DSCI 100 Week 1 : Introduction

Sky (Kehan) Sheng

Meet your instructor

• Sky (Kehan) Sheng, PhD
• 👩‍💻 I am a post-doc of computer science and sessional lecturer of statistics.
• My research spans data science, AI fairness and animal welfare science.
• Contact
  • 📧: skysheng@cs.ubc.ca
  • 💼: ICCS Building Room 187
  • 🔗: skysheng.io

My path to data science:

• Grew up loving animals and wanted to be a vet as an undergrad, just like many of you might be figuring out your path right now
• Volunteered for wildlife rescue in Costa Rica, learned about tracking wild rhino using small satellites, which sparked my curiosity about the behaviour and movement patterns hidden in animal data
• Learned programming and how to analyze animal movement data, which led to a PhD using data science to study animal behaviour, preferences, friendships, and rivalries
• That work grew into research on AI fairness, how human values get embedded (and sometimes distorted) in AI systems
• Now: years of teaching experience, currently a post-doc and instructor

TA introductions

1. Data scientists come from all kinds of backgrounds, that’s what makes this field so interesting.
2. This class is diverse: different majors, experiences, and starting points.
3. If you have prior experience: help others! Teaching is one of the best ways to test your own understanding, explaining a concept simply to someone else reveals what you truly know. Everyone in this room knows something the rest of the class doesn’t.
4. If you have zero experience: that was me too when i entered university. My first laptop, my first terminal, it was intimidating, especially surrounded by classmates using jargon I didn’t understand. I thought I wasn’t smart enough for this. Looking back, that wasn’t true at all. Not knowing something just means you haven’t had the chance to learn it yet, it has nothing to do with your intelligence or your potential to succeed in this field.
5. Make friends and collaborate. Knowledge is freely available online, but friendships aren’t. The biggest thing you’ll gain from this course (and university in general) is the people you meet and the practice you get communicating, collaborating, and thinking together.

iClicker Set Up for Section 008

https://join.iclicker.com/HTES

• iClicker questions happen every Tuesday lecture
• Worth 2% of your final grade; your lowest 2 scores are dropped
• Each question: 0.5 points for participation + 0.5 points for correctness (unless stated otherwise)

iClicker test run: Do we still need to learn data science, programming and statistics in the AI era?

(A) YES! AI can’t replace my thinking!

(B) NO! My bestie ChatGPT knows it all!

(C) Strategically indecisive: “It depends…”

(D) I’m still figuring out how to click this thing

• There’s no correct answer to this warm-up question, it’s just to get comfortable using iClicker
• Haven’t set up iClicker yet? No worries, everyone gets credit for today’s questions regardless

Why learn data science in the AI era?

There is no shortcut to learning how to think

• You can’t outsource your thinking to AI. Exams do test whether you remember R syntax, but the long-term goal of this course isn’t memorizing code, AI is already great at that.
• My own experience: I learned Java years ago, rarely use it now, but the logical thinking skills stuck with me (I used to write R like I wrote Java!).
• This course trains you to be an independent thinker, life-long learner, and problem solver, to approach and solve new problems on your own. There’s no shortcut to that.
• If you copy-paste AI’s answers into your worksheets, you’re practicing copying and pasting, not thinking. That’s why AI isn’t allowed on tutorials, worksheets, or exams, you need to go through the process yourself, step by step.
• You’ll make mistakes, get stuck, and see scary error messages: that’s how you grow (my personal record is 8 hours debugging one issue!). Think of it like going to the gym: you have to lift the heavy weights yourself to build stronger problem-solving muscles.
• Your judgment and ability to think critically are what will make you stand out in this era.
• Read the book yourself, with your own brain. If you have AI read it for you, the machine is learning — not you.

AI updates every 6 months, but data science fundamentals don’t go out of fashion

• There’s a saying in AI: “If you learn slow enough, you’ll never need to learn again.”
• The best AI models and practices change every ~6 months. Techniques I’ve taught before (prompt engineering → system prompts → agentic workflows → MCP → harnesses) keep going out of date.
• It’s a better investment to spend your time learning the fundamentals — nobody can keep up with every new AI tool all the time.

DSCI 100: Absolute fundamentals a data scientist needs to know

• Some things don’t go out of fashion no matter how slowly you learn them, these are the absolute fundamentals every data scientist is expected to know.
• Example: in a future job interview, if you’re asked how regression works, “let me ask ChatGPT” won’t be the right answer
• DSCI 100 covers the absolute fundamentals of how to run a data analysis / data science project.

