Lecture time and location: Tu/Th 5:00-6:30pm, Social Sciences Building (SSB) 126

Lab time and location:

• Tu 3:00a-5:00p, Giannini 141

•  We 11:00a-1:00p, SSB 581

Office hours:

•  (Duncan) Thursday 4-5p, Giannini 337 (we’ll start walking over to class around 4:55p)

•  (Colette) Tuesday 2-3pand Wednesday 1-1:30p, 5 Giannini.

Please reach out to Duncan or Colette if these times don’t work; we’ll schedule another time.

Monthly coffee:

• Duncan will host coffee hour on the second Monday of each month, 10:30-11:30a at the Free Speech Movement Cafe. Sign up here. We’ll chat data, environment and society – but broader topics, not course nuts and bolts.

Course Description

This course will teach students to build, estimate and interpret models that describe phenomena in the broad area of energy and environmental decision-making.   The effort will be divided between (i) learning a suite of data-driven modeling approaches, (ii) building the programming and computing tools to use those models and (iii) developing the expertise to formulate questions that are appropriate for available data and models. Our goal is that students will leave the course as both critical consumers and responsible producers of data driven analysis.

We will work in Python in this course, and students must have taken Data 8 before enrolling. The course is designed to complement and reinforce Berkeley’s data science curriculum, in partic- ular Data 100 (though D100 is not a prerequisite). Whereas Data 100 focuses on a very broad set of data science tools including modeling, web technologies, working with text, databases and sta- tistical inference, this course focuses more on how to use prediction methods as decision-making tools in energy and environment contexts.

This is a four unit course, with three hours of lecture and two hours of lab section each week. Lectures will focus on theoretical and conceptual material but also introduce the programming structures required to use the material. Labs will be computer working sessions with a GSI and lab helpers available to work through weekly lab exercises.

Prerequisites

•  (required) Foundations of Data Science (CS/ INFO/ STAT C8)

•  (recommended) Computing: An introductory programming course (CS61A or CS88).

• Math:

–  (required) High school or college calculus.

–  (recommended) Linear Algebra (Math 54, EE 16a, or Stat89a).

COVID Safety Protocols

• Please remember that, for everyone’s safety, you are encouraged to wear a mask over your mouth and nose indoors.

• Consider wearing a KF94 or N95 mask.

• We don’t have indoor density or distancing requirements.  However, I ask that you sit in the same seat in the classroom every day. This limits our mixing.

• Stay home if you need to. We will course capture all lectures so you can watch later.

Satisfaction of degree requirements

This course can be used to satisfy the following requirements.

• Upper division domain emphasis for Data Science major

• Engineering Elective for Energy Engineering

• Upper division requirement for Energy and Resources Group minor

Resources

• You will need your own computer, but virtually any operating system will do (OSX, Win- dows, Linux, Chromebook). If you need hardware, consider the Student Technology Equity Program

• We will draw material from the excellent textbook, Introduction to Statistical Learning, avail- able in both print and pdf form.

• We will do a variety of readings from peer reviewed journals, popular press.  and other websites.

• Lectures and readings will be posted on bCourses

• You’ll complete all HW and lab assignments using Python, within Jupyter notebooks hosted on datahub.

• Links for assignments will be posted on bCourses. You’ll submit you work there, too.

• Homework and lab solutions will all be available on the course github site.

Assessment

The course will have weekly labs and homework assignments, lecture quizzes, a mid-term and a final project. Grading will be as follows:

• Homework: 30%

– There will be ten. We drop the two lowest grades.

– HW will be released on Thursdays and due the following Thursday.

• Lab assignments: 10%

– Released on Tuesdays and due the following Tuesday.

– Grading will focus on completeness rather than correctness.

– Attendance and participation are not required, but strongly encouraged.

– We drop the one lowest grade

• Low-stakes assessments:  10% (roughly 6, every two weeks, remote; we’ll drop the lowest grade).

• Mid-term: 15% (November 16, in class)

• Project: 35% total

– Preliminary presentation in Lab, 3% (Nov 7-8)

– Peer comment on preliminary presentatons, 2% (Nov 14)

– Final presenation, 5% (Dec 14 3-6p)

– Final notebook, 25% (Dec 15)

Late policy:

Homework:  You may request up  to two extensions of two days over the course of the semester. You must request an extension from the GSI before the homework is due. Other- wise, we will not accept late homeworks.

Late low stakes assessment submissions are not accepted. Remember, we drop the lowest grade.

Project: we take off 25% for each day the project is late.

Working with others and AI assistants

Homework and labs.

You are encouraged to learn from one another by brainstorming solution strategies. However the work you submit must clearly be your own. We will give zero credit for assignment submissions that are identical to one another. If you work with others, be sure to finish assignments on your own. Comments and markdown cells must clearly be your own.

Final project.

You must work in groups of 3-4 for the final project.  The final project writeup must include a statement describing each team member’s contributions and a statement that all team members agreed the division of labor was equitable.

AI assistants.

We adopt the following policy language, from David Joyner at Georgia Tech:

We treat AI-based assistance, such as ChatGPT and Copilot, the same way we treat collaboration with other people: you are welcome to talk about your ideas and work with other people, both inside and outside the class, as well as with AI-based assistants.

