Data Analytics and Visualization
RE 519, Runstad Department of Real Estate, University of Washington, Autumn 2025
Monday & Wednesday, 2:30 - 3:50pm, Mechanical Engineering Building 245
Haoyu Yue (Pre-doctoral Instructor), [email protected], Schedule Office Hours
Lab Sessions
Lab 1 - Basic of R and RStudio
Covers setup of R, RStudio, and GitHub, basic R and Markdown skills, and accessing Census data for simple data exploration and reproducible analysis.
Lab 2 - Data Wrangling for Dataframes
Focuses on data wrangling with tidyverse—modifying, summarizing, and joining dataframes, sampling for the Central Limit Theorem, and using GitHub for version control.
Lab 3 - Preparing Data for Visualization
Introduces tidy data and exploratory data analysis (EDA) with ggplot2, including data cleaning, handling missing values, and basic visualizations using the Zillow Home Value Index.
LAB 4 – Visualization Using R and ggplot2
Focuses on data visualization design principles and implementation using ggplot2, exploring aesthetic mappings, scales, and themes for expressive, effective, and ethical graphics.
LAB 5 – Tableau and Spatial Data in R
Combines Tableau and R for spatial data visualization. Introduces interactive dashboard design in Tableau and geospatial analysis in R using
sf, focusing on coordinate systems, spatial joins, and map-based analytics.
LAB 6 – Dashboard using Tableau and Miscellaneous
This lab serves as the starting point for the final project’s exploratory analysis and introduces interactive dashboard design with Tableau. The optional Section B provides a brief introduction to command line tools, virtual environments, and SQL, highlighting how they support data processing, reproducibility, and database querying in real-world analytics workflows.
LAB 7 – Linear Regression
Covers linear regression in both statistical and machine learning frameworks. Part A introduces classical regression using King County sales data, focusing on model specification, assumptions, diagnostics, interactions, nonlinear terms, model comparison, and prediction. Part B introduces regression in machine learning using
tidymodels, including data preprocessing, penalized regression (Ridge/Lasso), cross-validation, tuning, and test-set evaluation.
LAB 8 – Machine Learning
Introduces two classical machine learning methods: decision trees (supervised) and k-means clustering (unsupervised). Also, introduces neural-network intuition through 3Blue1Brown video.
Back to Top
Built on Just the Class developed by Kevin Lin at Allen School