Highlights of what it took to survive the sinking ship and what determined survival in a nutshell — Overview On April 15, 1912, the RMS Titanic sank into the depths of the Atlantic Ocean. This mighty ship was traveling from Southampton, England, to New York City with 2,224 souls, and the unthinkable happened — a collision with an iceberg. Without enough lifeboats to save all the passengers and crew…

Sigmoid Function, Linear Regression, and Parameter Estimation (Log-Likelihood & Cross-Entropy Loss) — Objective The primary objective of this article is to understand how binary logistic regression works. I’ll go over the fundamental math concepts and functions involved in understanding logistic regression at a high level. In the process, I’ll go over two well-known gradient approaches (ascent/descent) to estimate the 𝜃 parameters using log-likelihood…

Intuitively learn different components of window functions using Postgres and implement them into your data workflow — Introduction The main goal is to understand the fundamental concepts of window functions and apply them to your SQL workflow. Window functions are nothing more than FOPO (Function Over PartitionBy OrderBy). Here’s a quick outline of what will be covered in this article. The GROUP BY

Best Fitting Model, Feature & Permutation Importance, and Hyperparameter Tuning — Background I conducted my initial exploratory analysis and feature engineering in SQL. In my previous article, I demonstrated how powerful SQL can be in exploring data in relational databases. For more context, it might be worthwhile checking it out before reading this article, although it’s not required. …

Exploratory Data Analysis & Feature Engineering — Introduction There is nothing more powerful than learning something new or taking a skill to the next level by simply doing. In this article, I’ll use SQL (Postgres) to conduct my exploratory analysis and create a transformed feature training set for my machine learning model. Although Python or R is the…