Todd Warczak PhD

Todd Warczak PhD

Molecular & Cellular Biologist /
Data Scientist

My name is Todd Warczak, pronounced WAR-ZAK. I’m a mid-level Data Scientist and experienced R developer. If you need help with data analysis, engaging clients with dashboards or interactive apps, building predictive models, automating data driven reports, or just creating impressive data visualizations - I’m your guy!

I completed my PhD in 2020 from Dartmouth College, genetically engineering safer-to-eat crops that accumulate less arsenic from the soil. The most fulfilling part of my thesis work was building custom analysis tools and visualizations for my plant genomics data.

I moved to California in 2022 to work for Bio-Rad Laboratories as a Data Scientist II, building Shiny apps for a team of scientists to interact with their data in the cloud, developing ddPCR and NGS analysis pipelines in R, overseeing Bio-Rad software development for a Non-Invasive Prenatal Test (NIPT) kit our QX600 machine.

Sadly, In January 2023 our NIPT project did not pass feasibility stage. In March 2023 Bio-Rad performed a large round of layoffs and my position, along with others on the NIPT team, were terminated. But I’m excited to start new projects with a new team!

I currently live in Pleasanton, CA. Looking for opportunities in the Bay Area or Seattle.

Download my resumé.

Interests

  • Machine Learning
  • Deep Learning
  • Data Analysis
  • Data Visualization
  • Time-Series Forecasting
  • Regression/Classification
  • R for Data Science
  • AWS Cloud Tools

Education

  • PhD in Molecular & Cellular Biology, 2020

    Dartmouth College

  • BSc in Biology, 2012

    University of Utah

Recent Posts

SageMaker + RStudio to Predict Home Prices w/ Multi-class XGBoost; Explaining Model Behavior with Geospacial Plots and SHAP
In this post I explore an Austin Housing dataset and predict binned housing price. EDA includes static and interactive geospacial feature maps and feature engineering using natural language processing (NLP). After training/tuning multi-class XGBoost models , I run batch inference to predict the price of Austin, TX houses. I then submit predictions to the Kaggle competition which scrored 0.8876 (mlogloss), which would have placed 6th in the live competition. After submission, I generate SHapley Additive exPlanations (SHAP) plots to understand how XGBoost made predictions.
Last updated on 2021-10-14 rstats, AWS, SageMaker, XGBoost, NLP, R, SHAP, Geospacial
SageMaker + RStudio to Predict Home Prices w/ Multi-class XGBoost; Explaining Model Behavior with Geospacial Plots and SHAP
Predicting Bank Customer Churn using AWS SageMaker and XGBoost in Local RStudio
For this post, I experimented using AWS SageMaker with the AWS built-in XGBoost algorithm from within my local RStudio to predict whether a bank customer has churned. The data comes from the SLICED season 1 episode 7 Kaggle competition. SLICED is a data science competition where contestants are given a never-before-seen dataset and two-hours to code a solution to a prection challenge.
Last updated on 2021-10-14 rstats, AWS, SageMaker, XGBoost, R
Predicting Bank Customer Churn using AWS SageMaker and XGBoost in Local RStudio
Forecasting Daily Sales w/ {modeltime}
In my first blog post, I use the time-series modeling package {modeltime} and a Kaggle sales dataset to forecast 3 months of daily sales. This is a {tidymodels} approach with with a {modeltime} twist.
Last updated on 2021-10-14 rstats, tidymodels, modeltime, R
Forecasting Daily Sales w/ {modeltime}

Certifications

High-Performance Time Series Forecasting
Business Science Apr 2021 – May 2021
See certificate
DataCamp
Time Series with R Track
DataCamp Apr 2021 – Apr 2021
Time-series data analysis and core techniques.
See certificate
DataCamp
Data Scientist with R
DataCamp Feb 2021 – Apr 2021
See certificate

Popular Topics

AWS Deep Learning Geospacial ggmaps R reticulate rstats XGBoost