Due: 2024-10-02: 1200 UTC Released: 2024-09-27: 1159 UTC 10 Exercises 18 Points You need 13 points for 100% Time limit: 4 hours
Due: 2024-11-06: 1200 UTC Released: 2024-11-01: 1159 UTC 9 Exercises 17 Points You need 12 points for 100% Time limit: 4 hours
Due: 2024-12-11: 1200 UTC Released: 2024-12-06: 1159 UTC
Due: 2024-11-11 [time zone converter] Released: 2024-10-21
This notebook will walk you through the inner workings of a common statistical concept called linear regression
Due: 2024-11-18 [time zone converter] Released: 2024-11-04
Notebook 13 will guide you on the topic of classification, in which you are given a set of labeled data points and you wish to learn a model of the labels
This notebook will help you implement the logistic regression, which is a canonical example of a classification algorithm
We will discuss concepts related to discriminants and Heaviside, sigmoid function, maximum likelihood estimation, gradient descent, and optimization via Newton's method.
Released: 2024-09-02
The notebook is intended to help you review basic geometric concepts related to linear algebra. Treat the notebook as a diagnostic to see where you might want to brush up.
We are releasing this relatively early in the course. However, you will not deal with linear algebra in a meaningful way until we get to topic 11.
Released: 2024-09-09
The notebook gives you an introduction to mining the web using several packages including the requests module, BeautifulSoup, and web APIs
Released: 2024-09-16
This notebook is a demonstration on how to work with Pandas. There is nothing to submit, but it is a useful reference for some of the tasks you will have to accomplish using Pandas in this course.
Released: 2024-09-16
In this notebook, we will go through data visualization capabilities available to you in Python
Bootcamp:
Here is a summary of your goals for the coming week.
Complete Midterm 2 if you have not already done so. The exam window is posted above.
Complete Notebook 12
Practice problems for Midterm 2. See Practice Midterm 2 Release Notes linked above.
Office hours. We will have regularly scheduled office hours this week. As usual, feel free to prepost questions in the weekly office hour post.
Exam Results Watch Piazza for information on the presentation of exam stats and walkthrough.
Bootcamp:
Here is a summary of your goals for the coming week.
Prepare for Midterm 2. The exam window is posted above.
If you want to get a jump on the next assignment Notebook 12
Practice problems for Midterm 2. See Practice Midterm 2 Release Notes linked above.
Office hours. We will have regularly scheduled office hours this week. As usual, feel free to prepost questions in the weekly office hour post.
Bootcamp:
Here is a summary of your goals for the coming week.
Finish Topic 11 + Notebook 11. This topic and notebook is the last one whose material will be included in the upcoming Midterm 2.
Start studying for Midterm 2 if you haven't already. The exam window is posted above.
If you want to get a jump on the next assignment Notebook 12.
Practice problems for Midterm 2. See Practice Midterm 2 Release Notes linked above.
Office hours. We will have regularly scheduled office hours this week. As usual, feel free to prepost questions in the weekly office hour post.
Bootcamp:
Here is a summary of your goals for the coming week.
Finish Notebook 10
Start Topic 11 + Notebook 11
Regarding Topic/Notebook 10, if you are having any problems understanding COO/CSR storage formats, start with the Wikipedia article on sparse matrices. Then, go ahead and watch Topic 11, Lesson 3, especially if you are having trouble with the exercises in Notebook 10 related to these storage formats.
Practice problems for Midterm 2. See Practice Midterm 2 Release Notes linked above.
Office hours. We will have regularly scheduled office hours this week. As usual, feel free to prepost questions in the weekly office hour post.
Bootcamp:
Here is a summary of your goals for the coming week.
Finish Notebook 9
Start Topic 10 + Notebook 10
Regarding Topic/Notebook 10, if you are having any problems understanding COO/CSR storage formats, start with the Wikipedia article on sparse matrices.
Practice problems for Midterm 2. Coming soon. Stay tuned for updates!
