Skip to content

Teaching repo for Applied Data Science @ Columbia, a project-based course for data science skills (statistical thinking, machine learning, data engineering, team work, presentation, endurance of frustration, etc).

Notifications You must be signed in to change notification settings

lolibra2k4/ADS_Teaching

 
 

Repository files navigation

Stat GU4243/GR5243 Applied Data Science

Fall 2023 - Teaching Materials (Syllabus)


Project cycle 1: (Individual) R notebook for exploratory data analysis

(starter codes)

Week 1 (September 5)

Week 2 (September 11)

Week 3 (September 20)

  • Project 1 presentations.

Finished student projects


Project cycle 2: Shiny App Development

(starter codes)

Week 3 (September 20)

  • Project 2 starts.
    • Check Piazza for your project team and follow the video instructions to clone the starter codes.
    • After you join project 2, you can clone your team's GitHub repo to your local computer.
    • You can find in the starter codes:
      • the project description,
      • an example toy shiny app.

Week 4 (September 25)

Week 5 (October 2)

Week 6 (October 11)

  • Project 2 presentations

Finished student projects


Project cycle 3: Predictive analytics of climate data

(starter codes)

Week 6 (October 11)

Week 7 (October 18))

  • Presentation of ClimSim paper by Prof. Sungduk Yu
  • Q&A and Help/Discussion Session with a student who worked on ClimSim previously.

Week 8 (October 25)

Week 9 (November 1)

  • Project 3 submission and presentations

Project cycle 4: Algorithm implementation and evaluation

(starter codes)

Week 9 (November 1)

Week 10 (November 8)

  • Talk on fairness (see slides)
  • Overview on the methods
  • Method assignment on Piazza

Week 11 (November 15)

  • 1st half : Form groups and brainstorm for subject of project 5
  • 2nd half : Team meeting/helproom for project 4

Week 12 (November 22)

Thankgsgiving Break (November 22)

Week 13 (November 29)

  • Project 4 presentations

About

Teaching repo for Applied Data Science @ Columbia, a project-based course for data science skills (statistical thinking, machine learning, data engineering, team work, presentation, endurance of frustration, etc).

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages

  • HTML 97.6%
  • Jupyter Notebook 2.3%
  • Other 0.1%