Hello tabular data: Create a dataset and training an AutoML classification model

Use the Google Cloud Console to create a tabular dataset and use it to train a classification model.

This tutorial has several pages:

  1. Setting up your project and environment.

  2. Creating a tabular dataset and training an AutoML classification model.

  3. Deploying the model to an endpoint and sending a prediction.

  4. Cleaning up your project.

Each page assumes that you have already performed the instructions from the previous pages of the tutorial.

Create a tabular dataset

  1. In the Google Cloud Console, in the Vertex AI section, go to the Datasets page.

    Go to the Datasets page

  2. Click Create in the button bar to create a new dataset.

  3. Enter Structured_AutoML_Tutorial for the dataset name and select the Tabular tab.

    Leave the Region set to us-central1.

  4. Click Create to create the dataset.

  5. For Select a data source, click Select CSV files from Cloud Storage and enter cloud-ml-tables-data/bank-marketing.csv for the Cloud Storage path.

  6. Click Continue.

    The Analyze pane opens.

  7. Click Generate statistics to generate statistics for the dataset.

    When the statistics are generated, you can click on any feature to see more details about the data for that feature.

Train an AutoML classification model

  1. Click Train new model.

  2. In the Train new model pane, make sure the dataset you created previously is selected for the Dataset field and select Classification for the objective.

  3. Confirm that the AutoML training method is selected, and click Continue.

  4. Select Deposit for the target column and click Continue.

    The list of columns is displayed, with the transformation that will be used for each feature.

  5. Click Continue to display the Compute and pricing panel, and enter 1 for the training budget.

  6. Click Start training.

    The training budget determines actual training time, but the time to complete training includes other activities, so the entire process can take longer than one hour. When the model finishes training, it is displayed in the model tab as a live link, with a green checkmark status icon.

What's next

Follow the next page of this tutorial to deploy your model and request a prediction.