Case Study Part IV: Final Tasks

1. Case Study Part IV: Final Tasks

Awesome, great work getting through! Alright, you've had three relatively short exercises in the case study so far, and we're now going to go onto

2. Final tasks

the final section of this chapter. This will be a challenging set of problems, but I hope you'll nonetheless find them fun. In this section, you will be doing three tasks. The first is to find important GitHub users based on their collaborative relationships. The second is to find the largest communities of collaborators. And the final task is to build your very own recommendation system for GitHub users based on the concept of open triangles. I'm going to go into each of these tasks in a little bit more depth to help prepare you for them. In the first task,

3. Final tasks

which is about finding important users, you will look for GitHub users that share collaborations with the most number of other users. Do you remember the metric for finding users with this type of importance? If you guessed "degree centrality", then you're right on!

4. Final tasks

In the second task, you'll be looking for the largest communities of collaborators. Do you remember here what the starting point for finding communities is? That's right, it's the "maximal clique" concept. In the final task,

5. Final tasks

you'll be building a recommendation system. Can you recall what concept underlies recommendation systems? If you guessed it right, it's "open triangles"! Open triangles are characterized by the following relationship: I'm connected to two people who are not connected to one another.

6. Let's practice!

The final section will be a test of your capabilities, and I hope you have fun with it!

Create Your Free Account

or

By continuing, you accept our Terms of Use, our Privacy Policy and that your data is stored in the USA.

This exercise is part of the course

Introduction to Network Analysis in Python

IntermediateSkill Level

4.8+

Start Course for Free

In this chapter, you'll be introduced to fundamental concepts in network analytics while exploring a real-world Twitter network dataset. You'll also learn about NetworkX, a library that allows you to manipulate, analyze, and model graph data. You'll learn about the different types of graphs and how to rationally visualize them.

Exercise 1: Introduction to Networks Exercise 2: What is a network?Exercise 3: Basics of NetworkX API, using Twitter network Exercise 4: Basic drawing of a network using NetworkX Exercise 5: Queries on a graph Exercise 6: Types of graphs Exercise 7: Checking the un/directed status of a graph Exercise 8: Specifying a weight on edges Exercise 9: Checking whether there are self-loops in the graph Exercise 10: Network visualization Exercise 11: Visualizing using Matrix plots Exercise 12: Visualizing using Circos plots Exercise 13: Visualizing using Arc plots

You'll learn about ways to identify nodes that are important in a network. In doing so, you'll be introduced to more advanced concepts in network analysis as well as the basics of path-finding algorithms. The chapter concludes with a deep dive into the Twitter network dataset which will reinforce the concepts you've learned, such as degree centrality and betweenness centrality.

Exercise 1: Degree centrality Exercise 2: Compute number of neighbors for each node Exercise 3: Compute degree distribution Exercise 4: Degree centrality distribution Exercise 5: Graph algorithms Exercise 6: Shortest Path I Exercise 7: Shortest Path II Exercise 8: Shortest Path III Exercise 9: Betweenness centrality Exercise 10: NetworkX betweenness centrality on a social network Exercise 11: Deep dive - Twitter network Exercise 12: Deep dive - Twitter network part II

This chapter is all about finding interesting structures within network data. You'll learn about essential concepts such as cliques, communities, and subgraphs, which will leverage all of the skills you acquired in Chapter 2. By the end of this chapter, you'll be ready to apply the concepts you've learned to a real-world case study.

Exercise 1: Communities & cliques Exercise 2: Identifying triangle relationships Exercise 3: Finding nodes involved in triangles Exercise 4: Finding open triangles Exercise 5: Maximal cliques Exercise 6: Finding all maximal cliques of size "n"Exercise 7: Subgraphs Exercise 8: Subgraphs I Exercise 9: Subgraphs II

In this final chapter of the course, you'll consolidate everything you've learned through an in-depth case study of GitHub collaborator network data. This is a great example of real-world social network data, and your newly acquired skills will be fully tested. By the end of this chapter, you'll have developed your very own recommendation system to connect GitHub users who should collaborate together.

Exercise 1: Case study!Exercise 2: Characterizing the network (I)Exercise 3: Characterizing the network (II)Exercise 4: Characterizing the network (III)Exercise 5: Case study part II: Visualization Exercise 6: Matrix plot Exercise 7: Arc plot Exercise 8: Circos plot Exercise 9: Case study part III: Cliques Exercise 10: Finding cliques (I)Exercise 11: Finding cliques (II)Exercise 12: Case Study Part IV: Final Tasks

Current Exercise

Exercise 13: Finding important collaborators Exercise 14: Characterizing editing communities Exercise 15: Recommending co-editors who have yet to edit together Exercise 16: Final thoughts