Practical Data Science with Amazon SageMaker

Course subjects

Module 1: Introduction to machine learning

• Types of ML

• Job Roles in ML

• Steps in the ML pipeline

Module 2: Introduction to data prep and SageMaker

• Training and test dataset defined

• Introduction to SageMaker

• Demonstration: SageMaker console

• Demonstration: Launching a Jupyter notebook

Module 3: Problem formulation and dataset preparation

• Business challenge: Customer churn

• Review customer churn dataset

Module 4: Data analysis and visualisation

• Demonstration: Loading and visualising your dataset

• Exercise 1: Relating features to target variables

• Exercise 2: Relationships between attributes

• Demonstration: Cleaning the data

Module 5: Training and evaluating a model

• Types of algorithms

• XGBoost and SageMaker

• Demonstration: Training the data

• Exercise 3: Finishing the estimator definition

• Exercise 4: Setting hyper parameters

• Exercise 5: Deploying the model

• Demonstration: hyper parameter tuning with SageMaker

• Demonstration: Evaluating model performance

Module 6: Automatically tune a model

• Automatic hyper parameter tuning with SageMaker

• Exercises 6-9: Tuning jobs

Module 7: Deployment / production readiness

• Deploying a model to an endpoint

• A/B deployment for testing

• Auto Scaling

• Demonstration: Configure and test auto scaling

• Demonstration: Check hyper parameter tuning job

• Demonstration: AWS Auto Scaling

• Exercise 10-11: Set up AWS Auto Scaling

Module 8: Relative cost of errors

• Cost of various error types

• Demo: Binary classification cutoff

Module 9: Amazon SageMaker architecture and features

• Accessing Amazon SageMaker notebooks in a VPC

• Amazon SageMaker batch transforms

• Amazon SageMaker Ground Truth

• Amazon SageMaker Neo

Please note: This is an emerging technology course. Course outline is subject to change as needed.