Introduction
  • Introduction to the course
  • Course curriculum overview
  • Course requirements
  • Setting up your computer
  • Course Material
  • The code
  • Presentations
  • Download Dataset
  • Additional Resources for the required skills
  • How to approach the course
Overview of Model Deployment
  • Deployments of Machine Learning Models
  • Deployment of Machine Learning Pipelines
  • Research and Production Environment
  • Building Reproducible Machine Learning Pipelines
  • Challenges to Reproducibility
  • Streamlining Model Deployment with Open-Source
  • Additional Reading Resources
Machine Learning System Architecture
  • Machine Learning System Architecture and Why it Matters
  • Specific Challenges of Machine Learning Systems
  • Principles for Machine Learning Systems
  • Machine Learning System Architecture Approaches
  • Machine Learning System Component Breakdown
  • Additional Reading Resources
Research Environment - Developing a Machine Learning Model
  • Research Environment - Process Overview
  • Machine Learning Pipeline Overview
  • Feature Engineering - Variable Characteristics
  • Feature Engineering Techniques
  • Feature Selection
  • Training a Machine Learning Model
  • Research environment - second part
  • Code covered in this section
  • Python library versions
  • Data analysis demo - missing data
  • Data analysis demo - temporal variables
  • Data analysis demo - numerical variables
  • Data analysis demo - categorical variables
  • Feature engineering demo 1
  • Feature engineering demo 2
  • Feature selection demo
  • Model training demo
  • Create a Machine Learning Pipeline
  • Score new data with the house price model
  • Scoring new data with our model
  • Research environment - third part
  • Python Open Source for Machine Learning
  • Open Source Libraries for Feature Engineering
  • Feature engineering with open source demo
  • Research environment - fourth part
  • Intro to Object Oriented Programing
  • Inheritance and the Scikit-learn API
  • Create Scikit-Learn compatible transformers
  • Create transformers that learn parameters
  • Feature engineering pipeline demo
  • Should feature selection be part of the pipeline?
  • Research environment - final section
  • Getting Ready for Deployment - Final Pipeline
  • Create and end to end Pipeline for Classification
  • Bonus: Additional Resources on Scikit-Learn
Packaging The Model for Production
  • Introduction to Production Code
  • Repo for this section
  • Code Overview
  • Reminder: Download the Kaggle Data
  • Package Requirements Files
  • Working with tox [Do NOT skip - important]
  • Troubleshooting Tox
  • Package Config
  • The Model Training Script & Pipeline
  • Introduction to Pytest [Optional]
  • Feature Engineering Code in the Package
  • Making Predictions with the Package
  • Building the Package
  • Tooling
  • Section Notes & Further Reading
Section 6: Serving and Deploying the model via REST API
  • Running the API Locally
  • Understanding the Architecture of the API
  • Introduction to FastAPI
  • The API Endpoints
  • Using Schemas in our API
  • Logging in our Application
  • The Uvicorn Web Server
  • Introducing Heroku and Platform as a Service (PaaS)
  • Deploying our Application to Heroku
  • Understanding the Heroku-Specific Project Files
  • Section Notes & Further Reading
Serving the model via REST API
  • How to Use the Course Resources
Continuous Integration and Deployment Pipelines
  • Attention !!! - we are updating this section!
  • 8.1 - Introduction to CI/CD
  • 8.2 - Setting up CircleCI
  • 8.3 - Setup Circle CI Config
  • 8.4a - Gotchas
  • 8.4 - Publishing the Model to Gemfury
  • 8.5 - Testing the CI Pipeline