- Instructor: Andy Choens, MSW
- Course Name - Number: Intro to Data
- PBH210 (Intro To Data)
- PBH211 (Intro To Data Lab)
- Course Location - Time: Thursday 17:30 - 19:30
- Office Hours and Location: Since I also work in Troy, office
hours are a little tricky. I can make myself by appointment as
needed. I will ALWAYS be available after class and can stay as late
as I need to. Additionally, I do not work on the following days, and
can be at the school to discuss the class, lab, etc. by appointment.
- January 17
- January 31
- February 14
- February 28
- March 13
- March 27
- April 10
- April 24
- May 8
- Contact Information:
- ACPHS Email: Andrew.Choens@acphs.edu
- Acuitas Email: Andy.Choens@AcuitasHealth.com
Mathematics is the language in which God has written the universe.
-- Galileo Galilei
| Description | Date |
|---|---|
| First Day of Spring Semester | Jan 13, 2020 |
| Week 01 | Jan 16, 2020 |
| Week 02 | Jan 23, 2020 |
| Week 03 | Jan 30, 2020 |
| Week 04 | Feb 06, 2020 |
| Week 05 | Feb 13, 2020 |
| Week 06 | Feb 20, 2020 |
| Week 07 | Feb 27, 2020 |
| Midterm Exam | Mar 05, 2020 |
| Spring Break (No Class) | Mar 12, 2020 |
| Week 09 | Mar 19, 2020 |
| Week 10 | Mar 26, 2020 |
| Week 11 | Apr 02, 2020 |
| Week 12 | Apr 09, 2020 |
| Week 13 | Apr 16, 2020 |
| Week 14 | Apr 23, 2020 |
| Reading Day | Apr 29, 2019 |
| Final Exam | Apr 30, 2019 |
Attendance Policy: I expect you to attend/participate in class and lab. By doing so, you will learn more. With that said, you are an adult and I intend to treat you as such. If for some reason you are unable to attend class notify me as soon as possible and we will work out how you can complete the necessary assignments.
Office Hours: As an adjunct, I dont have an office other than our classroom/lab and I spend most of my day in Troy, NY at my day job. If there is something you would like to discuss, contact me via Slack and we will arrange a time to meet. You are welcome to come out to my office in Troy where we can meet in a conference room. Alternatively, I will usually be in the classroom by ~6:00 PM on Thursday nights. If you tell me ahead of time - I can guarantee I will be in the classroom by 6:00. I am here to support you. Let me know how I can best do that.
Inclement Weather: If the school is closed we will not have class. If the school is open we will have class. With that said, our class is at night and I suspect at least some of you live off campus. If you feel unsafe about traveling before/after our class due to weather, let me know and we will work something out.
Data science is an interdisciplinary field that uses scientific methods, processes, algorithms and systems to extract knowledge and insights from data in various forms, both structured and unstructured,[1][2] similar to data mining.
Data science is a "concept to unify statistics, data analysis, machine learning and their related methods" in order to "understand and analyze actual phenomena" with data.[3] It employs techniques and theories drawn from many fields within the context of mathematics, statistics, information science, and computer science.
Turing award winner Jim Gray imagined data science as a "fourth paradigm" of science (empirical, theoretical, computational and now data-driven) and asserted that "everything about science is changing because of the impact of information technology" and the data deluge.[4][5]
Topics touched upon in this interdisciplinary course include:
The Intro To Data course breaks down into roughly two halves. The first half of the course, which ends roughly when you go off for Spring Break, is focused on data manipulation. That is, the science of importing, managing, and describing your data. After you get back refreshed and renewed from Spring Break, we will spend some time thinking about regression (linear and logistic) and comparisons (the dreaded p-value).
This course has a single prerequisite - curiosity. No analyst or researcher can succeed with out curiosity. Bring it in abundance.
Out-of-pocket costs for this course are zero. All materials needed to complete this course are available online, for free. That said, these materials are very important. Because classroom time is limited, there will be important material covered in the reading that will not be covered in-class.
- R For Data Science (R4DS) by Hadley Wickham and Garrett Grolemund
- Additional assigned readings, videos, etc.
There is a dead-tree edition of the primary text. Although it does cost money, the authors have earned it. I personally own a copy of each. However, the online edition has everything you need for class. Purchasing the dead-tree edition is optional.
