Gio Circo, Ph.D.

Executing Python Scripts from the Command Line

Or: how to pass a job interview
Python
Data Science Applications
Here’s a short one for a Friday afternoon.
Sep 20, 2024
Gio Circo, Ph.D.

Going Back to (Bayesian) School

Self-study with Regression and Other Stories
R
Bayesian Statistics
This is just a bit of fun, mostly for myself. In my day-to-day as a data scientist, I don’t get to use Bayesian statistics as much as I would like. In my role, a lot of the…
Aug 24, 2024
Gio Circo, Ph.D.

Dear Crime Analysts: Why You Should Use SQL Inside of R

Using duckDB in R to speed up analysis
R
SQL
When I was in grad school working on my Ph.D. I learned a lot about math, statistics, research methods, and experimental design (among a LOT of other things). For a good…
Jul 23, 2024
Gio Circo, Ph.D.

Creating Synthetic Spatial Data

Simulating Gas Stations and Robberies
R
Spatial Statistics
In my work as a data scientist I have been working increasingly more with synthetic data generation. Synthetic data can be very useful when you are working on products that…
Jun 15, 2024
Gio Circo, Ph.D.

If You Order Chipotle Online, You Are Probably Getting Less Food

Comparing weights of orders
R
Miscellaneous
Here’s a quick one. The question posed here is “do you get less food if you order your Chipotle order online versus in person?” There are plenty of posts going back years…
Apr 3, 2024
Gio Circo, Ph.D.

Don’t Evaluate Your Model On a SMOTE Dataset

or: try this one weird trick to increase your AUC
R
Machine Learning & Prediction
I recently found a paper published called “Advancing Recidivism Prediction for Male Juvenile Offenders: A Machine Learning Approach Applied to Prisoners in Hunan Province”.…
Mar 26, 2024
Gio Circo, Ph.D.

An Outsider’s Perspective On Media Mix Modelling

A Bayesian Approach to MMM
R
Bayesian Statistics
I’m trying something a bit new this time. Typically how I learn is that I see something interesting (either in a blog post, an academic article, or through something a…
Mar 18, 2024
Gio Circo, Ph.D.

How to Draw Lines Between Pairs of Points in R

Visualizing journeys between cities
R
Spatial Statistics
Here’s a quick one. I was recently asked how you might plot the travel of individuals over time on a map. For example, if you had longitudinal data recording the residences…
Jan 16, 2024
Gio Circo, Ph.D.

Using NLP To Classify Medical Falls

Or: An Old Dog Learning New Tricks
Python
Data Science Applications
There’s no question that natural language processing (NLP) facilitated by deep learning has exploded in popularity (much of which is popularized by the ChatGPT family of…
Jan 8, 2024
Gio Circo, Ph.D.

The Great American Coffee Taste Test

A deeper dive with Bayes
R
Bayesian Statistics
Miscellaneous
In October I was lucky enough to participate in popular coffee YouTuber James Hoffman’s Great American Coffee Taste Test. In short, participants got 4 samples of coffee and…
Dec 1, 2023
Gio Circo, Ph.D.

Synthetic Controls and Small Areas

A short discussion on ‘microsynthetic’ controls
R
Causal Inference
Bayesian Statistics
Andrew Gelman recently covered a mildly controversial paper in criminology that suggested that a policy of “de-prosecution” by the Philadelphia District Attorney’s office…
Oct 25, 2023
Gio Circo, Ph.D.

Generating Spatial Risk Features using R

Creating ‘RTM’ style map data
R
Spatial Statistics
Machine Learning & Prediction
In criminology there is a considerable research on the role that fixed spatial features in the environment have on crime. These spatial risk factors have criminogenic…
Oct 6, 2023
Gio Circo, Ph.D.

Good Mythical Morning: Blind Fast Food Taste Tests

How good are Rhett and Link?
R
Miscellaneous
So, its no secret that my wife and I are fans of Rhett and Link’s YouTube series Good Mythical Morning. Specifically, we are fans of the large variety of food- related…
Jul 27, 2023
Gio Circo, Ph.D.

Building an Outlier Ensemble from ‘Scratch’

Part 3: Histogram-based anomaly detector
R
Anomaly Detection
Machine Learning & Prediction
This is the third part of a 3-part series. In the first two posts I described how I built a principal components analysis anomaly detector and a k-nearest neighbors anomaly…
May 14, 2023
Gio Circo, Ph.D.

Building an Outlier Ensemble from ‘Scratch’

Part 2: K-nearest neighbors anomaly detector
R
Anomaly Detection
Machine Learning & Prediction
This is the second part of a 3-part series. In the previous post I talked a bit about my desire to work on building the pieces of an outlier ensemble from “scratch”…
Apr 25, 2023
Gio Circo, Ph.D.

Anomaly Detection for Time Series

Applying a PCA anomaly detector
R
Anomaly Detection
Machine Learning & Prediction
Identifying outliers in time series is one of the more common applications for unsupervised anomaly detection. Some of the most common examples come from network intrusion…
Apr 24, 2023
Gio Circo, Ph.D.

Building an Outlier Ensemble from ‘Scratch’

Part 1: Principal components anomaly detector
R
Anomaly Detection
Machine Learning & Prediction
I strongly believe in “learning by doing”. One of the things I have been working on quite a bit lately is unsupervised anomaly detection. As with many machine-learning…
Apr 7, 2023
Gio Circo, Ph.D.

An Alternative to Buffers for Spatial Merging

Car Crashes in Austin
R
Spatial Statistics
This is a bit of a mini-blog post based on a workflow that I have used based on some of my own work. A common issue in spatial analysis - and especially in criminology - is…
Mar 20, 2023
Gio Circo, Ph.D.

The Power of Ensembles

Adventures in outlier detection
Python
Anomaly Detection
Machine Learning & Prediction
It’s no secret that ensemble methods are extremely powerful tools in statistical inference, data science, and machine learning. It’s long been known that many “imperfect”…
Feb 15, 2023
Gio Circo, Ph.D.

Injuries at Amazon Warehouses - A Bayesian Approach

R
Bayesian Statistics
My friend, Andy Wheeler, just recently posted on his blog about reported injuries at Amazon warehouses. As he rightly points out, the apparent high number of injuries at…
Nov 11, 2022
Gio Circo, Ph.D
No matching items