Course home for Introduction to Data Science at the University of Science, VNU-HCMC, Faculty of Information Technology. This page collects the course materials maintained by the teaching assistants. The term project is organized below, and further materials appear here as they are released.
The term project crawls the full-text LaTeX sources of arXiv publications, parses each version into a hierarchical structure, and finishes with a machine learning pipeline that matches citations to their crawled metadata, evaluated by Mean Reciprocal Rank and graded at a poster session.
The coding session statement moves the data designated for the statement through one complete pipeline, from acquisition and storage through quality assessment and exploration to the serving of a trained model, all in one runnable notebook.