Professional Documents
Culture Documents
Week 8, Thursday
Agenda
• Homework 8 Solution Review
• Up Next
HW8 Solution Review – Advanced Regression
Q11.1 Using the crime data set uscrime.txt from Questions 8.2, 9.1,
and 10.1, build a regression model using:
1. Stepwise regression
• step()
2. LASSO
• cv.glmnet() function in R; alpha = 1 (𝜆 analogous to 𝜏 from the lectures)
𝑗
• σ𝑖=1 𝑎𝑖 ≤ 𝜏
3. ElasticNet
• cv.glmnet() function in R; vary alpha (𝜆 analogous to 𝜏 from the lectures)
𝑗 𝑗
• 𝜆 σ𝑖=1 𝑎𝑖 + 1 − 𝜆 σ𝑖=1 𝑎𝑖2 ≤ 𝜏
• Takeaways
• Variable selection ultimately made a big difference (less overfit models
compared to other HWs)
• PCA didn’t help in this case, but it’s a tool at your disposal (can
be combined with others)
HW9 Preview – Design of Experiments
Q12.1 – describe a situation or problem from your job, everyday life, current
events, etc., for which a design of experiments approach would be
appropriate
a. Binomial
b. Geometric
c. Poisson
d. Exponential
e. Weibull
HW9 Preview – Simulation
• Q13.2 – Airport simulation
• Passengers arrive at an airport with given distributions for arrival rate and
inter-arrival time
• They need their IDs checked and baggage scanned; each has a service
capacity
• How many ID checkers / baggage scanners do you need to keep the
average max wait time below 15 minutes?
HW9 Preview – Simulation
• Option 1 – Arena
• PC only (I’ve heard it runs via emulation on Mac and Linux)
• https://www.rockwellautomation.com/en-us/products/software/arena-
simulation/academic.html
• Click Download Free Trial; enter deets
• Will be sent download link via email
• License key = STUDENT
• SMARTS/Examples
• GT ONLY: https://mycloud.gatech.edu
• ISYE-2021 or ISYE-SIMIO desktop (don’t use the Apps feature; there’s issues with multi-
window stuff)
• DO NOT save to your desktop (remember it’s a VM); only use your Prism drive (P)
HW9 Preview – Simulation
• Option 2 – SimPy
• All platforms
• Python-based simulation language
• Yup, week 6 and another new language (hint: it’s going to come up again… and again… and
again)
• Python.org
• Anaconda Navigator (lots of excellent tutorials) (anaconda.org)
• No GUI like Arena, you’ve got to code everything yourself
• https://simpy.readthedocs.io/en/latest/
• Installing – easiest is to use pip: pip install simpy
• Crash course: https://simpy.readthedocs.io/en/latest/simpy_intro/index.html
• Carwash example: https://simpy.readthedocs.io/en/latest/examples/carwash.html
Not supported (i.e., we can't offer tech support), but Google Colab has been
successfully used by students in the past
• Install SimPy with shell command in your notebook: !pip install simpy
Up Next…
• HW8 peer reviews due Sunday/Monday, HW9 due
Wednesday/Thursday