Specific readings will be assigned from these additional resources:
- R-bloggers
- Andrew Gelman's blog: Statistical Modeling, Causal Inference, and Social Science
- Frank Harrell's blog: Statistical Thinking
The tools used in this class are Free and Open Source Software (FOSS). We'll discuss what that means in class, but for now it can simply mean you don't have to pay anything to use them. The first lab includes time to install and configure these tools.
Students will use the following software:
| Name | Recommended Download Link | License | Cost |
|---|---|---|---|
| R | Download R - CRAN | GPL v2 | $0.00 |
| R Studio | Download RStudio Desktop | AGPL v3 | $0.00 |
| Excel/LibreOffice | Download LibreOffice | MPL v2 | $0.00 |
Students may use other R IDEs such as Emacs ESS, but classroom examples will focus on RStudio. Students may use either Microsoft Excel or LibreOffice Calc for spreadsheet assignments/projects (or other compatible software).
Although taught together, the lab portion of the course (PBH211) will be graded separately from the class.
| Assignments | Assign Date | Due Date | % Final Grade |
|---|---|---|---|
| Worth Discussing | 10% | ||
| Assignment 01 | 2020-01-16 | 2020-01-30 | 10% |
| Assignment 02 | 2020-02-06 | 2020-02-27 | 10% |
| Midterm Exam | 2020-03-05 | 25% | |
| Assignment 03 | 2020-03-19 | 2020-04-02 | 10% |
| Assignment 04 | 2020-04-09 | 2020-04-23 | 10% |
| Final Exam | 2020-04-30 | 25% | |
| Total | 100% | ||
| : Intro to Data Assignments |
Throughout the course I have a series of planned discussion I am calling "Worth Discussing". These are articles, often from a newspaper such as the Washington Post or Ars Technica which highlight something interesting that I would challenge you to think about. There is no single right or wrong answer to these discussions, but they are important nonetheless.
- Assignment 01: Collect it yourself!
- Assignment 02: How will data affect your life?
- Assignment 03: Reproducibility & Replicability
- Assignment 04: Crisis
Assignment details are available on Canvas.
Each lab builds on the content of that weeks lecture. Thus, each lab is assigned on the day of the lecture and is due the day before the next lecture. Because I recognize that things happen and that this is a lot to learn in a short amount of time, I will drop your lowest lab grade. But, be aware that you are still responsible for the material on that lab for the midterm/final exam.
| Description | Assign Date | Due Date |
|---|---|---|
| Lab 01 | Jan 16, 2020 | Jan 22, 2020 |
| Lab 02 | Jan 23, 2020 | Jan 29, 2020 |
| Lab 03 | Jan 30, 2020 | Feb 05, 2020 |
| Lab 04 | Feb 06, 2020 | Feb 12, 2020 |
| Lab 05 | Feb 13, 2020 | Feb 19, 2020 |
| Lab 06 | Feb 20, 2020 | Feb 26, 2020 |
| Lab 07 | Feb 27, 2020 | Mar 04, 2020 |
| Lab 08 | Mar 05, 2020 | Mar 18, 2020 |
| Lab 09 | Mar 19, 2020 | Mar 25, 2020 |
| Lab 10 | Mar 26, 2020 | Apr 01, 2020 |
| Lab 11 | Apr 02, 2020 | Apr 08, 2020 |
| Lab 12 | Apr 09, 2020 | Apr 15, 2020 |
| Lab 13 | Apr 16, 2020 | Apr 22, 2020 |
| Lab 14 | Apr 23, 2020 | Apr 29, 2020 |
| : Intro to Data Labs |
| Grade Letter | Numeric Score | Criteria |
|---|---|---|
| A | 95 | Lab notebook contains complete, correct, and throughtful answers for all questions. |
| B | 85 | Lab notebook contains a mostly complete, correct, and relevant answers for most questions. |
| C | 75 | Lab notebook is incomplete or contains consistent errors. |
| D | 65 | Lab notebook is incomplete or contains consistent errors. |
| F | 55 | Lab notebook demonstrates student is not completing the readings and/or understanding the material. |
| NA | 00 | Failed to complete and/or submit the lab. |
| :Lab Grade Criteria |
PBH210 is a class. PBH211 is a lab. Programming and working with data
are skills best learned by asking lots of questions and engaging in
the practice. There is a lecture component of this class. You will get
more out of it if you are engaged. If you don't understand, tell me.
