QuestionQ89

VerifiedScaling prototypes into ML models

You have been asked to build a model using a dataset stored in a medium-sized (~10 GB) BigQuery table. You need to rapidly determine whether this data is appropriate for model development. You want to produce a one-time report containing both informative visualizations of data distributions and more sophisticated statistical analyses to share with other ML engineers on your team. You require maximum flexibility in creating the report. What should you do?

Explanation

Vertex AI Workbench user-managed notebooks provide a Jupyter-based environment that can access BigQuery data and run custom Python, SQL, visualization, and statistical-analysis code. That flexibility supports an ad hoc exploratory report with both distribution plots and advanced analyses.

Learn more

Community Discussion

No comments yet. Be the first to start the discussion!