Exploring the Movie Actor Network in Python
Network clustering is a powerful way of exploring social networks.
Take any social network. Say actors who act together. Or words that are similar. Or people who email each other. Or products that are bought together.
Clustering the network gives us sub-groups within the network -- like actors who generally act together, products that are often bought together, etc.
This workshop explores popular network clustering algorithms (using the scikit-network and networkx Python libraries) on real-world movie datasets -- letting you discover insights such as what it takes to connect two actors, and how Iranian and Turkish actors are far removed from Hollywood but close to each other.
The Jupyter Notebooks are on Google Colab:
Shortest path: https://colab.research.google.com/dri...
Actor network: https://colab.research.google.com/dri...
Outline:
00:00 - Introduction
00:24 - Shortest path between actors
00:45 - Explore and download the IMDb data
06:17 - Load and process the IMDb data
12:55 - Find the shortest path using networkx
20:04 - Explore shortest path between famous actors
23:43 - Explore network clustering algorithms
30:23 - Which actors act with each other the most?
37:36 - Create and name actor clusters
40:35 - Explore the actor network clusters and their interactions
43:59 - Conclusion
Delivered first at PyCon Iran on 16 Feb 2022: https://ir.pycon.org/schedule?lang=en ( • Workshop / S Anand / Exploring Network Clu... )
#Minecraft #Python #WebSockets