Overview

This exercise demonstrates how to create a custom text classification model using Azure AI Language Service. The model is trained to categorize text into predefined classes.

Steps & Configuration Details

1. Provision an Azure AI Language Resource

  • Open Azure Portal (https://portal.azure.com) and sign in.
  • Select Create a resource → Search for Language Service → Click Create.
  • Configuration Items:
    • Subscription: Your Azure subscription.
    • Resource Group: Select or create a resource group.
    • Region: Choose from:
      • Australia East
      • Central India
      • East US
      • North Europe
      • South Central US
      • Switzerland North
      • UK South
      • West Europe
      • West US 2
      • West US 3
    • Name: Enter a unique name.
    • Pricing Tier: F0 (Free) or S (Standard).
    • Storage Account: Create a new storage account.
    • Storage Account Type: Standard LRS.
    • Responsible AI Notice: Agree.

After provisioning, navigate to Keys and Endpoint in the Resource Management section.

2. Configure Storage Access

  • Open Azure Portal → Navigate to Storage Account.
  • Select Access Control (IAM) → Add Role Assignment.
  • Configuration Items:
    • Role: Storage Blob Data Contributor
    • Assign Access To: User, group, or service principal
    • Select Members: Choose your user account.

3. Upload Sample Articles

  • Download sample articles:
    https://aka.ms/classification-articles
  • Extract files and upload them to Azure Blob Storage:
    • Create a Blob Container named articles.
    • Set Anonymous Access Level to Container (anonymous read access for containers and blobs).
    • Upload extracted .txt files.

4. Create a Custom Text Classification Project

  • Open Language Studio (https://language.cognitive.azure.com) and sign in.
  • Select Custom Text Classification → Create a project.
  • Configuration Items:
    • Project Type: Single Label Classification
    • Project Name: ClassifyLab
    • Primary Language: English (US)
    • Description: Custom text classification lab
    • Blob Store Container: articles
    • Labeling Option: No, I need to label my files as part of this project

5. Label Training Data

  • Navigate to Data Labeling.
  • Define four classes:
    • Classifieds
    • Sports
    • News
    • Entertainment
  • Assign labels to articles:
    Article 1 → Sports (Training)
Article 10 → News (Training)
Article 11 → Entertainment (Testing)
Article 12 → News (Testing)
Article 13 → Sports (Testing)
Article 2 → Sports (Training)
Article 3 → Classifieds (Training)
Article 4 → Classifieds (Training)
Article 5 → Entertainment (Training)
Article 6 → Entertainment (Training)
Article 7 → News (Training)
Article 8 → News (Training)
Article 9 → Entertainment (Training)
  • Save labels.

6. Train the Model

  • Navigate to Training Jobs → Start a Training Job.
  • Configuration Items:
    • Model Name: ClassifyArticles
    • Training Mode: Manual Split
  • Click Train.

7. Evaluate the Model

  • Navigate to Model Performance → Select ClassifyArticles.
  • Review Accuracy Metrics.
  • If errors exist, check Test Set Details.

8. Deploy the Model

  • Navigate to Deploying Model → Add Deployment.
  • Configuration Items:
    • Deployment Name: articles
    • Model: ClassifyArticles
  • Click Deploy.

9. Configure Your Application

  • Clone the repository:
    git clone https://github.com/MicrosoftLearning/mslearn-ai-language
  • Open the folder in Visual Studio Code.
  • Install dependencies:
    • C#:
      dotnet add package Azure.AI.TextAnalytics --version 5.3.0
    • Python:
      pip install azure-ai-textanalytics==5.3.0
  • Open the configuration file:
    • C#: appsettings.json
    • Python: .env
  • Update Configuration Values:
    • Azure AI Language Endpoint
    • API Key
    • Project Name (ClassifyLab)
    • Deployment Name (articles)
  • Save the configuration file.

10. Add Code to Classify Documents

  • Open the code file:
    • C#: Program.cs
    • Python: classify-text.py
  • Add references:
    • C#:
      using Azure;
using Azure.AI.TextAnalytics;
    • Python:
      from azure.core.credentials import AzureKeyCredential
from azure.ai.textanalytics import TextAnalyticsClient
  • Create the AI Language client:
    • C#:
      AzureKeyCredential credentials = new AzureKeyCredential(aiSvcKey);
Uri endpoint = new Uri(aiSvcEndpoint);
TextAnalyticsClient aiClient = new TextAnalyticsClient(endpoint, credentials);
    • Python:
      credential = AzureKeyCredential(ai_key)
ai_client = TextAnalyticsClient(endpoint=ai_endpoint, credential=credential)
  • Submit classification requests:
    • C#:
      ClassifyDocumentOperation operation = await aiClient.SingleLabelClassifyAsync(WaitUntil.Completed, batchedDocuments, projectName, deploymentName);
foreach (ClassifyDocumentResult documentResult in operation.Value) {
    Console.WriteLine($"Category: {documentResult.ClassificationCategories[0].Category}");
    Console.WriteLine($"Confidence Score: {documentResult.ClassificationCategories[0].ConfidenceScore}");
}
    • Python:
      operation = ai_client.begin_single_label_classify(batchedDocuments, project_name=project_name, deployment_name=deployment_name)
document_results = operation.result()
for classification_result in document_results:
    print(f"Category: {classification_result.classifications[0].category}")
    print(f"Confidence Score: {classification_result.classifications[0].confidence_score}")

11. Run Your Application

  • C#:
    dotnet run
  • Python:
    python classify-text.py
  • Observe the output, which should display classifications and confidence scores.

12. Clean Up

  • Delete Azure resources to avoid unnecessary costs:

This summary captures the essential steps while highlighting all configuration items and code references required for creating a custom text classification model using Azure AI Language.

Related Posts