My name is Lovkush Agarwal. I recently decided to change careers and become a
data scientist. Following David Robinson’s’
advice, I decided to create this blog, to record my progress, learning and projects.
I begin the hyper-parameter optimisations. The first attempt to optimise `n_estimators` had a surprising range of performances, so I delved further to better understand how the performance depends on the folds.
May 29, 2020
I create a table of actors and their bacon numbers using recursion in SQL. The largest finite bacon number is 13.
May 24, 2020
I start my AI for Games project by creating a brute force algorithm for TicTacToe
May 20, 2020
I create a simple hand-made model by just asking how many features are closer to the fraudulent mean than to the non-fraudulent mean. This achieves an AUC of 0.68.
May 19, 2020
I see what happens if I remove entries from the dataset. The hope is that it reduces the time needed to create the models without too much reduction in performance.
May 16, 2020
Jekyll stopped working! I describe what happened and how I fixed the issue.
May 14, 2020
I present my initial attempts at predicting credit card fraud using a Kaggle dataset. Charts and code are included.
May 14, 2020
In this post, I will briefly explain how I created this blog, using Jekyll and GitHub Pages.
May 13, 2020
May 12, 2020
A tutorial of fastpages for Jupyter notebooks.
Feb 20, 2020
A minimal example of using markdown with fastpages.
Jan 14, 2020