the analysis of people and organizational networks. Starting with an overview of the origins of graph theory and its current applications in the social sciences, the book proceeds to give in-depth technical instruction on how to construct and store graphs from data, how to visualize those graphs compellingly and how to convert common data structures into graph-friendly form. The book explores critical elements of network analysis in detail, including the measurement of distance and centrality, the detection of communities and cliques, and the analysis of assortativity and similarity. An extension chapter offers an introduction to graph database technologies. Real data sets from various research contexts are used for both instruction and for end of chapter practice exercises and a final chapter contains data sets and exercises ideal for larger personal or group projects of varying difficulty level. Key features: Immediately implementable code, with extensive and varied illustrations of graph variants and layoutsExamples and exercises across a variety of real-life contexts including business, politics, education, social media and crime investigationDedicated chapter on graph visualization methodsPractical walkthroughs of common methodological uses: finding influential actors in groups, discovering hidden community structures, facilitating diverse interaction in organizations, detecting political alignment, determining what influences connection and attachmentVarious downloadable data sets for use both in class and individual learning projectsFinal chapter dedicated to individual or group project examples Cover Half Title Title Page Copyright Page Contents Foreword by Professor Jeff Polzer Introduction 1. Graphs Everywhere! 1.1. The Seven Bridges of Königsberg 1.2. Graphs as mathematical models 1.3. Graph theory in the analysis of people and groups 1.3.1. The study of connection 1.3.2. The study of information flow 1.3.3. The study of community, diversity and familiarity 1.3.4. The study of importance, influence and attachment 1.3.5. Graphs as data sources 1.4. Purpose, structure and organization of this book 2. Working with Graphs 2.1. Elementary graph theory 2.1.1. General definition of a graph 2.1.2. Types of graphs 2.1.3. Vertex and edge properties 2.1.4. Representations of graphs 2.2. Creating graphs in R 2.2.1. Creating a graph from an edgelist 2.2.2. Creating a graph from an adjacency matrix 2.2.3. Creating a graph from a dataframe 2.2.4. Adding properties to the vertices and edges 2.3. Creating graphs in Python 2.3.1. Creating a graph from an edgelist 2.3.2. Creating a graph from an adjacency matrix 2.3.3. Adding vertex and edge properties to a graph 2.4. Learning exercises 2.4.1. Discussion questions 2.4.2. Data exercises 3. Visualizing Graphs 3.1. Visualizing graphs in R 3.1.1. Native plotting in igraph 3.1.2. Graph layouts 3.1.3. Static plotting with ggraph 3.1.4. Interactive graph visualization using visNetwork 3.1.5. Interactive graph visualization using networkD3 3.2. Visualizing graphs in Python 3.2.1. Static plotting using networkx and matplotlib 3.2.2. Interactive visualization using networkx and pyvis 3.3. Learning exercises 3.3.1. Discussion questions 3.3.2. Data exercises 4. Restructuring Data for Use in Graphs 4.1. Transforming data in rectangular tables for use in graphs 4.1.1. Creating a simple graph of a management hierarchy 4.1.2. Connecting customers through sales reps 4.1.3. Connecting customers through common purchases 4.1.4. Approaches using Python 4.2. Transforming data from documents for use in graphs 4.2.1. Scraping data from semi-structured documents 4.2.2. Creating an edgelist from the scraped data 4.2.3. Approaches in Python 4.3. Learning exercises 4.3.1. Discussion questions 4.3.2. Data exercises 5. Paths and Distance 5.1. Theory of graph traversal, paths and distance 5.1.1. Paths and graph traversal 5.1.2. Path length and distance 5.1.3. Shortest path algorithms 5.1.4. Graph diameter and density 5.2. Calculating paths, distance, diameter and density 5.2.1. Calculating in R 5.2.2. Calculating in Python 5.3. Examples of uses 5.3.1. Facilitating introductions in a workplace 5.3.2. Finding distant colleagues in a workplace 5.4. Learning exercises 5.4.1. Discussion questions 5.4.2. Data exercises 6. Vertex Importance and Centrality 6.1. Vertex centrality measures in graphs 6.1.1. Degree centrality 6.1.2. Closeness centrality 6.1.3. Betweenness centrality 6.1.4. Eigenvector centrality 6.2. Calculating and illustrating vertex centrality 6.2.1. Calculating in R 6.2.2. Calculating in Python 6.2.3. Illustrating centrality in graph visualizations 6.3. Examples of uses 6.3.1. Finding ‘superconnectors’ 6.3.2. Identifying influential employees 6.4. Learning exercises 6.4.1. Discussion questions 6.4.2. Data exercises 7. Components, Communities and Cliques 7.1. Theory of components, partitions and clusters 7.1.1. Connected components of graphs 7.1.2. Vertex partitioning 7.1.3. Vertex clustering and community detection 7.1.4. Cliques 7.2. Finding components, communities and cliques using R 7.2.1. Finding connected components of disconnected graphs 7.2.2. Partitioning and community detection in R 7.2.3. Finding cliques in R 7.3. Finding components, communities and cliques using Python 7.3.1. Finding connected components using Python 7.3.2. Partitioning and community detection using Python 7.3.3. Finding cliques in Python 7.4. Examples of uses 7.4.1. Detecting communities and cliques among Facebook friends 7.4.2. Detecting politically aligned communities on Twitter 7.5. Learning exercises 7.5.1. Discussion questions 7.5.2. Data exercises 8. Assortativity and Similarity 8.1. Assortativity in networks 8.1.1. Categorical or nominal assortativity 8.1.2. Degree assortativity 8.2. Vertex similarity 8.3. Graph similarity 8.4. Calculating assortativity and similarity in Python 8.5. Learning exercises 8.5.1. Discussion questions 8.5.2. Data exercises 9. Graphs as Databases 9.1. Graph database technology 9.1.1. Labelled-property graphs 9.1.2. Resource description frameworks 9.2. Example: how to work with a Neo4J graph database 9.2.1. Using the browser interface 9.2.2. Working with Neo4J using R 9.2.3. Working with Neo4J using Python 9.3. Moving to persistent graph data in organizations 9.4. Learning exercises 9.4.1. Discussion questions 9.4.2. Data exercises 10. Further Exercises for Practice 10.1. Friendships among Scottish teenage girls 10.2. Interactions between dolphins in Doubtful Sound, New Zealand 10.3. Character interaction in Victor Hugo’s novel Les Misérables 10.4. Communication between criminals involved in a drug importation operation 10.5. Academic collaboration between network scientists 10.6. Other sources of data for practice References Glossary Index