Each week's lab will build upon what we learned during the lecture. Students are permitted to discuss their labs with others in the class, discuss on Canvas, etc. That said - what you submit should be YOUR work.
Students are expected to complete all class readings. I cannot stress this enough. Most of you, I assume, are not programmers. There is going to be a learning curve. If class is the first time you encounter a concept, you won't learn this material.
- Topics:
- Course Introduction
- Please complete your name poster!
- Complete class survey (if you have not already done so).
- What is "Data Science"?
- What is Tidy Data?
- Define: Vector
- Define: Dataframe
- Our Tools (R, RStudio, Excel)
- Note: Students may access these tools via the ACPHS virtual desktops.
- I will refer to the book, R For Data Science as R4DS to save space here.
- Assigned Reading:
- The readings for weeks one and two will cover R4DS Part 1, Explore.
- R4DS: Introduction
- R4DS: Explore-Intro
- R4DS: Data Visualization
- R4DS: Workflow Basics
- Topics:
- Explore
- Data Visualization
- Workflow Basics
- Measures of centrality
- Assigned Reading:
- Topics:
- Data Transformation
- Workflow: Scripts
- EDA
- Workflow: Projects
- Compare R to Excel
- Due: Assignment 01
- Assigned Reading:
- Readings for weeks three and four will cover R4DS Part II, Wrangle.
- R4DS: Wrangle Introduction
- R4DS: Tibbles
- R4DS: Data import
- R4DS: Tidy data
- Topics: Visualize This
- Data Wrangling (yee-haw)
- Tibbles v. data.frames
- Data Import
- Tidy Data
- Assigned Reading:
- R4DS: Relational data
- Read this one a couple of times. It isn't easy.
- R4DS: Strings
- R4DS: Factors
- R4DS: Dates and times
- R4DS: Relational data
- Topics:
- Relational data (inner join)
- Strings
- Factors
- Dates and times
- Assigned Reading:
- Readings assigned for week five will cover R4DS Part III, Program.
- R4DS: Program Introduction
- R4DS: Pipes
- R4DS: Functions
- R4DS: Vectors
- R4DS: Iteration
- Topics:
- Relational data (left join)
- Program Control: if/then/else statements
- Loops: for/while
- Functions
- Vectors
- Assigned Reading:
- Readings assigned for week six wil cover R4DS Part V, Communicate.
- R4DS: Communicate Introduction
- R4DS: R Markdown
- R4DS: Graphics for communication
- R4DS: R Markdown formats
- R4DS: R Markdown workflow
- Topics:
- R Markdown
- Relational Review
- What do you want to discuss/review?
- Assigned Reading:
- Readings assigned for week seven introduce no new concepts. These are useful and will expand on your understanding of things we have already introduced in class/lab.
- Tidy Data by Hadley Wickham
- Wikipedia: Literate Programming
- Why I Love R Notebooks
- Data wrangling with R and RStudio
- A 55 minute video which will review much of the material we have covered thus far in the course. Nothing new added, but, hearing it a different way cannot hurt you.
- Data Transformation Cheat Sheet
- Data Visualization Cheat Sheet
- Pizza, and an exam.
- Assigned Reading:
- Pull Oneself Up By One's Bootstraps
- R Markdown Formats
- How to do EVERYTHING in R Markdown (nearly)
- What Has Happened Down Here Is The Winds Have Changed
- Please use this time to review anything you did not understand in the first half of the course.
- I am still working on some of the readings for the second half of the class, so some of these may change.
- Topics: Is Statistical Significance, Significant?
- Standard Deviation
- Confidence Intervals
- What is a P-Value?
- What else can we do?
- R Markdown
- Assigned Reading:
- Topics: Tell me straight, does it fit?
- Basic Linear regression
- Judging a linear model?
- Assigned Reading:
- Topics:
- Multivariate linear regression
- Ridge/Lasso regression
- Assigned Reading:
- Topics: Lasso Your Future :robot_face:
- Ethical Analysis
- Logistic Regression
- Assigned Reading:
- Topics: Can't See The Forest For All These Trees
- Ethical Analysis 2
- Decision Trees
- Random Forests
- The relationship between the random Forest and bootstrapping
- Due: Assignment 04
- Assigned Reading:
- Due: Assignment 05
- Assigned Reading:
- The final exam includes complimentary pizza.