AI evaluation (AI eval) is a fancier term for data science

• “AI evaluation” is really just data science with a new name.
• The same tools you’ll learn here: bootstrapping, data visualization, statistical inference, prediction, are exactly what’s needed to evaluate AI models, one of the most in-demand skills today.

Introduction of the course

Your Teaching Team

Instructors

• Section 003 (R) Kenny Chiu
• Section 004 (R) Lasantha Premarathna
• Section 008 (R) Sky Sheng
• Section 009 (R) Lasantha Premarathna
• Section 101 (Python) Payman Nickchi

Coordinator

• Julia Peng (courses@stat.ubc.ca)

If you have administrative questions (e.g. are sick and going to miss a quiz), please read the FAQ and contact the course coordinator

Your turn!

• We encourage you to work collaboratively throughout DSCI 100
• Let’s start by getting to know the person next to you
  • Introduce yourself
  • Which program are you from?
  • Why are you interested in Data Science?
  • Anything else you want to mention!

Course Guidelines

Visit and abide by the course Code of Conduct on Canvas.

Basically: be good to each other.

• Help other students if they’re struggling
• Respect others while they speak; don’t interrupt
• Come to class prepared
• Value diversity, respect everyone’s ideas
• Be respectful and helfpul on Piazza

Remember: students in this class come from a wide variety of backgrounds - be good to each other!

What is data science exactly?

Data science is the use of reproducible and auditable processes to obtain value (i.e., insight) from data.

High-level goals of this course:

1. Learn how to use reproducible tools (Jupyter + R) to do data analysis
2. Learn how to identify and solve 4 common problems in data science

Problems we will focus on:

1. Predict a class/category for a new observation/measurement (e.g., cancerous or benign tumour)

2. Predict a value for a new observation/measurement (e.g., 10 km race time for 20 year old females with a BMI of 25)

3. Find previously unknown/unlabelled subgroups in your data (e.g., products commonly bought together on Amazon)

4. Estimate an average or a proportion from a representative sample (group of people or units) and use that estimate to generalize to the broader population (e.g., the proportion of undergraduate students that own an iphone)

Brief course walkthrough:

Read the Syllabus, Frequently Asked Questions, and JupyterGuide pages carefully!

Lecture/Tutorial Structure

• The first class meeting of the week is for your “lectures”, and the second is for your “tutorials”.

• We will post a reading before each lecture

  • e.g. the first chapter is reading_01

• The readings often provide example answers for the questions in worksheets and tutorials!

• We will kick off each lecture with a little intro

  • the slides should be up before each lecture, e.g. slides_01

Weekly Assignments

• You will typically have one graded assignment per lecture / tutorial

  • Lecture worksheets start in the first class each week, due Saturday 11:59pm
  • Tutorial worksheets start in the second class each week, due Saturday 11:59pm
  • No “submit button” - our server takes a snapshot at the due date/time
  • No extensions for weekly assignments. We will drop the lowest grade for each worksheet and tutorial at the end of the semester.

Main Evaluations

• One midterm covering ~6 weeks of material (summer ~3 weeks)

  • Same time & location of week 7’s tutorial (summer week 4). Invigilated in-person.

• One final covering all the material in the course

  • To be scheduled by Classroom Services. Invigilated in-person.

• A project (more on this later!)

  • You can collaborate with other people in class, but the work should be yours

First week learning goals:

• Edit and execute code and markdown in Jupyter notebooks

• Do the basics of data manipulation and visualization in R

• Use the help and documentation tools in R

I’ll begin with a quick Jupyter notebook demo using your first assignment, Worksheet 1.

Demo

• What is a notebook?
• Cells with either code or text
• Run with play button
• Saving notebook
• Restart kernel and run all before submitting
• Shut down the server when you are done

Demo

• If you run into a technical issue you can’t solve, first try to restart the kernel
  • Click the menu in the top left: Kernel -> Restart Kernel and Run All
• If the problem persists, restart your Jupyter server instance.
  • Save the notebook (avoid losing work). Download it to be extra safe.
  • Click File -> Hub Control Panel
  • Click “Stop my server”
  • Click the Log Out button in the top right corner
  • Close all JupyterLab tabs
  • Refresh Canvas page, click worksheet link again

Now it’s your turn!

• Navigate to Canvas, open worksheet_intro
• Use Firefox or Chrome, not Safari

Want to save these slides?
Right click > Print > Save to PDF.