Exploratory data analysis and automated feature engineering
summary
Overview of Amazon SageMaker tools that turns manual EDA into clickable workflows: SageMaker Data Wrangler connects to S3, Athena, Snowflake or Databricks, auto-detects types, runs a data insights report, offers 300+ built-in transforms and ML-specific ops, and exports to S3, Feature Store or Pipelines. Time-series transforms use TSFresh to generate up to 800 features per column with one click; a customer reports a 50% reduction in data-prep time. Flows export as Python for CI/CD and scale by instance when needed.
AI-written summary · about
chapters (11)
- 0:00Introduction and agenda
- 2:48Defining EDA and engineering
- 6:58Challenges in data prep
- 8:36AWS ML low-code options
- 12:19Sagemaker Data Wrangler
- 17:43EDA and visualization
- 20:43Data transformation
- 23:57Time series specific features
- 28:37Data flow and export
- 32:34Demo: Bitcoin data
- 42:54Conclusion and resources
related talks
33mAccelerate data preparation with Amazon SageMaker Data Wrangler
58mPrepare data and model features for ML with ease, speed, and accuracy
34mPrepare data for machine learning with ease, speed, and accuracy
21mAWS On Air ft. Amazon SageMaker Canvas
30mAmazon SageMaker Feature Store: Store, discover, & share features for ML apps
31mUse AutoML to create high-quality models with just a few clicks
31mUse AutoML to create high-quality models with just a few clicks
44mSimplify Data Preparation for Machine Learning