Today Next Midsemester (First Semester) · in 8 days
DS 227

Knowledge Discovery in Data

Frameworks and processes of knowledge discovery in data, scraping, preprocessing, exploration, storytelling, and ethics

🔌 Try the live API Playground → Poke a real public API in your browser, then copy the Python and run it in Colab — the Week 4 skills, hands-on.
Course Overview
📖
Course Syllabus
Schedule, grading, policies & resources
→
KDD Foundations 3 modules
intro
Welcome to DS 227
Module intro
→
1
Introduction to Knowledge Discovery in Data
Module 1
→
2
KDD Frameworks: CRISP-DM, SEMMA & the KDD Process
Module 2
→
Data Scraping & Preprocessing 4 modules
3
Data Scraping I: Web Fundamentals & HTML Parsing
Module 3
→
4
Data Scraping II: APIs, Dynamic Pages & Scraping Ethics
Module 4
→
5
Data Preprocessing I: Cleaning, Missing Data & Outliers
Module 5
→
6
Data Preprocessing II: Integration, Transformation & Reduction
Module 6
→
Data Exploration 2 modules
7
Data Exploration I: Descriptive Statistics & Univariate EDA
Module 7
→
8
Data Exploration II: Multivariate EDA & Visualization
Module 8
→
Journalism & Storytelling 2 modules
9
Data Journalism: Finding Stories in Data
Module 9
→
10
Data Storytelling: Narrative, Dashboards & Communication
Module 10
→
Ethics, Privacy & Synthesis 2 modules
11
Ethics & Privacy in Data and Analytics
Module 11
→
12
Course Synthesis & Final Presentations
Module 12
→
👥

No Projects Yet

Group projects for this course will appear here.

Loading resources...

Weekly Lab Exercises

Practice exercises for each week's lecture (30-60 min each).

1
Week 1 Lab
Welcome Lab: Where You're Starting From
2
Week 2 Lab
Walking a Dataset Through CRISP-DM
3
Week 3 Lab
Parsing HTML with BeautifulSoup
4
Week 4 Lab
Pulling Data from an API
5
Week 5 Lab
Missing Values & Outliers
6
Week 6 Lab
Integrating & Reducing Data
7
Week 7 Lab
Descriptive Statistics & Univariate EDA
8
Week 8 Lab
Multivariate EDA & Visualization
9
Week 9 Lab
Finding a Story in Data
10
Week 10 Lab
Building a Narrative Dashboard
11
Week 11 Lab
Auditing a Dataset for Privacy Risk
12
Week 12 Lab
Final Project Workbench

💡 Tip: Labs run and are submitted right here in the browser — no installs, no Colab. Your submitted code is what's recorded, and re-submitting a lab replaces your previous attempt.