However, all work you submit must be your own.   You should  never include in your assignment anything that was not written directly by you without proper citation (including quotation marks and in-line citation for direct quotes).

Including anything you did not write in your assignment will be treated as an academic misconduct case. If we are sufficiently concerned that you have violated this policy and in our discussion with you, you refute that concern, then we will refer the case to the Berkeley Center for Student Conduct to proceed with the case. If you are unsure where the line is between collaborating with AI and copying AI, we recommend the following heuristics:

Heuristic 1:  Never hit “Copy” within your conversation with an AI assistant.  You can copy your own work into your own conversation, but do not copy anything from the conversation back into your assignment.

Instead, use your interaction with the AI assistant as a learning experience, then let your assignment reflect your improved understanding.

Heuristic 2:  Do not have your assignment and the AI agent open at the same time.  Similar to the above, use your conversation with the AI as a learning experience, then close the interaction down, open your assignment, and let your assignment reflect your revised knowledge.

This heuristic includes avoiding using AI directly integrated into your composition environment: just as you should not let a classmate write content or code directly into your submission, so also you should avoid using tools that directly add content to your submission.

Deviating from these heuristics does not automatically qualify as academic misconduct; however, fol- lowing these heuristics essentially guarantees your collaboration will not cross the line into misconduct.

Course Policies

Inclusion: We are committed to creating a learning environment welcoming of all students that supports a diversity of thoughts, perspectives and experiences, and respects your identities and backgrounds (including race/ethnicity, nationality, gender identity, socioeconomic class, sexual orientation, language, religion, ability, etc.) To help accomplish this:

• If you have a name and/or set of pronouns that differ from those that appear in your official records, please let us know.

• If you feel like your performance in the class is being impacted by your experiences outside of class (e.g., family matters, current events), please don’t hesitate to come and talk with us. We want to be resources for you.

• We (like many people) are still in the process of learning about diverse perspectives and identities.  If something was said in class (by anyone) that made you feel uncomfortable,

please talk to us about it.

• As a participant in this class, recognize that you can be proactive about making other students feel included and respected.

Berkeley honor code: Everyone in this class is expected to adhere to this code: “As a member of the UC Berkeley community, I act with honesty, integrity, and respect for others.”

Academic honesty: You are encouraged to form study groups and work together to understand course material, but all written work as well as responses to in-class questions should be your own.  You may not copy other students’ work.  Academic integrity and ethical conduct are of utmost importance in the College of Engineering and at U.C. Berkeley.

Accommodation policy:  We honor  and respect the different learning needs of our students, and are committed to ensuring you have the resources you need to succeed in our class.  If you need religious or disability-related accommodations, if you have emergency medical information you wish to share with us, please share this information with us as soon as possible.  You may speak with either instructor privately after class or during office hours.  Also see DSP under “Resources” .

Resources

Center for Access to Engineering Excellence (CAEE): The Center for Access to Engineering Excellence is an inclusive center that offers study spaces, nutritious snacks, and tutoring in >50 courses for

Berkeley engineers and other majors across campus.  The Center also offers a wide range of professional development, leadership, and wellness programs, and loans iclickers, laptops, and professional attire for interviews.

Disabled Students’ Program (DSP) The(Disabled Student’s Program) (260 CésarChávez Student Center #4250; 510-642-0518) serves students with disabilities of all kinds.  Services are individu- ally designed and based on the specific needs of each student as identified by DSP’s Specialists.

Counseling and Psychological Services The main University Health Services Counseling and Psychological Services staff is located at the Tang Center (http://uhs.berkeley.edu; 2222 Bancroft Way; 510-642-9494) and provides confidential assistance to students managing problems that can emerge from illness such as financial, academic, legal, family concerns, and more.

The Care Line (PATH to Care Center)

The Care Line (510-643-2005) is a 24/7, confidential, free, campus-based resource for urgent support around sexual assault, sexual harassment, interpersonal violence, stalking, and invasion of sexual privacy.   The Care Line will connect you with a confidential advocate for trauma- informed crisis support including time-sensitive information, securing urgent safety resources, and accompaniment to medical care or reporting.

Ombudsperson for Students

The Ombudsperson for Students (102 Sproul Hall; 510-642-5754) provides a confidential ser- vice for students involved in a University-related problem (academic or administrative),acting as a neutral complaint resolver and not as an advocate for any of the parties involved in a dispute. The Ombudsman can provide information on policies and procedures affecting students, facil- itate students’ contact with services able to assist in resolving the problem, and assist students in complaints concerning improper application of University policies or procedures. All matters referred to this office are held in strict confidence. The only exceptions, at the sole discretion of the Ombudsman, are cases where there appears to be imminent threat of serious harm.

UC Berkeley Food Pantry

The UC Berkeley Food Pantry (68 Martin Luther King Student Union; ) aims to reduce food insecurity among students and staff at UC Berkeley, especially the lack of nutritious food.  Stu- dents and staff can visit the pantry as many times as they need and take as much as they need while being mindful that it is a shared resource.  The pantry operates on a self-assessed need basis; there are no eligibility requirements.  The pantry is not for students and staff who need supplemental snacking food, but rather, core food support.