The Wayback Machine - https://web.archive.org/web/20230716230936/https://docs.aws.amazon.com/sagemaker/latest/dg/canvas-getting-started.html
Getting started with using Amazon SageMaker Canvas - Amazon SageMaker
Prerequisites for setting up Amazon SageMaker CanvasStep 1: Log in to Amazon SageMaker Canvas as a business userStep 2: Use SageMaker Canvas to get predictions

Getting started with using Amazon SageMaker Canvas

This guide tells you how to get started with using SageMaker Canvas. If you're an IT administrator, see Setting Up and Managing Amazon SageMaker Canvas (for IT Administrators) to set up SageMaker Canvas for your users.

If you're a business user or analyst, read the following sections.

Prerequisites for setting up Amazon SageMaker Canvas

To set up Amazon SageMaker Canvas, you can either contact your administrator or do the following:

  • Set up an Amazon SageMaker Domain

  • Give yourself permissions to use specific features in Canvas

    • Optional: Give yourself permissions to to upload local files

    • Optional: Give yourself permissions to build custom image and text prediction models

    • Optional: Give yourself permissions to use Ready-to-use models

    • Optional: Give yourself permissions to do time series forecasts

    • Optional: Give yourself permissions to send batch predictions to Amazon QuickSight

    • Optional: Give yourself permissions to register models to the model registry

    • Optional: Give yourself permissions to collaborate with Amazon SageMaker Studio

    • Optional: Give yourself permissions to import Amazon Redshift data

The following sections describe how to set up an Amazon SageMaker Domain and give yourself SageMaker Canvas permissions.

Important

For you to set up Amazon SageMaker Canvas, your version of Amazon SageMaker Studio must be 3.19.0 or later. For information about updating Amazon SageMaker Studio, see Shut down and Update SageMaker Studio.

Onboard to Domain using IAM Identity Center

To onboard to Domain use the following procedure:

  1. Open the SageMaker console.

  2. Choose Domains in the navigation pane.

  3. On the Domains page, choose Create domain

  4. Choose Standard setup.

  5. Choose Configure.

Use the following procedure to configure the general settings for the Domain:

  1. Under Permission, for IAM role, choose an option from the role selector.

    If you choose Enter a custom IAM role ARN, the role must have at a minimum, an attached trust policy that grants SageMaker permission to assume the role. For more information, see SageMaker Roles.

    If you choose Create a new role, the Create an IAM role dialog opens:

    1. Choose Create role. SageMaker creates a new IAM AmazonSageMaker-ExecutionPolicy role with the AmazonSageMakerFullAccess policy attached.

  2. Under Network and storage, specify the following:

  3. Select Next.

Use the following procedure to configure the SageMaker Canvas settings for the Domain:

  1. For the Canvas base permissions configuration, leave the Enable Canvas base permissions option turned on (it is turned on by default). This attaches the AmazonSageMakerCanvasFullAccess policy to your user's execution role and establishes the minimum required permissions to use the SageMaker Canvas app.

  2. (Optional) For the Canvas Ready-to-use models configuration, leave the Enable Canvas Ready-to-use models option turned on to give your users permissions to generate predictions with Ready-to-use models in Canvas (it is turned on by default).

  3. (Optional) For the Time series forecasting configuration, leave the Enable time series forecasting option turned on to give your users permissions to do time series forecasting in SageMaker Canvas (it is turned on by default).

    1. If you left Enable time series forecasting turned on, select Create and use a new execution role, or select Use an existing execution role if you already have an IAM role with the required Amazon Forecast permissions attached (for more information, see the IAM role setup method.

  4. (Optional) If you left Enable time series forecasting turned on, select Create and use a new execution role, or select Use an existing execution role if you already have an IAM role with the required Amazon Forecast permissions attached (for more information, see the IAM role setup method).

  5. (Optional) For the ML Ops permissions configuration section, leave the Enable Model Registry registration permissions for all users option turned on to give your users permissions to register their model version to the SageMaker model registry (it is turned on by default). For more information, see Register a model version in the SageMaker model registry.

  6. (Optional) Add Tags to track your cost and usage trends in AWS Billing and Cost Management. SageMaker adds the tags you specify in the Domain to all of the SageMaker Canvas apps you create in the Domain. For more information about billing and tags, see Manage billing and cost in SageMaker Canvas.

  7. Finish making any other changes to your Domain setup, and then choose Submit.

Note

If you encounter any issues with granting permissions through the console, such as permissions for Ready-to-use models, see the topic Troubleshooting issues with granting permissions through the SageMaker console.

When you set up the Domain, SageMaker Canvas creates an Amazon S3 bucket with a name that uses the following pattern: sagemaker-<Region>-<your-account-id>. Your Canvas application data, such as imported datasets and batch predictions, are stored in the Canvas/ folder in the bucket.

Give yourself permissions to use specific features in Canvas

The following information outlines the permissions that you can grant to a Canvas user to allow the use of various features and functionalities within Canvas:

  • Local file upload. The permissions for local file upload are turned on by default in the Canvas base permissions when setting up your Domain. If you don’t have the ability to upload local files from your machine to SageMaker Canvas, you can attach a CORS policy to the default bucket that SageMaker created for your Domain (sagemaker-<Region>-<your-account-id>). For more information, see Grant Your Users Permissions to Upload Local Files.

