Hello text data: Create a text classification dataset and import documents

Starting on September 15, 2024, you can only customize classification, entity extraction, and sentiment analysis objectives by moving to Vertex AI Gemini prompts and tuning. Training or updating models for Vertex AI AutoML for Text classification, entity extraction, and sentiment analysis objectives will no longer be available. You can continue using existing Vertex AI AutoML Text models until June 15, 2025. For a comparison of AutoML text and Gemini, see Gemini for AutoML text users. For more information about how Gemini offers enhanced user experience through improved prompting capabilities, see Introduction to tuning. To get started with tuning, see Model tuning for Gemini text models

To learn more, run the "Create, train, and deploy an AutoML text classification model" Jupyter notebook in one of the following environments:

Open in Colab | Open in Colab Enterprise | Open in Vertex AI Workbench user-managed notebooks | View on GitHub

Use the Vertex AI console to create a text classification dataset. After your dataset is created, use the CSV that you copied into your Cloud Storage bucket to import those documents into the dataset.

This tutorial has several pages:

1. Setting up your project and environment.

2. Creating a text classification dataset .

3. Training an AutoML text classification model.

4. Deploy model to an endpoint and send a prediction.

5. Cleaning up your project.

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

1. Go to the Vertex AI console.

2. From the Get started with Vertex AI page, click Create dataset.

3. Specify details about your dataset.

   1. Specify a name for this dataset, such as text_classification_tutorial.

   2. In the Select a data type and objective section, click Text and then select Text classification (Single-label).

   3. For the Region, select us-central1.

      This tutorial uses us-central1, but Vertex AI supports other regions, such as europe-west4.

   4. Click Create to create the empty dataset and then import documents.

4. On the import page, select the Select import files from Cloud Storage and specify the Cloud Storage location of your CSV file. Tip: Click Browse, select the happiness.csv file in the Select object dialog, and click Select.

   For this tutorial, the CSV file is at: gs://${BUCKET}/text/happiness.csv. The bucket for this tutorial is in the same region as the dataset, but you can specify files that are in buckets from any region.

5. Keep the Default data split.

   Vertex AI automatically assigns documents to training, validation, and test sets. For more information, see About data splits for AutoML models.

6. Click Continue to start the import.

   The import process will take a few minutes. When the import completes, you can browse all of the imported documents and their associated labels in the dataset's Browse tab.

What's next

Follow the next page of this tutorial to start an AutoML model training job.