Schedule

Part 1: Data Analysis

Week 1

Monday, 10/5

Before Class:

  1. Watch class welcome video

  2. Watch "Tableau for Data Science and Data Visualization - Crash Course Tutorial"

  3. Install Tableau Public (here), free. Or, if you can't / don't want to then let me know and I can help get an online version for you.

  4. Totally optional: I was on the UCSD Data Science Student Society (DS3) podcast recently, and really enjoyed it. Give it a listen if you want to learn more about me.

Class:

Wednesday, 10/7

Before Class:

  1. Watch "Data is Messy Part 1"

  2. Read "French election results: Macron’s victory in charts"

Class:

Week 2

Monday, 10/12

Before Class:

  1. Read "Confident Data Skills" Chapters 1 & 2.

  2. Watch Tableau in Two Minutes - Joining and Unioning Data Sources

Class:

  • Discuss reading

  • San Diego Police Department (SDPD)

Wednesday, 10/14

Before Class:

  1. Watch "Data is Messy" video 2

  2. Watch Mollie Pettit make amazing visualizations of police data.

  3. I also love This collection of "falsehoods programmers believe in". It isn't assigned reading, but I recommend you poke around. A good example is Falsehoods programmers believe about time, which starts with "There are always 24 hours in a day."

Class:

  • Discussion

  • Finish SDPD + Tableau

    • This one gets "turned in". I made a slack channel #sdpd-results. Screenshot the plot you think is most interesting or you are most proud of or whatever and send it to that channel (with a short note if it isn't clear alone).

Week 3

Monday, 10/19

Before Class:

  1. Read "Confident Data Skills". If you have the first edition, read Ch 3. For the second edition read the intro section of Part 2 ("The data science process" and "getting started").

  2. Read San Diego Union-Tribune article about faulty SDPD data analysis

Class:

Part 2: Data and the Internet

Wednesday, 10/21

Before Class:

  1. Watch "Questions and Metrics"

  2. Read "Confident Data Skills" Ch 4 "Identify the question"

Class:

Week 4

Monday, 10/26

Before Class:

  1. Watch "Natural Language Processing"

  2. Make an effort to read and understand "Using bias in word embeddings for historical analyses". It is an academic paper that explores a popular method of processing English text (the word2vec algorithm) and how it encodes societal biases of the training data. It is a pretty tough read, so you may need to google some terms and take some time to work through it, and it is ok if you don't totally follow everything

  3. Read "She Giggles, He Gallops" (fun article)

Class:

Wednesday, 10/28

Before Class:

  1. Watch "Web Scraping"

Class:

Week 5

Monday, 11/2

Before Class:

  1. Read Women in Congress

  2. Read Murder rates don't tell us everything about gun violence

Class:

Wednesday, 11/4

Before Class:

  1. Watch "Imposter Syndrome"

  2. Read The media has a probability problem

Class:


Part 3: Audio Classification in the Cloud

Week 6

Monday, 11/9

Before Class:

  1. Watch "Audio is Data"

Class:

Wednesday, 11/11

No class.

Week 7

Monday, 11/16

Before Class:

  1. Read How does Spotify know you so well?

Class:

Wednesday, 11/18

Before Class:

  1. Watch "The Cloud"

Class:


Part 4: Photoshop Detection

Week 8

Monday, 11/23

Before Class:

  1. Watch "Images are Data!"

  2. Read Physiognomy’s New Clothes

Class:

Wednesday, 11/25

Before Class:

  1. Read at least one case study from "Ethics and Data Science". I recommend reading the whole thing, but I get that you all have other classes too... UPDATE: Looks like some of the links to case studies in that book are broken. Check them out here: https://aiethics.princeton.edu/case-studies/case-study-pdfs/

Class:

  • Just talking

  • catching up / finishing audio stuff

Week 9

Monday, 11/30

Before Class:

  1. Skim bits of this very long paper: A Picture's Worth... We will be developing one algorithm from the paper together, in class.

Class:

Wednesday, 12/2

Before Class:

  1. Read We Experiment on Human Beings!

Class:

Week 10

Monday, 12/7

Before Class:

  1. Watch "How Classification Works"

  2. bonus (optional, hard, deep) Why most published research findings are false

Class:

Wednesday, 12/9

Before Class:

  1. Watch "Final Lecture"

  2. Look, I get that you are more worried about finals than doing reading. So why don't you save this one for over break? To me, this gets at the core of data science: The Truth Continuum

Class:

  • Discussion