Introduction to Data Science
Computer Science Department, Rutgers University

CS 439, and Section(s) 1, 2
Class Meeting Time : 1:40-3:00 PM  M, W (On Zoom)

Fall 2020

About this course. This course covers topics needed to solve problems involving data, which includes preparation (collection and integration), characterization and presentation (information visualization), analysis (machine learning and data mining), and products (applications).

Prerequisites. CS 205 – Discrete Structures

The topics covered include (but not limited to):

Python for Data Science

Data Munging and Cleaning

Data Modeling and Visualization

Statistical Analysis, Linear Algebra

Linear and Logistic Regression

Bayesian Classification

Deep Learning

Big data platforms and technology

Map Reduce, Tensor Flow

Human Factors in Data Science

Contact Information

Instructor. Prof. A.D. Gunawardena

Email. andy.guna@rutgers.edu                        

Office. Hill 259 (Busch Campus) – Not Available in F20

Office hours. TH 2-3 PM on Zoom

Contact information for TAs or other course support staff. Please see canvas page.( https://rutgers.instructure.com/courses/65616

Learning Goals

• Prepare students to contribute to a rapidly expanding field of data science by acquiring a thorough grounding in the core principles and foundations of big data.
• Prepare students to understand the foundational machine learning methods that are used in interpreting data. 
• Emphasize the mathematical and statistical foundations necessary to understand data science
• Expose students to real world data sets and their applications by completing practical assignments and projects.  

Textbook, Discussions and Supplemental Videos

Recommended (not required) Text: Steven Skiena, Data Science Design Manual (DSM), Springer 2017 (Links to an external site.). (ISBN: 978-3-319-55443-3) . This book is not required. If you would like to buy it online you can do so at any site. Here is the amazon link.  (Links to an external site.)

Free online textbooks

• Berkeley Online textbook - http://www.textbook.ds100.org/ (Links to an external site.)
• Data Mining - https://www.saedsayad.com/data_mining.htm (Links to an external site.)

Technology Platforms

• Canvas course management system
• CUvids (https://cuvids.io/app), A curated video platform for videos in Computer Science.

Grading

• Students are assigned a data science lab assignment almost every week. The projects are completed on jupyter notebooks and are submitted to canvas and will be graded on a common rubric provided to all graders. Graders will provide sufficient feedback on your work.
• There will be a weekly quiz (almost every week) that covers the key ideas discussed in the lectures. Quizzes are administered on Canvas with a Friday midnight completion deadline. Quizzes cannot be retaken.
• Mid-semester project will be given (to be completed in 2 weeks)
• Final Exam will cover all material of the course. The final exam duration is 2-3 hours and date and time will be announced later. The final exam will be given online (details to follow)
• Lecture Attendance (zoom) and participation (through https://cuvids.io) is 10% of the grade.
• A grading scale is as given below

Grades for this course will be determined through a number of assignments. We recognize that different kinds of assignments feed into the strengths of different students, and we work to provide a range of opportunities for you to show what you’ve learned.

Final Grade Breakdown:

6-7 Jupyter labs                        40% of final grade

weekly quizzes                        30% of final grade

Mid-semester project                 10% of final grade

Attendance/Participation         10% of final grade

Final Exam                        10% of final grade

• Late work will not be accepted unless there is a valid excuse. Valid excuses are mostly related to medical and must be supported by an official document signed by a medical provider. If the student miss lectures for too long for some valid excuse, instructor will present a range of options, including dropping the class, replacing some assignments with others etc.
• Academic integrity is very important to us. You are expected to sign a statement with each assignment to indicate that the submitted work is yours. No assignment will be graded without this statement.

Assignments & Homework

• Labs. The lab assignments are challenging assignments that are completed as jupyter notebooks and submitted. The labs are completed using Python code. If you use any publicly available python library you need to include the reference to the source. (searching web for solutions or accessing any non-listed class material is prohibited). Completed labs are submitted to canvas.
• Weekly Quizzes. The quizzes are designed to check your understanding of the most recent material covered. Quizzes are given each week on canvas and to be completed by 7AM Saturday.
• Attendance and participation. We will track your attendance, effort and participation
• Mid-Semester Project. Mid-semester project is a 2-week project that provides the opportunity to work with a real data set and discover hidden patterns of data.
• Final Exam. Will be comprehensive and details will be announced later.

Attendance, Participation, and Classroom Climate

• Attendance. Your attendance is not mandatory. However, attendance and participation points (10%) will only be available to those who attend lectures, recitations and show effort.
• Participation. You will be given many opportunities to participate in class and out of class. We employ on-line tools such as CUvids (https://cuvids.io/app), and quick zoom polling software to give you an opportunity to participate. Here is our statement regarding participation.

Discussion and participation are a major emphasis in this course. This means that it is your responsibility to come to lecture ready and willing to take part in discussions. You will be given the opportunity to participate in “workshops”, a short breaks between concepts to build understanding.

• Technology. You are allowed to use technology in the course that are related to lecture participation. You are asked not to use any technology unrelated to course such as social media during lecture.
• Behavior. We expect that classroom interactions will remain civil, respectful, and supportive. You are not expected to talk loud in class or interrupt other students. You may be asked to leave the class, if your behavior is considered disrupting to the professor and other students.  For online courses, similar rules apply.
• Help. You are encouraged to speak with instructor and TA’s regarding your concerns. Please bring your concerns to course staff before reaching out to the department chair, or other advisors about any concerns you have about classroom dynamics and/or classroom climate.