Land your dream data job with a limited time offer!

Networks appear in lots of places in today's world. From social media to organizational charts to transportation, they can be visualized and analyzed using R. This track shows you how.

Learn how to visualize and analyze network data in R, using igraph and other visualization libraries.

with R

Network Analysis

In this chapter, you will be introduced to fundamental concepts in social network analysis. You will learn how to use the <code>igraph</code> R package to explore and analyze social network data as well as learning how to visualize networks. 


Introduction to networks

In this chapter you will learn about directed networks.  You will also learn how to identify key relationships between vertices in a network as well as how to use these relationships to identify important or influential vertices. 
Throughout this chapter you will use a network of measles transmission. The data come from the German city of Hagelloch in 1861. Each directed edge of the network indicates a child becoming infected with measles after coming into contact with an infected child.



Identifying important vertices in a network

This module will show how to characterize global network structures and sub-structures. It will also introduce generating random network graphs.

Characterizing network structures

This chapter will further explore the partitioning of networks into sub-networks and determining which vertices are more highly related to one another than others.  You will also develop visualization methods by creating three-dimensional visualizations.


Identifying special relationships

Friendship network data

Friendship network edge data

Friendship network node data

Forrest Gump network data

Measles network data

In this course you'll learn how to work with and visualize network data. You'll use the <code>igraph</code> package to create networks from edgelists and adjacency matrices. You'll also learn how to plot networks and their attributes. Then, you'll learn how to identify important vertices using measures like betweenness and degree. Next, this course covers network structures, including triangles and cliques. Next, you'll learn how to identify special relationships between vertices, using metrics like assortativity. Finally, you'll see how to create interactive network plots using threejs.

Intermediate R

In this course you'll learn to analyze and visualize network data with the igraph package.

Network Analysis in R

Probability & Statistics

In this chapter you will be introduced to labelled networks, network learning and the challanges that can arise.

Introduction, networks and labelled networks

In this chapter you will learn about homophily and how to compute the two measures that can be used to characterice it, dyadicity and heterophilicty.

Homophily

In this chapter you will use the igraph package to compute various network features and add them to the network.

Network Featurization

In this chapter you will use the network from Chapter 3 to create a flat dataset. Using standard data mining techniques, you will build predictive models and measure their performance with AUC and top decile lift.

Putting it all together

Student Customers dataset

Student Edge List dataset

Student Network dataset

In this course, you will learn to perform state-of-the art predictive analytics using networked data in R.  The aim of network analytics is to predict to which class a network node belongs, such as churner or not, fraudster or not, defaulter or not, etc.  To accomplish this, we discuss how to leverage information from the network and its underlying structure in a predictive way.  More specifically, we introduce the idea of featurization such that network features can be added to non-network features as such boosting the performance of any resulting analytical model.  In this course, you will use the igraph package to generate and label a network of customers in a churn setting and learn about the foundations of network learning. Then, you will learn about homophily, dyadicity and heterophilicty, and how these can be used to get key exploratory insights in your network. Next, you will use the functionality of the igraph package to compute various network features to calculate both node-centric as well as neighbor based network features.  Furthermore, you will use the Google PageRank algorithm to compute network features and empirically validate their predictive power. Finally, we teach you how to generate a flat dataset from the network and analyze it using logistic regression and random forests.

Supervised Learning in R: Classification

Learn to predict labels of nodes in networks using network learning and by extracting descriptive features from the network

Predictive Analytics using Networked Data in R

The challenge in this chapter is to spot the most highly connected terrorists in the network. We will first import the dataset and build the network. Then we will learn how to visualize it in different layouts using ggraph package. Later on, we will compute two basic yet important centrality measures in network science - degree and strength. We will use them to spot highly connected terrorists. We will finally touch two alternative centrality measures, betweenness and closeness.

The hubs of the network

In this chapter we will spot the most influential ties among terrorists in the network. We will use a centrality measure on ties, called betweenness, and will learn how to visualize the network highlighting connections with high betweenness centrality. Moreover, we will provide some alternative evidence regarding Mark Granovetter's theory of strength of weak ties, confirming that looser connections are crucial as demonstrated in the Madrid terrorism network.

In its weakness lies its strength

The challenge in this chapter is to discover pairs of similar (and dissimilar) terrorists. We will introduce the adjacency matrix as a mathematical representation of a network and use it to find terrorists with similar connection patterns. We will also learn how to visualize similar and dissimilar pairs of individuals using ggraph.

Connection patterns

In this chapter we will discover cells of similar terrorists. We will explore hierarchical clustering to find groups of similar terrorists building on the notion of similarity of connection patterns developed in the previous chapter. Furthermore, we will explore the visNetwork package to produce fulfilling interactive network visualizations.

Similarity clusters

Nodes of the network

Ties of the network

If you've ever wanted to understand more about social networks, information networks, or even the neural networks of our brains, then you need to know network science! It will demonstrate network analysis using several R packages, including dplyr, ggplot2, igraph, ggraph as well as visNetwork. You will take on the role of Interpol Analyst and investigate the terrorist network behind the Madrid train bombing in 2004. Following the course, you will be able to analyse any network with basic centrality and similarity measures and create beautiful and interactive network visualizations.

Introduction to the Tidyverse

Learn how to analyze and visualize network data in the R programming language using the tidyverse approach.

Network Analysis in the Tidyverse

In this chapter you'll explore a subset of an Amazon purchase graph. You'll build on what you've already learned, finding important products and discovering what drives purchases. You'll also examine how graphs can change through time by looking at the graph during different time periods.

Exploring graphs through time

In this lesson you'll explore some Twitter data about R by looking at conversations using '#rstats'.  First you'll look at the raw data and think about how you want to build your graph.  There's a number of ways to do this, and we'll cover two ways: retweets and mentions.  You'll build those graphs and then compare them on a number of metrics.

How do people talk about R on Twitter?

In this chapter you will analyze data from a Chicago bike sharing network.  We will build on the concepts already covered in the introductory course, and add a few new ones to handle graphs with weighted edges. You will also start with data in a slightly more raw form and cover how to build your graph up from a data source you might find.

Bike sharing in Chicago

So far everything we've done has been using plotting from igraph. It provides many powerful ways to plot your graph data.  However many people prefer interacting with other plotting frameworks like ggplot2, or even interactive frameworks like d3.js. In this lesson you'll look at other plotting libraries that build on the ggplot2 framework. You'll also look at other non-"hairball" type methods like hive plots, as well as building interactive and animated plots.

Other ways to visualize graph data

Amazon graph

Amazon purchase graph over time

Twitter retweet graph

Twitter mention graph

Bike sharing data

Now that you're familiar with the basics of network analysis it's time to see how to apply those concepts to large real-world data sets. You'll work through three different case studies, each building on your previous work. These case studies are working with the kinds of data you'll see in both academic and industry settings. We'll explore some of the computational and visualization challenges you'll face and how to overcome them. Your knowledge of igraph will continue to grow, but we'll also leverage other visualization libraries that will help you bring your visualizations to the web.

Apply fundamental concepts in network analysis to large real-world datasets in 4 different case studies.

Data Science Courses

Data Science Tracks

Our Learning Experience

Network Analysis with R

Create Your Free Account

Loved by learners at thousands of companies

Instructors