Home on Peter Baumgartner

tl;dr: Evaluate agentic tooling in realistic end-to-end agentic tasks, not in isolation.

Recently I’ve been using Quarto to generate HTML reports to share with stakeholders and I’d like to share a workflow and configuration that has worked for me.

In this blog post I’ll walk through step-by-step how I wrapped the voronoice Rust crate and created a Python package with it.

This year I decided to participate in Advent of Code (AoC) and use it as an opportunity to learn Rust.

Note: If you haven’t read my prior post on the bootstrap and inter-rater reliability, this post probably won’t make sense.

One of the most frequent questions that arises when doing applied ML projects is “How much data to I need to label?”

“Writing has so much to give, so much to teach, so many surprises.

This week my pal Vicki tweeted this, which I disagreed with: The funny part is that every single response to this is correct.

Since starting work at Explosion, I’ve been trying to learn more about Cython.

In this blog post I’ll walk you through the workflow I use for managing virtual environments and creating python packages.

I’m joining Explosion AI as a Machine Learning Engineer.

This is a short blog post on two things I’ve found helpful when I’m not using notebooks and running python code that I want to log things in.

In my work, writing tests serves three purposes: making sure things work, documenting my understanding, preventing future errors.

I’ve worked on several projects where we’re applying some natural language processing techniques on responses to open-ended survey items.

Context: I’ve recently been experimenting with porting portions of a simulation codebase from python to Julia.

tl;dr: Load data up to 77x faster with django-postgres-copy and an in-memory csv.

We work on a lot of projects where we need to iterate quickly on visualizations generated from a flat file of data.

TL;DR The Rule-Based Matcher in spaCy is awesome when you have small datasets, need to explain your algorithm, locate specific language patterns within a document, favor performance and speed, and you’re comfortable with the token attributes needed to wri…

Link to Notebook What’s in this notebook?

These are the main points and resources for my talk, Applied NLP: Lessons from the Field, delivered at spaCy IRL 2019.

Why did the chicken cross the road?

Summary: I wrote this document based on my experience validating a risk assessment instrument.

Summary: These are some notes, combined with my own experience and commentary, derived from Matthew Honnibal’s PyData Berlin 2018 talk: Building new NLP solutions with spaCy and Prodigy.

Links Link to Notebook What’s in this notebook?

Introduction When we think of data science, we often think of statistical analysis of numbers.

What are word embeddings?

TL;DR If you want to test ipython magics you can do the following: Import the global ipython app with from IPython.testing.globalipapp import get_ipython Crete an object with the global ipython app with ip = get_ipython() Load your magic with ip.magic('lo…

Links Link to Notebook What’s in this notebook?

This post will be an exploration into Earth Mover’s Distance as well as its application to NLP problems through Word Movers Distance.

Links Link to Notebook What’s in this notebook?

Risk Assessment tools are currently used to assist in decision-making at several points in the criminal justice system.

Links Link to Notebook What’s in this notebook?

Links Link to Notebook What’s in this notebook?

Links Link to Notebook What’s in this notebook?

Link to Notebook What’s in this notebook?

Note (2018-04-09): I no longer use Pelican as the engine to build my blog, so you want be able to see parts of this workflow in this blog's repository.

PyData Carolinas Recap & Presentation Reflection I was fortunate enough this year to attend the first PyData Carolinas conference, though my attendance was only made possible with the development and delivery of a tutorial talk.

Note (2018-04-09): Slack's API has changed since I wrote this article.