Full Catalog

Here is the full catalog of content linked to here on Featuring Data Science.

LinkedIn Post - Random Forest Hyperparameters

random forest

content:social

A note of caution about scikit-learn’s default settings

LinkedIn Post - Sixteen MLOps Terms

mlops

content:social

MLOps terms to know from Raphael Hoogvliets

SHAP Is Not All You Need

supervised learning

model explainability

Three blog posts about SHAP and alternatives to consider from Christoph Molnar and Giles Hooker

NumPy 2.0 - New Major Release

news

python

mlops

First major release of NumPy since 2006

Snowflake and Databricks Summits (June 2024)

news

data engineering

content:social

The main takeaways and major announcements from Tristan Handy

How the Guinness Brewery Invented the Most Important Statistical Method in Science

statistics

A story of the invention of the t-test from Jack Murtagh of Scientific American

Awesome Strategies to Visualize Change with Time

data visualization

time series

code

Professional plots with links to R code from Bo Yuan, PhD

LinkedIn Post on PCA on Non-Linear Data

dimensionality reduction

feature selection

data visualization

content:social

Some thoughts about PCA from Shai Nisan, PhD and Prof. Hamid Karimi

Evolving from Rule-based Classifier: Machine Learning Powered Auto Remediation in Netflix Data Platform

rules-based algos

neural networks

real-life use cases

Combining a rules-based engine and a neural network to save data platform costs from Binbing Hou et al. at Netflix

How DoorDash Improves Holiday Predictions via Cascade ML Approach

time series

real-life use cases

A real example of time series forecasting from Chad Akkoyun and Zainab Danish at DoorDash

Defining Data Intuition

data science:general

Two blog posts on data intuition from Ryan Harter and Harvard Business

What Data Scientists Need to Know about MLOps Principles

mlops

content:audio

Podcast interview of MLOps engineer Mikiko Baseley hosted by Daliana Liu

What are the most important statistical ideas of the past 50 years?

statistics

Counterfactual Causal Inference, Bootstrapping, Regularization, and more from Andrew Gelman and Aki Vehtari

Deep Dive into Clustering: k-Means and HDBSCAN: a detailed comparison

unsupervised learning

clustering

code

Introduction to HDBSCAN with examples and code from Daniel Capellupo, PhD

Deep Dive into Clustering: The k-Means algorithm and choosing the number of clusters

unsupervised learning

clustering

code

Comparing 4 clustering metrics from Daniel Capellupo, PhD

A Brief History of Data Science

data science:general

“Statistics, Data Analysis, and Coding converge to form a new career for the 21st century” from Daniel Capellupo, PhD

Combining Rule Engines and Machine Learning

rules-based algos

Thoughts about rules-based algorithms and ML from Neal Lathia

A Modern Dilemma: When to Use Rules vs. Machine Learning

rules-based algos

Insights on using rules and ML together from Andrew Bonham at Capital One

Metrics for Multi-Class Classification: an Overview

supervised learning

classification

statistics

arXiv

From accuracy to Cohen-Kappa from Margherita Grandini et al. at CRIF

XGBoost Resources

supervised learning

xgboost

content:video

Series of four detailed videos about how XGBoost works from Josh Starmer at StatQuest

Beware Default Random Forest Importances

explainability

supervised learning

random forest

Important reading for anyone using linear model coefficients or tree-based feature importance from Terence Parr et al.

Machine Learning vs. Statistics

data science:general

statistics

Different approaches to similar problems from Tom Fawcett and Drew Hardin

How to make beautiful data visualizations in Python with matplotlib

data visualization

code

Some examples, with code, of color schemes and simplifying the plot display from Dr. Randal Olson