Writing
Notes on data, models and building
I write Hustle Data, a newsletter of tutorials, competition write-ups and engineering practice. Articles open on Substack.
-
20 SQL Commands For Your Next Data Science Job
The SQL you are most likely to be asked about in a data science interview, one command at a time.
-
How to Evaluate Machine Learning Models using Classification Metrics: ROC, AUC, Precision, Recall, and Beyond
What each classification metric actually measures, with reusable code for every one of them.
-
Deep Learning is all about Gradient Descent Algorithm
Backpropagation, gradient descent and stochastic gradient descent, and how they drive learning in neural networks.
-
Multiclass Classification using Neural Networks
Predicting La Liga match outcomes (win, draw, loss) with a neural network built in PyTorch.
-
Python Development Best Practices: Virtual Environments and requirements.txt
Why isolated environments and pinned dependencies keep Python projects from breaking.
-
From Underdog to Top Contender: How I Surpassed 76% of Teams on Kaggle
A write-up of the GoDaddy microbusiness density forecasting competition: the data, the models and what worked.
-
Unleashing the Power of Dask: Conquer Data at Lightning Speed!
Using Dask for data preprocessing and manipulation when a dataset outgrows pandas.