End-To-End: Interactive Code (Python) - AutoML in Vertex AI for ML Operations [notebook 02b]

An end-to-end workflow using Python clients for Vertex AI on Google Cloud Platform. We will use AutoML to train a machine learning model. A walkthrough of all the steps from connecting to data sources, training a model, evaluating the final model, deploying to an online endpoint and requesting predictions from multiple clients. A few deep dives along the way including model explainability! This video follows the notebook 02b - Vertex AI - AutoML with clients (code). GitHub Repository: https://github.com/statmike/vertex-ai-mlops The Notebook followed in this video: https://github.com/statmike/vertex-ai-mlops/blob/main/02%20-%20Vertex%20AI%20AutoML/02b%20-%20Vertex%20AI%20-%20AutoML%20with%20clients%20(code).ipynb Timeline: 0:00 - Introduction 0:40 - Overview 2:15 - Start Walkthrough 4:12 - [Notebook Section] Setup 6:55 - [Notebook Section] Create Dataset 8:47 - [Notebook Section] Train Model with AutoML (part 1) 9:10 - Q&A: AutoML model types? 14:25 - [Notebook Section] Train Model with AutoML (part 2) 17:00 - Q&A: What optimization objective? 20:42 - [Notebook Section] Train Model with AutoML (part 3) 23:40 - Evaluate Model (with console) 29:58 - [Notebook Section] Endpoint and Deployment 35:17 - [Notebook Section] Prediction 42:01 - [Notebook Section] Batch Predictions 44:28 - [Notebook Section] Explanations (part 1) 44:45 - Q&A: What are explanations? 47:47 - [Notebook Section] Explanations (part 2) 50:14 - Q&A: When should I use clients for AutoML? 52:10 - Wrap-up