10 Years of Reading Data
I’ve compiled 10 years of my reading data and made good faith guesses at understanding the authors’ preferred gender, race/ethnicity, and geographic country ...
Blog Posts
2020
Calibrating a Random Forest Classifier
In the previous blog post , we looked at the probability predictions that come out of naive implementation of the scikit-learn Random Forest classifier. We n...
Random Forest is not a Calibrated Classifier
What does it mean to have a calibrated classifier? Why is that important? Let’s try to answer that question with a minimal amount of code.
Handy Jupyter Notebook Snippets for Data Scientists
There are a few snippets of code that I put at the top of literally every single Jupyter notebook I create. I hope some of them are useful to you, too.
2018
Three Books that Changed the Way I Work
Who this is blog post for: Knowledge workers, people who work in offices, students, writers, introverts of all stripes. Technology seems to attract the self...
Words are (not) particles!
Last time I went through the first few equations of the word2vec paper (Distributed Representations of Words and Phrases and their Compositionality) and th...
Words are particles!
I have a new project at work that means that I get to dive into a new field - natural language processing. My boss and coworkers suggested a few papers for m...