Incidental Findings

Deterministically anonymize identifiers and dates

Code snippets to deterministically anonymize identifiers and dates, while maintaining intra-individual time series relationships, to facilitate sharing examples of clinical dashboards.

Unexpected Pandoc failure after RStudio upgrade

I have a fragile pipeline to generate monthly clinical dashboards that fails regularly in fairly typical ways. However, this month it failed in a completely new and unexpected way, resulting in a period of mild panic. TL;DR – add folder to Windows Path environment variable.

Data science goals, shorter TLDR version

The last post was way too long. Here’s the short version.

Clinician data scientists – musings in response to an email

I received an email from a PediTools user that led me to think about what it means to be a clinician who also codes and enjoys data science. I really think that more clinician data scientists are needed to translate the hugely increasing amount of clinical data available into better clinical care.

Disable Citrix Workspace automatic startup

In a recent update, Citrix decided it would be a good idea to force automatic startup of the Citrix Workspace with every reboot, with no way of disabling it.

PediTools: improving ease of use of the AAP 2022 bilirubin guidelines

PediTools clinical decision support tool for managing neonatal hyperbilirubinemia, including newly developed treatment threshold plots to facilitate clinical care.

Bilirubin treatment thresholds

Data visualization

Comparing bilirubin phototherapy and exchange transfusion thresholds between the AAP 2004 and 2022 guidelines

From Blogdown to Quarto

When this blog was created in 2018, it used the paradigm of R with blogdown to GitHub through Netlify with Hugo to continuous deployment. I set up a custom domain, found a Hugo theme I really liked. And then, very quickly, everything went wrong.

Learning Julia with Advent of Code

Advent of Code is a great way to learn a new programming language.

R for Animal Crossing flower genetics

Animal Crossing New Horizons uses Mendelian inheritance of bi-allelic polygenic traits to determine flower colors. I wrote some tools in R to help plan flower crosses.

Finding Minecraft Strongholds with Math

Find a Minecraft stronghold in just three Eye of Ender throws

Using the medianeffect package for dose-effect analysis

Vignette for the medianeffect R package for dose-effect analysis and quantifying synergism and antagonism via the Median Effect Principle.

Cheating at anagrams with Python

How to cheat at anagram word puzzles (or Scrabble) with Python.

RISK battles: Simulating the distribution of outcomes

Playing RISK recently, I was annoyed when I lost a battle despite overwhelming numbers. ‘What are the odds of that?!?’ Which led me to write this simulation.

Tidy Tuesday – NLP on Wine Ratings Dataset

Machine learning

Natural language processing of wine descriptions to predict wine review scores.

Analysis of Pokemon Go Spawn Frequencies to Identify Possible Biomes

Data visualization

Using Pokemon spawns and geocoding to identify biomes.

Generating a union of overlapping intervals

This function takes a set of overlapping intervals and returns the union of the intervals.

Using R in an exploratory data visualization for predicting tree cover

Data visualization

I share here the full code and output for an exploratory data visualization in R Markdown submitted for a contest in January 2017.

Up and running with blogdown, GitHub, Netlify, and tranquilpeak

I am primarily a MacOS user who does most of my analytics and presentation work in R / RStudio / RMarkdown, so it was natural to take advantage of using the R blogdown package.

Hello world!

This blog will serve as a place to share data science analyses, professional and personal projects, snippets of useful code, and other various geekery.