Introduction to Data Analytics and Python

DSA101

Author

Alexandria Deliz Liang

Published

September 4, 2026

Introduction

Welcome to Introduction to Data Analytics and Python! This course is an open enrollment course at the University of Zurich. The material is aimed towards teaching BSc, MSc, and PhD students about quantitative robust assessment of data in chemistry, biochemistry, business chemistry, and related fields.

The course meets in the Fall semester on Wednesdays and Fridays from 10.15-12.00 h in room Y19-H22. This site contains the core material covered in the course, and the statistics and Python knowledge necessary to pass the course can be learned from this online platform. The in-person class sessions are interactive and focus on additional worked examples of this material, and more practical knowledge regarding real-world data analysis. Thus, for students who interested in the topic for their future careers (beyond just passing the course), it is recommended to attend the lectures.

FAQ

Note

Class attendance is not required, but for students who are interested in excelling in the topics of the course for further application, I would recommend attending the in-person sessions.

  • What materials do you need for class? - You need to bring a Laptop and have access to OLAT.
  • What background information do I need to know? - Please see the pre-reading and refresher materials and the section on chemical topics below.
  • Will I become an expert in Python? - If you learn how to apply all the code covered this course, I would equate that to being about “A2” if we make an analogy to spoken languages.
  • What kind of assessment can we expect? - The exam is a written exam that includes principles in statistics, data analytics, and code comprehension. You will receive a practice exam.

Learning Objectives

After completing this course, you should be able to:

  • Plan an experiment with the appropriate controls and power
  • Describe the types of experimental replicates and their importance
  • Wrangle or process data in an honest and clear way
  • Visually represent data using Python
  • Determine descriptive and inferential statistical metrics for a dataset
  • Determine the correct statistical test(s) to address a hypothesis
  • Mathematically identify outliers and address them in a clear and honest way
  • Compare data using statistical models or tests
  • Complete regression analysis for datasets
  • Identify use cases for DOE, chemometrics, and ML

Website structure

The website is divided into several sections:

Sessions 15-18 are taught by an excellent co-lecturer and are not yet on this website. The topics of these sessions are reproducible coding and git.

Resources

Textbooks for statistics:

  • Statistics and Chemometrics for Analytical Chemistry — JN Miller, JC Miller, and RD Miller (older editions titled Statistics for Analytical Chemistry are also fine)
  • Essential Mathematics and Statistics for Science — G Currell and A Dowman

Online References for Python:

On Using Generative AI in Education

AI tools can assist with many tasks! In particular, Claude Code (which I often use myself) has become a valuable coding assistant. But these tools come with important caveats:

  • They can give incorrect solutions, particularly for common mistakes
  • You are accountable for anything you submit, regardless of the source you used
  • Recent research suggests that relying on AI for answers reduces retention
  • Both reduced learning and de-skilling are serious concerns if you rely too much on these tools

A suggested reasonable approach: use AI only when you already understand the problem well enough to immediately evaluate the output, or for routine tasks where the risk of error is low. Always review the result.

I really like the perspective of Science Journalist, Cleo Abram, in the perspective in the video below.

Disclosure on AI use for this course: The original course was designed by Alexandria Deliz Liang (2022-2025). In 2026, this website was created after several requests from students to provide alternatives to in-person learning and requests from external colleagues to open the material for wider use. Making a website for the course was a difficult choice to make existentially. What is even the point of the four-hours per week of lecture. Will this reduce attendance? What is the point of attendance? Do I really want to make all of this public? After deciding that the pros out-weighed the cons, Claude Code was used to scrape text, images, audio recordings, and coding examples from the original course material to create the framework for this website. The scraped material was evaluated and further edited by the Alexandria Deliz Liang.