Model development in a managed notebooks instance
This page describes common ways to develop a machine learning (ML) model in Vertex AI Workbench managed notebooks. You can use pre-installed Python packages that are commonly used for ML model development, Vertex AI custom training, and BigQuery ML.
Common Python packages
By default, managed notebooks instances are pre-installed with Python packages that are commonly used for model development. Import these packages into your notebook file and they are ready to use.
Vertex AI custom training
You can use Vertex AI custom training to create and train models from within your managed notebooks instance.
Install one of the Vertex AI client libraries on your instance, or use the Vertex AI API to send API requests from a Jupyter notebook file.
BigQuery ML
Using BigQuery ML, you can train models that use your BigQuery data, all from within your managed notebooks instance. For example, by using the Python client for BigQuery, you can send SQL commands from your notebook file to create a model, and then use the model to get batch predictions.
BigQuery ML leverages the BigQuery computational engine, so you don't need to deploy the compute resources required for batch predictions or model training. This can reduce the time it takes to set up training, evaluation, and prediction.
What's next
To learn more about Vertex AI custom training, see Understand the custom training service.
To learn more about BigQuery ML, see What is BigQuery ML?