DataScienceResources

This repository houses some of the links which I found useful for data science and machine learning.

Model explanations

The most important features in your data for a complex machine learning model (such as an ensemble model) can be provided by training an explainable model. The explainable model is known as the surrogate model. More on how to derive the explanations from the explainable model and which explainable model to pick please refer to the link.

There are other techniques on machine learning interpretibility where we compare the explanations from multiple explanations techniques like LIME and SHAP. More on these techniques can be found at the link.

Feature Engineering

To train a good machine learning model you require good features. Creating good features requires in depth understanding of the raw data and how to transform into the most meaningful features via feature engineering. Some of the feature engineering techniques are captured in the following links:-

• Fundamental Techniques of Feature Engineering for Machine Learning
• Feature Engineering for Machine Learning: A Comprehensive Overview

Dimensionailty Reduction

• PCA A Step-by-Step Explanation of Principal Component Analysis (PCA)

Bias vs Variance

• Bias-Variance Trade-Off in Machine Learning link

Using pandas.cut method

• All Pandas cut() you should know for transforming numerical data into categorical data link

Ensembling

• A Comprehensive Guide to Ensemble Learning link
• Ensemble Methods in Machine Learning: What are They and Why Use Them? link

Bias and exclusion in Machine learning

• How to Recognize Exclusion in AI linke