Chapter 1: Getting Started: Data Analysis and Feature Engineering
Chapter Goal: Establish the premise of the problem we want to solve with machine learning. Analyze several data sets and process them.
No of pages - 30 pages
Sub - Topics
1. Premise
4. Data analysis
5. Feature engineering
Chapter 2: Building a Machine Learning Model
Chapter Goal: Build a machine learning model on a data set / several data sets that we processed the data for in chapter 4.
No of pages – 40 pages
Sub - Topics:
1. Building the model
2. Training and testing the model
3. Validation and optimizing
Chapter 3: What is MLOps?
Chapter Goal: Introduce the reader to MLOps, various stages of automation in MLOps setups, automation with pipeline, and to CI/CD and CD Deployment.
Pipelines for: source repo to deployment, prediction services, performance monitoring, etc
Continuous Integration (source repo updated with new models), and Continuous Delivery (new models deployed).
No of pages – 40 pages
Sub -Topics
1. What is MLOps?
2. MLOps setups
3. Automation
4. CI/CD – Continuous Integration & Delivery
5. CD - Deployment
Chapter 4: Introduction to MlFlow
Chapter Goal: Introduce the reader to MLFlow and how to incorporate MLFlow into our ML training process (PyTorch, Keras, TensorFlow)
No of pages – 30 pages
Sub - Topics:
1. What is MLFlow?
2. MLFlow in PyTorch
3. MLFlow in Keras
4. MLFlow in TensorFlow
Chapter 5: Deploying in AWS – 40 pages
Chapter Goal: Guide the reader through the process of deploying an MLOps setup on AWS SageMaker.
-Description: The chapter will walk the reader through AWS SageMaker and help them deploy their MLOps setup (data processing scripts, model train, test, validation scripts) in AWS.
Chapter 6: Deploying in Azure – 40 pages
Chapter Goal: Guide the reader through the process of deploying an MLOps setup on Microsoft Azure.
-Description: The chapter will walk the reader through Microsoft Azure and help them deploy their MLOps setup (data processing scripts, model train, test, validation scripts) in Azure.
Chapter 7: Deploying in Google – 40 pages
Chapter Goal: Guide the reader through the process of deploying an MLOps setup on Google Cloud.
-Description: The chapter will walk the reader through Google Cloud and help them deploy their MLOps setup (data processing scripts, model train, test, validation scripts) in Google Cloud.
Appendix A: a2ml – 20 pages
Chapter Goal: This appendix chapter is optional and guides users through the process of deploying an MLOps setup using a2ml.
-Description: The chapter will walk the reader through a2ml and help them deploy their MLOps setup (data processing scripts, model train, test, validation scripts) through a2ml.