MSDS692 Data acquisition

There are lots of exciting and interesting problems in data science, such as figuring out what the right question is, selecting features, training a model, and interpreting results. But all of that presupposes a tidy data set that is suitable for analysis or training models. Industry experts all agree that data collection and preparation is roughly 3/4 of any analysis effort. Or, as Kareem Carr puts it (I'm guessing he includes data acquisition and organization in the term "cleaning"):

The title of this course is "Data Acquisition" but of course, once we get the data, we have to organize it into handy data structures and typically have to extract information from the raw data. For example, we might need to boil down a Twitter stream into a single positive or negative sentiment score for a given user. This course teaches you how to collect, organize, coalesce, and extract information from multiple sources in preparation for your analysis work. Along the way, you'll learn about the commandline, git, networks, the internet protocols, and building your own web servers.

This course is part of the MS in Data Science program at the University of San Francisco.

Course details

INSTRUCTOR. Terence Parr. I’m a professor in the computer science and data science program departments and was founding director of the MS in Analytics program at USF (which became the MS data science program). Please call me Terence or Professor (not “Terry”).

OFFICE HOURS

Terence is generally available on slack or email on-demand.

SPATIAL COORDINATES:<br>

Downtown campus combined rooms 155-156 on main floor.
My office is room 525 @ 101 Howard

TEMPORAL COORDINATES. Tue Aug 24, 2021 - Thur Oct 14, 2021 with 2 Sections of live lecture: 10am-11:50am and 1pm-2:50pm. Morning lecture will be zoom recorded for any remaining remote students.

INSTRUCTION FORMAT. Live class runs for ~2 hours, 2 days/week. Instructor-student interaction during lecture is encouraged by speaking up in zoom. We'll often mix in mini-exercises / labs during class. All programming will be done in the Python 3 programming language, unless otherwise specified.

LAPTOP POLICY. My policy is that all student laptops must be closed during class unless we are doing a lab or I specifically ask you to follow along as I type into my computer. All materials for the course are available in this repository, which reduces your need to take notes considerably.

Student evaluation

| Artifact | Grade Weight | Due date | |--------|--------|--------| |Data pipeline| 5%| Tue, Aug 31, 1pm (start of section 2) | |Search Engine Implementation| 12% | Tue, Sep 14, 1pm | |TFIDF document summarization| 10%| Thu, Sep 23, 1pm | |Recommending Articles| 9% | Sat, Oct 2 11:59pm | |Tweet Sentiment Analysis| 9% | Tue, Oct 12 1pm | |Exam 1| 25%| Tue, Sep 21 | |Exam 2| 30%| Thu, Oct 14 |

I reserve the right to change projects until the day they are assigned.

All projects are individual projects not group efforts! All projects will be graded with the specific input or tests given in the project description, so you understand precisely what is expected of your program. Consequently, projects will be graded in binary fashion: They either work or they do not. The only exception is when your program does not run on the grader's or my machine because of some cross-platform issue. This is typically because a student has hardcoded some file name or directory into their program. In that case, we will take off a minimum of 10% instead of giving you a 0, depending on the severity of the mistake. Some projects will be tested with some hidden unit tests; e.g., see the evaluation section of the search project.

Please go to github and verify that the website has the proper files for your solution. That is what I will download for testing.

Each project has a hard deadline and only those projects working correctly before the deadline get credit. My grading script pulls from github at the deadline.

No partial credit. Students are sometimes frustrated about not getting partial credit for solutions they labored on that do not actually work. Unfortunately, "almost working" just never counts in a job situation because nonfunctional solutions have no value. We are not writing essays in English that have some value even if they are not superb. When it comes to software, there is no fair way to assign such partial credit, other than a generic 30% or whatever for effort. The only way to determine what is wrong with your project is for me to fix and/or complete the project. That is just not possible for 90 students. Even if that were possible, there is no way to fairly assign partial credit between students. A few incorrect but critical characters can mean the difference between perfection and absolute failure. If it takes a student 20 hours to find that problem, is that worth more or less partial credit than another project that is half-complete but could be finished in five hours? To compensate, I try to test multiple pieces of the functionality in an effort to approximate partial credit.

Grading standards. I consider an A grade to be above and beyond what most students have achieved. A B grade is an average grade for a student or what you could call "competence" in a business setting. A C grade means that you either did not or could not put forth the effort to achieve competence. Below C implies you did very little work or had great difficulty with the class compared to other students.

Honorlock

All tests use HonorLock via Canvas and have strict time limits. You will be unable to do anything other than take the test; no access to the Internet etc. A proctor will monitor you during exams to ensure you do not communicate with anyone else during the test. Generally speaking, HonorLock will record all your web, computer, and personal activities (e.g., looking at your phone) during the quiz. It will flag suspicious behavior for my review and will save the recordings for 6 months if I need to go back and check it.

Please see the How to use" page for students. Either I or another instructor will launch a practice quiz on Canvas during the first week of class to ensure everything is set up properly.

Google Chrome and a webcam are required. At the beginning of the quiz, you will be able to add the Chrome extension for Honorlock, then follow the instructions to share your screen and record your quiz.
You might be asked to change settings on your computer while doing this. You can change the setting and come back to the quiz. This change should only be expected once.
If you are showing us the side view of your face we don’t know if you’ve got an earbud in your other ear. This is not allowed.
Make sure you are facing into the camera as Honorlock will shut down the system and force you to restart.
Make sure that you are not looking down and to the right as if you are looking at notes or using your phone. Honorlock will flag this as cheating.
You must not start and stop your browser; Honorlock will flag this is cheating.
You must not use other applications or visit non-Canvas-quiz URLs during the exam unless the exam indicates this is permitted.
Do not have your phone visible as the proctor will stop the quiz

Side notes:

Start the quiz with a single Chrome window and single tab in that window.
When the "share screen button" is grey, you can still click it and it will work.
HonorLock flags activities other than the allowed ones: for example when you are accessing a website other than canvas or looking at your phone. I will evaluate these cases and make a judgment myself. I will reach out to you when necessary. If you have followed the guidelines, you don’t need to worry.
If you have an honorlock software issue during the test, you must take a screen picture with your phone or ipad and notify me immediately via private slack to timestamp the situation with the picture and reason why you cannot proceed. Please contact tech support on the screen to resolve (they are very quick). I will c

Msds692

Install / Use

README

MSDS692 Data acquisition

Course details

Student evaluation

Honorlock