Amazon SageMaker Example Notebooks

Welcome to Amazon SageMaker. This site highlights example Jupyter notebooks for a variety of machine learning use cases that you can run in SageMaker.

This site is based on the SageMaker Examples repository on GitHub. To run these notebooks, you will need a SageMaker Notebook Instance or SageMaker Studio. Refer to the SageMaker developer guide’s Get Started page to get one of these set up.

On a Notebook Instance, the examples are pre-installed and available from the examples menu item in JupyterLab. On SageMaker Studio, you will need to open a terminal, go to your home folder, then clone the repo with the following:

git clone https://github.com/aws/amazon-sagemaker-examples.git

---

Introduction

• Introduction to Amazon SageMaker

We recommend the following notebooks as a broad introduction to the capabilities that SageMaker offers. To explore in even more depth, we provide additional notebooks covering even more use cases and frameworks.

Get started on SageMaker

• Customer Churn Prediction with XGBoost

Prepare data

• Amazon SageMaker Data Wrangler
• Distributed Data Processing using Apache Spark and SageMaker Processing
• Get started with SageMaker Processing

Train and tune models

• Hyperparameter Tuning with the SageMaker TensorFlow Container
• Train a SKLearn Model using Script Mode

Deploy models

• Host a Pretrained Model on SageMaker
• Deploying pre-trained PyTorch vision models with Amazon SageMaker Neo
• Use SageMaker Batch Transform for PyTorch Batch Inference

Track, monitor, and explain models

• Amazon SageMaker Multi-hop Lineage Queries
• Amazon SageMaker Model Monitor
• Fairness and Explainability with SageMaker Clarify

Orchestrate workflows

• Orchestrate Jobs to Train and Evaluate Models with Amazon SageMaker Pipelines
• SageMaker Pipelines Lambda Step

Popular frameworks

• Hugging Face Sentiment Classification
• Iris Training and Prediction with Sagemaker Scikit-learn
• Train an MNIST model with TensorFlow
• Train an MNIST model with PyTorch

---

More examples

SageMaker Studio

• Get Started with SageMaker Studio
• Framework examples
• Model compilation with Neo
• Bring your own container to Studio

Introduction to Amazon Algorithms

• Introduction to Amazon Algorithms

SageMaker End-to-End Examples

• Fraud Detection System
• Music Recommender
• Understanding Trends in Company Valuation with NLP

SageMaker Use Cases

• Music Streaming Service: Customer Churn Detection
• Fleet Predictive Maintenance
• E-Commerce Personalization
• Pipelines with NLP for Product Rating Prediction
• Credit Risk
• SageMaker Data Wrangler
• SageMaker Algorithms with Pre-Trained Model Examples by Problem Type

Autopilot

• Get started with Autopilot
• Feature selection
• Model explainability
• Autopilot Pipelines

Ingest Data

• Get started with data ingestion
• Athena
• EMR
• Redshift
• Amazon Keyspaces (for Apache Cassandra)

Prep Data

• Get started with data prep
• Detect pre-training data bias
• Tabular data guide

Feature Store

• Get started with SageMaker Feature Store

Frameworks

• Frameworks and Libraries
• Apache MXNet
• Deep Graph Library
• PyTorch
• R
• Scikit-learn
• TensorFlow
• JAX

Training

• Algorithms
• Reinforcement Learning
• Debugger
• Tuning
• Distributed Training
• Training Compiler
• Script Mode
• Bring Your Own Container
• Management Features
• Heterogeneous Clusters

Inference

• Deploy Models with SageMaker
• Batch transform
• Bring your own container
• Data types
• Model Compilation with Neo
• Model deployment
• Model monitor
• Multi-Model Deployment
• Nvidia Triton Inference
• Model Governance

Workflows

• Get started with SageMaker Pipelines
• Pipeline Parameterization
• SageMaker Pipeline Multi-Model
• Pipeline Compare
• Launch AutoML with Pipelines
• Processing
• Spark
• Step Functions
• Notebook Jobs

Advanced Functionality

• Advanced Functionality
• Serverless Inference

Advanced examples

• SageMaker Clarify
• Science of ML
• AWS Marketplace
• Amazon Sagemaker Geospatial Service

Community examples

• Contributions