Professor: Jeff Blanchard, Noyce 2516, 269-3304, blanchaj (at) math.grinnell.edu
Resources: There is no required textbook for this course.
Applied Data Science involves the skills and tools necessary to solve problems, make recommendations, deepen insights, or create knowledge using data. Typically, data science applications involve problems, recommendations, or insights required by a client who help pose questions. The breadth of problems makes it likely that new skills and techniques will be needed to complete a specific data science project. This course will help prepare students to navigate an applied data science project by serving as members of a team working on a data project for an on-campus client. The learning goals for this course are:
- develop the ability to craft and refine questions related to data;
- develop skills to identify, obtain, organize, clean, and wrangle data;
- develop or expand computing expertise related to all stages of a data science project;
- identify and acquire new data analysis modeling, and visualization techniques necessary to complete specific tasks in a data science project;
- effectively communicate technical processes and data-driven results through writing, oral presentation, and creation of data products;
- develop project management skills and systems;
- analyze and assess other data science projects and improve ability to provide constructive criticism and praise;
- improve ability to work with others of divers backgrounds and personalities, develop skills to constructively disagree yet move forward, and properly value the contributions of team members, advisors, and clients;
- understand, navigate, and foster the relationship and communication with a project client.
This class will meet approximately 2 hours 40 minutes per week. To accomplish the course learning goals and contribute to high quality projects, students should expect to spend at least an additional 9 hours 20 minutes per week of focused effort related to this course.
There are several items that will be assigned a grade during the course of the semester. These items comprise 55% of the final grade.
- Individual student development will be assessed throughout the semester.
- Progress Briefings: Each Thursday two teams will present the current state of progress on their project and discuss short and long term goals. The briefings will be followed by a feedback period from the other class members.
- Goal Assessments: Each Thursday class will end with a planning session where short and intermediate goals are defined and recorded. The following Thursday will begin with a quick assessment of progress toward the project goals.
- Advisor Team Assessment: On each Thursday students will form advisor teams to work with the two teams who did not complete a Progress Briefing. In week 8 and 9, the advisor teams will briefly take over a project for planning purposes. Each individual member of the advisor team will write a two page recommendation memorandum for completion of the project. The advisor teams will give a short presentations on Tuesday, April 3.
- Peer Reviews: Three times during the semester, students will complete an assessment of their team's members, including themselves. The quality of the student's submissions of peer reviews will be graded. The consensus of other students' peer assessment will also contribute to the peer review grade.
The final products make up 45% of the final grade. The final products consist of four items:
- Executive Summary: The executive summary is a two page paper written for a public audience that describes the problem/question, data, assumptions, recommendations/insights, and the final data product. Due April 26.
- Presentation: The final presentation will be a 20 minute oral presentation describing the complete project. Due May 3.
- Data Product: The data product is the tool or model developed for the client (including a user guide and source code) ultimately delivered to the client. Due May 10.
- Technical Report: The technical report is the full project report written for a technically literate audience akin to the readers of a subject specific journal. This has a maximum length of 15 pages. Due at noon on Wednesday, May 16.
All students must be aware of and comply with the Grinnell College Academic Honesty policy.
In this course students will work in teams to create data products for on-campus clients. It is a matter of academic honesty to maintain confidentiality with respect to off-campus communication of the clients' ideas, questions, data sources, etc. and any insights or tools you have generated using the intellectual property of the client. All public announcements related to the projects and any sharing of data provided by clients must be approved by Dr. Blanchard.
It is imperative that students properly cite sources used to obtain data, software, software packages, and analysis techniques in the course of the projects.
Absences permitted by the college (athletics, performance, religious observation, etc.) must be coordinated prior to the class period; this coordination must be done in person prior to the absence.
This course is collaborative by design and therefore requires attendance in class and at team meetings. While absences will impact the participation portion of a student's grade, excessive absences may result in reduced final letter grades:
- The fifth and subsequent absences will each reduce the student's final grade by a letter grade.
- Missing four consecutive classes will cap the final letter grade at C.
If you are in need of specific learning accommodations, please let me know early in the semester so that your learning needs may be appropriately met. If you have not already done so, you will need to provide documentation to and discuss your needs with the Coordinator for Student Disability Resources, John Hirschman (hirschma), located on the 3rd floor of the Rosenfield Center (x3089).
Go to my homepage.