Automatically Build Models With Amazon Sagemaker
summary
Shows how Amazon SageMaker Autopilot ingests a CSV (Direct Marketing Dataset ~41,000 rows, 20 features, label 'Y'), splits 95/5, and automatically generates 10 candidate pipelines with concrete steps like RobustImputer, ThresholdOneHotEncoder, RobustStandardScaler, PCA and trains XGBoost or LinearLearner. It runs hyperparameter tuning (default 50 jobs per pipeline, i.e. ~500 models), produces runnable notebooks (Data Exploration, Candidate Definition with exact preprocessing code), and deploys a real SageMaker endpoint for predictions.
AI-written summary · about
chapters (7)
- 0:00Introduction
- 1:07Import Sagemaker SDK
- 6:38Analyse Data
- 14:57Pipelines
- 15:34Running the Model
- 22:46Deploy Endpoint
- 23:38Summary
related talks
32mBuild quality ML models easily & quickly with Amazon SageMaker Autopilot
31mUse AutoML to create high-quality models with just a few clicks
31mPut Your Machine Learning on Autopilot
31mUse AutoML to create high-quality models with just a few clicks
34mPrepare data for machine learning with ease, speed, and accuracy
45mAutomate your ML workflows with pipelines
33mBuild, train, and deploy ML models using Amazon SageMaker
19mDrive transformation through machine learning