DATA 419

Data Mining (Machine Learning)

Quiz #6 (and last) finally posted!

no comment

Sorry so long to get this to you! The final quiz has been posted. It is open-book, open-notes, timed at 30 minutes, and is due by midnight December 10th. Good luck!


no comment

You guys’ responsive reading #2’s were orders of magnitude better than your previous ones. Wow — great job! Every single person but one got at least a +40XP! :-O

I didn’t write much formative feedback on these, since there was no rewrite opportunity and I can’t even physically return it to those who skip the final. You can, however, see your score on this assignment (and on all others) but clicking on the “My XP” tab (the third tab) of the scoreboard and entering your real name and screen name.

Join us for Advent of Code 2022! 🎄

no comment

Looking to keep your programming skills sharp over winter break?

🎁 Join us for 25 days of fun programming challenges during 2022’s Advent of Code! 

  • Keep in touch with your peers!
  • Make new friends within the department!
  • Solve daily programming challenges with a cute holiday theme!
  • Compete against other UMW students for bragging rights!
  • Help others!

Starting 12:00am December 1st through Christmas day, a two part programming challenge will drop each day. Solve the day’s easy challenge to earn a silver star. Once you’ve earned your silver star, earn a gold star for that day by solving a harder challenge.

The student who earns the first silver or gold star on a given day will earn the most points, followed by the second student, then third, and so on. If you want to place highest on the scoreboard, you’ll have to solve both parts of each problem before others do!

Students are encouraged to try to solve each problem on their own first. If you get stuck or just want to talk to others about the problem each day, join our Discord server (link below) where you can talk to fellow students who are also taking part in the competition. If you think your solution is really cool and want to share it with others, feel free to!

Interested in participating? Sign up for an Advent of Code account, then join the UMW leaderboard by entering our leaderboard code (1652544-28d712c7) on the leaderboard page. Once you’ve joined the private leaderboard, you’ll be able to see how many stars you’ve earned and compare yourself to your peers!

Please also join our Discord server where we will be talking about the problems, sharing tips, and posting our solutions each day!

If you have any questions, please reach out to Lauren Knight on Discord.

GraphViz woes and solutions

no comment

Some people have reported troubles with getting GraphViz to be found and to successfully plot. Here is Ryan’s adventure with this problem, whose solution may be useful to others:

While trying to create my decision tree image, I encountered an error with graphviz. This error occurred on Windows. The error is “pydot.InvocationException: GraphViz's executables not found.” This can be solved by following these steps:

  1. go to this website
  2. download the 64-bit version (the third option).
  3. When the installer runs, click agree for all the ToS and such, but when it asks if you would like to install it on your PATH say yes! There will be two options: install it on the PATH for the current user or all users. This is up to you and depends on how many people are using your computer.
  4. Restart your Terminal and re-run your code.

I have not verified this solution myself, but it gave Ryan great joy and I encourage you to consider it.

Quiz #5 graded

no comment

Sorry for the delay! I was just now reminded that I never put this on the scoreboard.

We really have no class

no comment

By popular demand and democratic resolution, we will not have class tomorrow (Tue Nov 22)!

Programming contest XP

no comment

Great turnout at the programming contest last night — congratulations to all who participated!

To claim your XP for this event, just send me an email with subject line “DATA 419 programming contest XP” and in the body of the email state your team name and team members and how many problems you got right. (Reminder: if you’re also in my CPSC 350 class, you have to choose which class to apply your XP to. I will go by what’s in the subject line of the email.)

Homework #6 posted!

no comment

Homework #6, worth up to +60XP, is your final assignment of the year. It calls you to work with the most recent techniques from class (trees, forests, and ensembles) and also to step back and summarize your overall findings from one of your two data sets. It’s due on the last day of classes.

Good luck!

Code posted

no comment

The code for our decision tree regressor has been posted to github.

Quiz #5 posted!

no comment

Quiz #5 has been posted to Canvas, and is due Saturday at midnight. It is open-book, open-notes, closed-calculator, closed-Python, and closed-other humans. It is also timed at 50 minutes.

Good luck!