Notes from the data-science trenches

Tutorials, certification deep-dives, and field notes on ML, Azure AI, and NLP.

From Jekyll to Quarto: A Blog Migration Journey

Migrating a data-science blog from Jekyll/fastpages to Quarto, including theme polish, TOC fixes, and dark-mode comments.

Jul 9, 2026

Azure AI-102 Certification Journey - Day 2 - Plan and prepare to develop AI solutions on Azure

5 min

Study notes for the first module in my Azure AI-102 certification journey: ‘Plan and prepare to develop AI solutions on Azure’. Key concepts, services, and hands-on…

Nov 17, 2025

Azure AI-102 Certification Journey - Day 1 - Plan and prepare to develop AI solutions on Azure

4 min

Study notes for the first module in my Azure AI-102 certification journey: ‘Plan and prepare to develop AI solutions on Azure’. Key concepts, services, and hands-on…

Nov 15, 2025

Azure AI-102 Certification Journey - Introduction

1 min

Intro for my Azure AI-102 certification journey: took the official practice assessment, received a customised learning plan, and will follow recommended modules (Plan and…

Nov 11, 2025

Building a Sticky Table of Contents: From Spec to Implementation

14 min

A comprehensive guide to implementing a responsive, accessible sticky TOC component using spec-driven development methodology

Oct 4, 2025

Back from Hiatus: Jekyll Blog Security Hardening with Spec-Driven Development

9 min

How I returned to blogging by systematically resolving 12 security vulnerabilities using Kiro’s spec-driven approach, and what’s coming next

Sep 30, 2025

Explaining prediction models and individual predictions

4 min

Implementation of algo from Explaining prediction models and individual predictions.

May 29, 2021

Probability - d2l.ai Exercises - Part 6

2 min

This notebook tries to solve the probability exercises in d2l.ai

May 23, 2021

Automatic differentiation - d2l.ai Exercises - Part 5

4 min

The fifth notebook in the series solving exercises from d2l.ai, this blog tries to test and understand the working of the autodiff functionality in tensorflow

May 16, 2021

Text mining with chemical text from chemdNER

3 min

This is a take home project that I did for a company as part of their interview process.

Apr 26, 2021

Calculus - d2l.ai Exercises - Part 4

3 min

The fourth notebook in a series to be posted aiming to solve and understand exercises from d2l.ai curriculum on deep learning

Apr 25, 2021

Recommending a product price for a seller

4 min

This is another take home assignment that I did for a company as part of their interview process

Apr 10, 2021

Linear Algebra - d2l.ai Exercises - Part 3

5 min

The third notebook in a series to be posted aiming to solve and understand exercises from d2l.ai curriculum on deep learning

Feb 9, 2021

Data Preprocessing - d2l.ai Exercises - Part 2

1 min

The second notebook in a series to be posted aiming to solve and understand exercises from d2l.ai curriculum on deep learning

Feb 7, 2021

Data Manipulation - d2l.ai Exercises - Part 1

2 min

The first notebook in a series to be posted aiming to solve and understand exercises from d2l.ai curriculum on deep learning

Feb 4, 2021

Gradient Descent for Linear Regression

5 min

Data extraction from Wikimedia dump

Aug 31, 2020

Tabular data modeling - with Tensorflow

2 min

In this notebook I try to use a competition dataset of log parameters of a server and classify if there was an attempt to attack the server

Jun 24, 2020

Mother’s day Sentiment analysis - with spaCy

6 min

In this notebook I try to use a competition dataset of tweets reacting to Mother’s day and classify their sentiments with spaCy

May 30, 2020

Mother’s day Sentiment analysis

3 min

In this notebook I explore a competition dataset of tweets reacting to Mother’s day

May 24, 2020

Building தமிழ் language model

4 min

In this notebook I try to build a language model for தமிழ்(Tamil) to help in some basic NLP tasks

Apr 20, 2020

Testing out தமிழ் language tokenizer

3 min

In this notebook I test out the sentencepiece tokenizers built previously

Apr 19, 2020

Wiki data extraction

3 min

Data extraction from Wikimedia dump

Apr 14, 2020

Building தமிழ் language tokenizer

1 min

In this notebook I try to build sentencepiece tokenizers for தமிழ் language with data extracted from wiki dump

Apr 14, 2020

Building a Pokemon Classifier

4 min

Here I try to build a pokemon classifier, to understand transfer learning for image classification

Jun 1, 2019