M3239.003100

Data Analytics and Visualization
(데이터 분석과 시각화)

Fall 2021

Tue/Thu, 12:30 - 13:45

Instructor: Hyunwoo Park (oksure@gmail.com, Office: 942-417)
Office hours: By appointment

Overview

Businesses and organizations today collect and store unprecedented quantities of data. In order to make informed decisions with such a massive amount of the accumulated data, organizations seek to adopt and utilize data mining and machine learning techniques. Applying advanced techniques must be preceded by a careful examination of the raw data. This step becomes increasingly important and also easily overlooked as the amount of data increases because human examination is prone to fail without adequate tools to describe a large dataset. Another growing challenge is to communicate a large dataset and complicated models with human decision makers. Exploratory data analysis, and visualizations in particular, helps find patterns in the data and communicate the insights in an effective manner. This course aims to equip students with methods and techniques to summarize and communicate the underlying patterns of different types of data. In addition to creating high-quality static visualizations, this course teaches students how to build an interactive visual analysis system.

Objectives

By the end of this course, students should successfully be able to:
  • · Explain pros and cons of various visual representations depending on the context and form of data.

  • · Choose appropriate visual representations for special forms of data such as geospatial and network data.

  • · Compose a visual dashboard composed of interactive visual artifacts.

  • · Create high-quality static visualizations.

  • · Plan and implement a customized interactive visual analysis system.

Prerequisite

  • · Prior experience with Python

  • · While no experience in web programming (HTML, JavaScript, CSS) is assumed, students should be a self-learner to pick up the pace unless they have experience in web programming.

  • · Or, permission of the instructor

Weekly Schedule

  • Week 1 (9/2): Course Overview
  • Week 2 (9/7, 9/9): Data Wrangling / Python and Jupyter Setup
  • Week 3 (9/14, 9/16): Data Collection and Cleaning
  • Week 4 (9/21, 9/23): Univariate and Bivariate Visualization
  • Week 5 (9/28, 9/30): Geospatial Visualization
  • Week 6 (10/5, 10/7): Graph Analytics and Network Visualization
  • Week 7 (10/12, 10/14): Interactivity / d3 Setup
  • Week 8 (10/19, 10/21): Visual Analysis System Planning
  • Week 9 (10/26, 10/28): Aesthetics (Color, Font, Layout)
  • Week 10 (11/2, 11/4): Dashboard Design
  • Week 11 (11/9, 11/11): Describing Textual Data
  • Week 12 (11/16, 11/18): Time-series Visualization
  • Week 13 (11/23, 11/25): Visualization Tools and Frameworks
  • Week 14 (11/30, 12/2): Project Discussion
  • Week 15 (12/7, 12/9): Final Project Demo

  • Please note this schedule is subject to change.

Course Components and Grading Breakdown

Category
Points
Assignments
40
Group Project
50
Participation
10
Total
100
Late submissions will not be accepted.