Yang Liu

Participation, section design, rating distributions, and standing patterns from the 2025 SuperNationals VIII chess tournament in Orlando.

May 15, 2025

2024 National K-12: Does a Higher Rating Lead to a Higher Standing?

A look at participation, rating distributions, and the relationship between rating and final standing at the 2024 National K-12 Grades Championship.

Dec 15, 2024

How many children under 5 worldwide?

A compact reference for world and Africa age-group population totals, with 2025 figures from the UN World Population Prospects 2024 revision.

Dec 13, 2024

Plot multiple countries on the world map

Spatial Data

How to plot administrative areas from several countries in R, and how to avoid stray connecting lines caused by non-unique polygon group IDs.

May 29, 2023

R Markdown to GitHub Pages

Reproducible Workflow

A concise legacy R Markdown workflow for publishing small GitHub Pages sites, now preserved with a Quarto-era maintenance note.

Jan 6, 2021

US and China Admin1 COVID-19 mortality and incidence rate

R examples for mapping COVID-19 mortality and incidence rates across US states and Chinese provinces, with a comparison to lung cancer maps.

Jun 14, 2020

ggplot US state and China province heatmap

R examples for drawing US state and China province heatmaps with ggplot2, usmap, shapefiles, labels, scale bars, and leaflet-based alternatives.

Jun 12, 2020

Working with 3D array as long-format data in R

Reproducible Workflow

A compact R example for melting a 3D array into long-format data, modifying it, and rebuilding the array in the correct dimension order.

Jan 11, 2020

Drake: powerful tool for automatic reproducible workflow

Reproducible Workflow

A legacy R workflow note showing how drake can cache calculations and speed up R Markdown report rendering, with a note on modern targets workflows.

Sep 15, 2019

Notes on writing an R package

R package

Practical notes from preparing the SHAPforxgboost R package for CRAN, including DESCRIPTION, NAMESPACE, documentation, checks, and reviewer feedback.

Jul 28, 2019

SHAP for XGBoost in R: SHAPforxgboost

R package

A vignette-style guide to the SHAPforxgboost R package, covering SHAP values, global importance, dependence plots, interaction effects, and force plots.

Jul 18, 2019

Shiny in Blogdown

A short R note on embedding a hosted Shiny app inside a static blog page using an iframe or knitr helper.

Feb 24, 2019

Study shrinkage and DART in xgboost modeling using a simple dataset

A small R experiment that illustrates how shrinkage and DART dropout change the behavior of XGBoost trees on a simple toy dataset.

Nov 15, 2018

SHAP Visualization in R (first post)

The original R post on SHAP visualizations for XGBoost, now linked to the later SHAPforxgboost package vignette.

Oct 14, 2018

Spatial data in R: Dividing raster layers into equal-area rings

Spatial Data

An R spatial workflow for turning raster layers into equal-area rings, calculating urban saturation, and plotting city comparisons on a shared scale.

Jul 20, 2018

How to Draw Heatmap with Colorful Dendrogram

An R visualization example that builds a clustered heatmap with colorful dendrogram branches and labels using gplots, dendextend, and colorspace.

Jul 16, 2018

eXtreme Gradient Boosting (XGBoost): Better than random forest or gradient boosting

A hands-on R comparison of XGBoost, gradient boosting, random forest, lasso, and best subset regression on a slum-settlement modeling example.

Jul 9, 2018

Catalog of my old blog

A historical catalog of posts from my earlier Blogger site, with links to older work on statistics, data visualization, R programming, and urban research.