Blended live training with Eric J. Ma starts on September 30th at 1 PM (ET)
Training duration: 4 hours (Hands-on)
Subscribe now and start 7-day free trial
Sign-up for Premium Plan and Get 10-35% Additional Discount Live Training
Learning Objectives
-
Use the NetworkX package and the Python programming language to manipulate and visualize graphs
-
Understand how graph algorithms work, particularly how to "think on" graphs
-
Use linear algebra to represent graph problems and speed them up
-
Load graph data to and from disk
Instructor Bio:
Eric Ma
Principal Data Scientist, Platform Research | Moderna Therapeutics
Eric J. Ma
Eric is a Principal Data Scientist at Moderna Therapeutics and alumni of Novartis, Insight Data Science, and MIT. His ScD thesis research was conducted in the Department of Biological Engineering at MIT. His thesis addresses two distinct topics that are unified by a mission for infectious disease. The first problem he has addressed is the ecological question of whether genome shuffling is quantitatively important for ecological niche switching. The second problem he is addressing is the data science problem of interpretable machine learning models for predicting protein phenotype from genotype.
He believes in using open data, open science, and open source tools to ensure the long-term integrity of the scientific work that he conducts. To that end, he is committed to releasing source code and documentation for his scientific work and has already done so on two manuscripts that are currently submitted and under consideration.
10% discount ends in:
-
00 Days
-
00 Hours
-
00 Minutes
-
00 Seconds
DIFFICULTY LEVEL: INTERMEDIATE
Course Abstract
Have you ever wondered about how those data scientists at Facebook and LinkedIn make friend recommendations? Or how epidemiologists track down patient zero in an outbreak? If so, then this tutorial is for you. In this tutorial, we will use a variety of datasets to help you understand the fundamentals of network thinking, with a particular focus on constructing, summarizing, and visualizing complex networks.
Course Outline
Part 1: Introduction
- Networks of all kinds: biological, transportation.
- Representation of networks, NetworkX data structures
- Basic quick-and-dirty visualizations
Part 2: Hubs and Paths
- Finding important nodes; applications
- Pathfinding algorithms and their applications
- Hands-on: implementing path-finding algorithms
- Visualize degree and betweenness centrality distributions
Part 3: Cliques, Triangles & Structures
- Definition of cliques
- Triangles as the simplest complex clique, applications
- Using path-finding algorithms to find structures in a graph
- Open triangles as recommender systems.
Part 4: Bipartite Graphs
- Definition of bipartite graphs, applications
- Constructing bipartite graphs in NetworkX
- Summary statistics of bipartite graphs
Part 5: Linear Algebra and Graphs
- Graphs as matrices: adjacency and node feature matrices
- Message passing operations and how it is used in graph deep learning
- Speed vs. code readability tradeoffs when using matrix operations
Which knowledge and skills you should have?
-
If you're familiar with the Jupyter notebook/lab interface, are comfortable with Python programming (loops, functions, conditionals), and know how to make plots in matplotlib, you'll be well-prepared for the tutorial!
What is included in your ticket?
-
Access to on-demand session and live exercises and discussion with the instructor
-
Access to the on-demand recording
-
Certificate of completion
Upcoming Live Training & Recordings
Access all live training