Applied Machine Learning: Supervised Learning

Course details

In this course, Matt Harrison—a Python and data science corporate trainer, author, speaker, consultant, and advisor—shows you how to apply supervised learning techniques to real-world problems, focusing on both classification and regression tasks. Start with basic models like linear regression, and then advance to more complex algorithms like decision trees and XGBoost. Plus, explore model evaluation, optimization, and deployment techniques. With practical challenges and solutions, this course prepares you to apply supervised learning to solve problems in industries like healthcare, finance, and real estate.

Learning objectives
Implement and evaluate both classification and regression models using supervised learning.
Fine-tune and optimize machine learning models using cross-validation and hyperparameter tuning.
Apply advanced techniques like ensemble methods (bagging and boosting) and XGBoost.
Deploy a trained supervised learning model in a real-world application using Flask.

Concepts

0. Introduction

01 - A look at supervised learning
02 - What you should know
03 - How to use Codespaces

1. Introduction to Supervised Learning

04 - What is supervised learning
05 - Data - Features, labels, training sets
06 - Metrics for classification and regression

2. Linear Regression

07 - What is linear regression
08 - Implementing linear regression in Python
09 - Evaluating linear regression
10 - Challenge - Evaluate linear regression
11 - Solution - Evaluate linear regression

3. Classification Algorithms

12 - What is classification
13 - Logistic regression
14 - K-nearest neighbors
15 - Decision trees
16 - Challenge - A classification model
17 - Solution - A classification model

4. Overfitting and Underfitting

18 - Understanding overfitting and underfitting
19 - Decision stumps
20 - Overfitting
21 - Cross-validation and Goldilocks
22 - Challenge - Goldilocks model
23 - Solution - Goldilocks model

5. Additional Techniques

24 - Ensembles - Bagging and boosting
25 - Tuning hyperparameters
26 - Explaining simple models
27 - SHAP (SHapley Additive exPlanations)
28 - Challenge - XGBoost model
29 - Solution - XGBoost model

6. Deployment

30 - Deploying with Flask
31 - Querying the model
32 - Challenge - Deployment
33 - Solution - Deployment

Conclusion

34 - Next steps in your machine learning journey