model_garden/notebooks/official/tabular_workflows

Train a Prophet Model using Vertex AI Tabular Workflows

Learn how to create several Prophet models using a training Vertex AI Pipeline from Google Cloud Pipeline Components , and then do a batch prediction using the corresponding prediction pipeline.

The steps performed are:

1. Train the Prophet models.
1. View the evaluation metrics.
1. Make a batch prediction with the Prophet models.

   Learn more about Google Cloud Pipeline Components.

   Learn more about Prophet for tabular data.

TabNet Pipeline

Learn how to create classification models on tabular data using two of the Vertex AI TabNet Tabular Workflows.

The steps performed include:

- Create a TabNet CustomJob. This is the best option if you know which hyperparameters to use for training.
- Create a TabNet HyperparameterTuningJob. This allows you to get the best set of hyperparameters for your dataset.

   Learn more about Tabular Workflow for TabNet.

Wide & Deep Pipeline

Learn how to create two classification models using Vertex AI Wide & Deep Tabular Workflows.

The steps performed include:

- Create a Wide & Deep CustomJob. This is the best option if you know which hyperparameters to use for training.
- Create a Wide & Deep HyperparameterTuningJob. This allows you to get the best set of hyperparameters for your dataset.

   Learn more about Tabular Workflow for Wide & Deep.