Brian Patrick Kent

A Claude Sonnet 4 regression

AI Engineering

Claude Sonnet 4 seems to be a clear step backward in its ability to follow instructions regarding the format of code output.

A DSPy footgun

AI Engineering

Python

Variable names in DSPy signatures must have semantic meaning for your LLM.

How to use an LLM to generate SQL queries

AI Engineering

SQL

Python

Replicating and extending Rami Krispin’s excellent ODSC East talk.

Things I read in April

reading

Interesting things I’ve read over the past month. Ramping up on LLM evals.

Things I read while the algae grew in my fur - April 2025

reading

Interesting things I’ve read over the past month.

LLM as piano teacher

AI Engineering

Here’s an AI use case I haven’t seen come up elsewhere: LLM as (beginner) piano teacher.

Announcing Apricot, a better way to subscribe to content

meta

recsys

Social media has become the way to stay in the loop. News and long-form commentary, official government and corporate communications, educational content, professional development—it’s all on social media. Thing is, social media is also destroying lives and tearing society apart. Enter Apricot.

Six keys to successful data science management

management

Data science management is a hard job. Here’s what I’ve learned from my years on both sides of the table—manager and individual contributor.

My conversation with Manuel Bruscas, VP of Data Analytics

RL

MLOps

management

I chatted last week with Manuel Bruscas, VP of Data Analytics at Holaluz, about MLOps, reinforcement learning, and data science management.

Making the leap: porting our Python data science blog to Quarto

meta

Quarto is the hot new technical publishing system. Built by the company formerly known as RStudio, I decided to see how it would work for this Python-oriented blog.

How to use PyTorch LSTMs for time series regression

Python

IOT

time series

Most intros to LSTM models use natural language processing as the motivating application, but LSTMs can be a good option for multivariable time series regression and classification as well. Here’s how to structure the data and model to make it work.

Applications of survival analysis (that aren’t clinical research)

survival analysis

Survival analysis has been a standard tool for decades in clinical research, but data scientists in other domains have mostly ignored it. Here are some applications for which you might use survival analysis, to jump-start your creative data science engine.

How to compute Kaplan-Meier survival curves in SQL

SQL

survival analysis

Decision-makers often care how long it takes for important events to happen. In this article, I show how to compute Kaplan-Meier survival curves and Nelson-Aalen cumulative hazard curves directly in SQL, so you can answer time-to-event questions directly in your SQL-based analytics tables and dashboards.

How to construct survival tables from duration tables

Python

survival analysis

The survival table is the workhorse of univariate survival analysis. Previously, I showed to build a duration table from an event log; now I show how to take the next steps, from duration table to survival table and estimates of survival and hazard curves.

A review and how-to guide for Microsoft Form Recognizer

reviews

information extraction

Form Recognizer is Microsoft Azure’s answer to Amazon Textract and Google Form Parser for information extraction from form documents. I put all three to the test on a challenging set of invoice documents and was surprised to see Microsoft’s service come up short.

A review and how-to guide for Amazon Textract

reviews

information extraction

At just two years old, Amazon Textract is already the grizzled veteran of the fast-moving information extraction-as-a-service market. I put it to the test against Google Form Parser and Microsoft Form Recognizer to see which service has the best speed, accuracy, and developer experience.

How to plot survival curves with Plotly and Altair

Python

survival analysis

Survival curve plots are an essential output of survival analysis. The main Python survival analysis packages show only how to work with Matplotlib and hide plot details inside convenience functions. This article shows how to draw survival curves with two other Python plot libraries, Altair and Plotly.

Google Form Parser, a review and how-to

reviews

information extraction

Google Form Parser is a new challenger in the information extraction arena, offering general-purpose off-the-shelf form extraction. We compared Form Parser to Amazon Textract and Microsoft Form Recognizer in terms of accuracy, speed, and ease of use. Take our code snippets and try it yourself!

How to build duration tables from event logs with SQL

SQL

survival analysis

Duration tables are a common input format for survival analysis but they are not trivial to construct. In our last article, we used Python to convert a web browser activity log into a duration table. Event logs are usually stored in databases, however, so in this article we do the same conversion with SQL.

How to convert event logs to duration tables for survival analysis

Python

survival analysis

Survival models describe how much time it takes for some event to occur. This is a natural way to think about many applications but setting up the data can be tricky. In this article, we use Python to turn an event log into a duration table, which is the input format for many survival analysis tools.

A checklist for professionalizing machine learning models

MLOps

Data scientists are drawn to the latest and greatest machine learning tasks and models, even though tabular binary classification remains the industry workhorse. We should take more pride in professionalizing the models that we know to work, rather than reflexively chasing every new thing.

Review: Statistical Rethinking, by Richard McElreath

reviews

This is an absolute gem of a book. McElreath has found an elusive combination: Statistical Rethinking is not only one of the best intro textbooks for both causal and Bayesian modeling, it’s also highly readable, even entertaining.

Streamlit review and demo: best of the Python data app tools

Python

data apps

reviews

Streamlit has quickly become the hot thing in data app frameworks. We put it to the test to see how well it stands up to the hype. Come for the review, stay for the code demo, including detailed examples of Altair plots.

How to analyze a staged rollout experiment

experimentation

Python

data apps

Recently we argued that confidence intervals are a poor choice for analyzing staged rollout experiments. In this article, we show a better way: a Bayesian approach that gives decision-makers the answers they really need. Check out our interactive Streamlit app first, then the article for the details.

Research digest: what does cross-validation really estimate?

model evaluation

A new paper by Bates, Hastie, and Tibshirani reminds us that estimating a model’s predictive performance is tricky. For linear models at least, cross-validation does not estimate the generalization error of a specific model, as you would assume. How much does this matter for data science in practice?