Office hours. We will have regularly scheduled office hours this week. As usual, feel free to prepost questions in the weekly office hours thread that you'd like answered in the office hour.
Bootcamp: Module 0: Session 17
Here is a summary of your goals for the coming week.
Notebook 7 (Pandas) - There is a notebook titled Topic 7 (optional) which is a primer on Pandas. Additionally there is a graded assignment titled Notebook 7 (required) which contains exercises you are expected to complete.
Notebook 9 (SQL) - If you get ahead Notebook 9 has been released.
Office hours. We will hold regularly scheduled office hours. As usual, feel free to pre-post any questions to the weekly OH post.
Exam Results Watch Piazza for information on the presentation of exam stats and walkthrough.
Bootcamp: Module 0: Session 15, 16
Your main task for this week is to prep for and take the first exam, Midterm 1.
Exam window open and close are listed above. Please note that UTC is a 24-hour time. This means that there is only one 11:59 (the minute before noon). Also note that your exam must be complete before the exam window closes.
Please review the exam guide and release notes before asking questions on logistical details.
Other items
Notebooks 7. If you want to get a head start on this assignment, it is available on your LMS.
Office hours. We will hold a regularly scheduled office hour session on Thursday. Please do not ask questions concerning exam logistics or topics, they will not be answered in the office hours session. Information on logistics is provided in great detail on this website, and any unaddressed questions are best posted publicly to Piazza.
Bootcamp: Module 0: Session 12, 13, 14
Here is a summary of your goals for the coming week.
Finish Topic 5 + Notebook 5. Since Midterm 1 includes this material and starts shortly after, we will not accept any submissions after the late-deadline.
Study for Midterm 1. See the release notes linked above. You can find the problems and video walkthroughs on your LMS. There will be more detailed logistical information about Midterm 1 just before it is released.
Per the schedule, Topics 7 (required) and 8 (optional, ungraded) will also release this week. However, since it's not on Midterm 1 and isn't due until after the midterm closes, I will be asking the staff to prioritize questions related to the exam and related notebooks.
Office hours. We will have regularly scheduled office hours. The agenda is Notebook 5, due on Monday. If you have specific questions, you can request them in the weekly office hours post.
(edX only) Take ID Verification Quiz: Make sure you have completed the ID verification quiz that is required to take the exam next week. You do not want to leave that until the day before.
Bootcamp: Module 0: Session 9, 10, 11
Here is a summary of your goals for this coming week.
Finish Notebook 4
Continue your review of the practice problems of "Topic 3" (math prerequisites review)
Plan to review the sample solutions for Notebook 2 when they are released on Wednesday. Piazza is a good place to ask questions about them.
Start Topics 5&6 If you finish the above early.
Practice Problems for Midterm 1. Check Practice Midterm 1 Release Notes. The problems are on Vocareum and you can find the links on your LMS.
Office hours. We will hold regularly scheduled office hours. As before, you are welcome to pre-post questions on the weekly office hours post.
Bootcamp: Module 0: Session 5, 6, 7, 8
Here is a summary of your goals for the coming week.
Your primary goal for this week is to finish Topic 2.
Note: The Topic 2 videos will ask you to stop periodically and do specific pieces of Notebook 2. It will also show you solutions but do try to do the exercises yourself before you watch them. Notebook 2 has been refactored since the videos were produced, so the solutions will not align exactly. The video solutions will still be helpful as the concepts in the notebook have not changed. Also, Topic 2 videos refer to "quizzes," which did not make it into the final cut. So, ignore references to those.
Office hours. We will hold a regularly scheduled office hour session. The exact agenda is TBD. You are as always welcome to pre-post questions for the session as a "follow-up discussion" on the weekly office hours post (look later this week), and we'll try to address them.
Practice exam questions. We will release these early next week (along with solutions and video walkthroughs), so stay tuned.
