Amazon SageMaker Canvas now integrates with Amazon SageMaker Data Wrangler, enabling comprehensive data preparation capabilities for tabular, timeseries, image, and text data from 50+ sources, data analysis and transformations with 300+ operators, and scalable execution on distributed Spark, all without writing code.

<div>
<p>Amazon SageMaker Canvas now supports comprehensive data preparation capabilities powered by Amazon SageMaker Data Wrangler. This allows users to import, analyze, visualize, and transform large amounts of data for machine learning (ML) without writing any code.</p>
<p>Specifically, the article covers:</p>
<ul>
<li>Importing data from over 50 data sources, including S3, Athena, Redshift, and more</li>
<li>Generating Data Quality and Insights reports to identify issues that could impact model quality</li>
<li>Transforming data using 300+ built-in operators to create features for ML</li>
<li>Scaling data preparation steps using distributed Spark processing jobs</li>
<li>Exporting prepared data to train models or make predictions with ML models</li>
<li>Integrating data preparation workflows into SageMaker pipelines</li>
</ul>
</div>


Amazon SageMaker Canvas announces support for comprehensive data preparation capabilities

Related articles