aws-samples / Amazon Forecast Samples
Labels
Projects that are alternatives of or similar to Amazon Forecast Samples
Amazon Forecast Samples
Notebooks and examples on how to onboard and use various features of Amazon Forecast
Getting Started Notebooks
This is a place where you will find various examples covering Amazon Forecast best practices
Open the notebooks folder to find a CloudFormation template that will deploy all the resources you need to build your first campaign with Amazon Personalize. The notebooks provided can also serve as a template to building your own models with your own data.
In the notebooks folder you will learn to:
- Prepare a dataset for use with Amazon Forecast.
- Build models based on that dataset.
- Evaluate a model's performance based on real observations.
- How to evaluate the value of a Forecast compared to another.
MLOps with AWS Step Functions
This is a place where you will find various examples covering Machine Learning Operations best practices.
To get started navigate to the ml_ops folder and follow the README instructions.
In the ml_ops folder you will learn how to:
- Deploy an automated end to end pipeline from training to visualization of your Amazon Forecasts in Amazon QuickSight
No code workshop
In this repository, you will find a tutorial to walk you through an energy consumption use case with two different methods:
- For the first method, you will only use the service console and this will be 100% no-code: use this markdown file to follow along.
- For the second method, you will fire up a SageMaker Notebook Instance and perform exactly the same process by using the Amazon Forecast API as documented here (for datasets and models management features) and here (for the query service): run this notebook to dive deeper in these APIs.
License Summary
This sample code is made available under a modified MIT license. See the LICENSE file.