  • Custom image and text prediction models. The permissions for building custom image and text prediction models are turned on by default in the Canvas base permissions when setting up your Domain. However, if you have a custom IAM configuration and don't want to attach the AmazonSageMakerCanvasFullAccess policy to your user's IAM execution role, then you must explicitly grant your user the necessary permissions. For more information, see Grant Your Users Permissions to Build Custom Image and Text Prediction Models.

  • Ready-to-use models. You might want to have the ability to use the Canvas Ready-to-use models to make predictions for your data. The permissions are turned on by default when setting up your Domain, or you can edit the permissions for a Domain that you’ve already created. The Canvas Ready-to-use models permissions option adds the AmazonSageMakerCanvasAIServicesAccess policy to your execution role. For more information, see the Get started section of the Ready-to-use models documentation.

  • Time series forecasting. If you’d like to have the ability to perform forecasts on time series data, you can add time series forecasting permissions when setting up your Domain, or you can edit the permissions for a Domain or user profile after creating your Domain. The required permissions are the AmazonSageMakerCanvasForecastAccess managed policy and a trust relationship with Amazon Forecast to the AWS IAM role you chose when setting up the user profile. For instructions on how to add these permissions to your IAM role, see Grant Your Users Permissions to Perform Time Series Forecasting.

  • Send batch predictions to Amazon QuickSight. You might want to have the ability to send batch predictions, or datasets of predictions you generate from a custom model, to Amazon QuickSight for analysis. In QuickSight, you can build and publish predictive dashboards with your prediction results. For instructions on how to add these permissions to your Canvas user's IAM role, see Grant Your Users Permissions to Send Predictions to Amazon QuickSight.

  • Register model versions to the model registry. You might want to register versions of your model to the SageMaker model registry, which is a repository for tracking the status of updated versions of your model. A data scientist or MLOps team working in the SageMaker model registry can view the versions of your model that you’ve built and approve or reject them. Then, they can deploy your model version to production or kick off an automated workflow. Model registration permissions are turned on by default for your Domain. You can manage permissions at the user profile level and grant or remove permissions to specific users. For more information, see Register a model version in the SageMaker model registry.

  • Collaboration with data scientists. If you want to collaborate with Studio users and share models, you must add additional permissions to the AWS IAM role you chose when setting up the user profile. For instructions on how to add the policy to the role, see Grant Users Permissions to Collaborate with Studio.

  • Import data from Amazon Redshift. If you want to import data from Amazon Redshift, you must give yourself additional permissions. You must add the AmazonRedshiftFullAccess managed policy to the AWS IAM role you chose when setting up the user profile. For instructions on how to add the policy to the role, see Grant Users Permissions to Import Amazon Redshift Data.

Note

The necessary permissions to import through other data sources, such as Amazon Athena and SaaS platforms, are included in the AmazonSageMakerFullAccess and AmazonSageMakerCanvasFullAccess policies. If you followed the standard setup instructions, these policies should already be attached to your execution role. For more information about these data sources and their permissions, see Connect to data sources.

Step 1: Log in to Amazon SageMaker Canvas as a business user

Contact your administrator to guide you through the process of setting up Amazon SageMaker Canvas.

When the initial setup is complete, you can access SageMaker Canvas by doing the following.

  1. Navigate to the SageMaker console.

  2. In the navigation pane, choose Canvas.

  3. In the Get Started box, select your user profile from the dropdown.

  4. Choose Open Canvas to open the application.

When you log into SageMaker Canvas for the first time, there is a welcome message with quick getting started tutorials that you can follow for a walkthrough of the SageMaker Canvas application.

Screenshot of the welcome message with the getting started tutorials in the SageMaker Canvas application.

You can follow the Get started with Canvas tutorial for a high-level overview of the SageMaker Canvas application. There are also shorter tutorials that guide you through the individual steps of using SageMaker Canvas. These tutorials show you how to import a dataset, build a model, analyze the results of a built model, and generate predictions with your model. You can revisit the tutorials at any time by choosing the Help button and then choosing one of the tutorials.

Screenshot of the help panel in the SageMaker Canvas application where you can access the getting started tutorials.

Step 2: Use SageMaker Canvas to get predictions

After you’ve logged in to Canvas, you can start building models and generating predictions for your data.

You can either use Canvas Ready-to-use models to make predictions without building a model, or you can build a custom model for your specific business problem. Review the following information to decide whether Ready-to-use models or custom models are best for your use case.

  • Ready-to-use models. With Ready-to-use models, you can use pre-built models to extract insights from your data. The Ready-to-use models cover a variety of use cases, such as language detection and document analysis. To get started making predictions with Ready-to-use models, see Use Ready-to-use models.

  • Custom models. With custom models, you can build a variety of model types that are customized to make predictions for your data. Use custom models if you’d like to build a model that is trained on your business-specific data and if you’d like to use features such as collaborating with data scientists and evaluating your model’s performance. To get started with building a custom model, see Use custom models.

You can also bring your own model (BYOM) from other features in SageMaker. An Amazon SageMaker Studio user can share their model with a Canvas user, and the Canvas user can generate predictions with the model. To learn more, see Bring your own model to SageMaker Canvas.