Words of encouragement. For some of you, it may have been quite a bit of work getting up to speed on Python, and you might not feel confident yet. Try not to be discouraged! (See this inspiring GT story about overcoming challenges and another positive reminder for grad students.
Bootcamp: Module 0: Sessions 2, 3, 4
Since the start of class, you should have ...
become acquainted with your LMS (Canvas for OMSA, EdX for VMM);
read the syllabus and reviewed the course schedule;
watched "Topic 0" and attempted Notebook 0
attended the "kick-off" office hour or watched the recording
and met some of your peers on Piazza. Indeed, the Piazza forums have been fairly active -- so thanks for your participation!
Office hours. We will hold office hours on Thursdays from 8:30-9:30 pm ET.
On any given week, feel free to post any specific office hour questions ahead of time in the appropriate Piazza thread, especially if you have a burning question and cannot attend the session itself. (Or, even if you can attend, posting in advance will help the staff on-call that day prepare.) These threads are usually created on Tuesdays.
Reminder. Per the syllabus, questions and concerns are submitted through Piazza. Messages sent via email or through Canvas will go unanswered.
Bootcamp: Module 0: Session 1
Read the syllabus. It's available on Canvas. It has lots of relevant information about logistics, philosophy, and expectations, all of which you are responsible for knowing and abiding by while taking this class. If you have questions about anything, feel free to make a piazza post to instructors.
Look at the schedule. It's also available on Canvas. We pre-post all due dates and times (see below) from today so you can plan your semester accordingly.
Learn the due-time convention. Per the syllabus, unless otherwise noted, all assignments are due at 11:59 UTC (Coordinated Universal Time). Learn what this means for wherever you happen to be! We will not grant any extensions because you misunderstood the deadlines. If it's helpful, please see this handy Time Zone Converter.
Get up to speed on Python. If you are rusty on programming in any language or have never used Python, you need to get up to speed quickly. For instance, please take this week to get a head start on next week's materials. These should be available as Topic 1 and Notebook 1.
Pro-tip: Topic and Notebook referencing convention.
The assignments,
which we interchangeably call "notebooks," may have one or more parts
and, within each part, several numbered exercises. Each notebook part will have its own dedicated public thread. We ask you to keep any public questions about that part on the appropriate thread. This makes it easier for other students to find find related posts. It is possible that your question has already been answered.
When you want to post
a question about a particular exercise, we strongly recommend using
the following convention: in the subject of your post (and within it),
use nb\<#>[.part#].[exercise#] to refer to a particular exercise.
For example, nb4.1.2 means Notebook 4, Part 1, Exercise 2. Also, please
tag your post with the associated notebook (e.g., nb4 in this example).
If a notebook only has one part, you can omit the part number, e.g.,
nb7.2. If your question concerns the general topic (or associated
readings and videos, rather than the notebook), use the appropriate tag
(e.g., topic4, topic7). Adhering to these conventions help your peers
find related questions and will help the instructors triage questions
faster.
Special "kick-off" session: Check Piazza for the details regarding your specific section. This "kick-off" office hour is intended to answer questions you might have about getting started in the course and will be recorded in case you can't make it. (That also implies that if you choose to connect by video, you may want to brush your hair or don a disguise if that's an issue.) If you are on the fence about whether to stay, this hour is a good chance to ask questions that will help you decide.
Office hours begin next week Every Thursday from 8:30-9:30 pm US Eastern Time, the teaching staff will hold a live office hour session. These begin this Thursday.
Boot Camp: We have put together the CSE6040 Bootcamp to help students with limited Python or programming exposure. See What is the bootcamp for more details.
All official discussions are on Piazza. The teaching staff use this forum, Piazza, for general Q&A. Announcments will be posted here. Doing so helps us triage and track issues. You can post anonymously if you wish! If you need to ask a question of one of us not visible to your peers, you can do so by posting a private message. To do so, click New Post, then select Individual/instructor(s) under Post to, then type Instructors. However, we strongly recommend posting publicly; you will get a response more quickly, and it's a great way to get to know your classmates.