Tabular Data Classification on Income Dataset

In this demo we will:

• Create a pipeline which can be used to classify tabular data

• Send a request to get a prediction

• Create an explainer - either an anchor or kernel SHAP explainer

• Send a request to a prediction pipeline

• View the explanation

Register an income classifier model

Register a pre-trained income classifier SKLearn model. See the “Register an income classifier model” section in the Drift Detection demo for detailed instructions.

Configure predictions schema for classifier

Edit the model metadata to update the prediction schema for the model. See the “Configure predictions schema for classifier” section in the Drift Detection demo for detailed instructions.

Launch a Seldon ML Pipeline

Deploy the income classifier model from the catalog into an appropriate namespace

1. From the model catalog, under the Action dropdown list, select Deploy.

   Expand to see deploy model

   

2. Enter the deployment details in the deployment creation wizard and click Next:

   • Name: income

   • Namespace: seldon

   • Type: Seldon ML Pipeline

   Expand to see deploy pipeline

   

3. The predictor details should already be filled in from the model catalog. Click Next.

4. Click Next for the remaining steps, then click Launch.

Get Predictions

1. Click on the income pipeline created in the previous section to enter the deployment dashboard.

2. Inside the deployment dashboard, on the left navigation drawer, click on the Predict button.

3. On the Predict page, enter the following text:

{
  "inputs": [
    {
      "name": "income",
      "datatype": "INT64",
      "shape": [1, 12],
      "data": [53, 4, 0, 2, 8, 4, 2, 0, 0, 0, 60, 9]
    }
  ]
}

4. Click the Predict button.

Add an Explainer

There are currently 2 explainers available for tabular data classification:

• Anchor Explainer

• Kernel SHAP Explainer

1. From the income deployment dashboard, click Add inside the Model Explanation card.

2. For step 1 of the Explainer Configuration Wizard, select Tabular then click Next.

3. Anchor ExplainerKernel SHAP Explainer

   For step 2, set the following details:

      - Explainer Algorithm: Anchor
   

   In step 3, set the following details:

      - Explainer URI: gs://seldon-models/scv2/samples/mlserver_1.6.0/income-sklearn/anchor-explainer
      - Explainer Project: default
   

4. Skip step 4

5. For step 5, set following details

   - Memory: 1Gi
   

6. Skip the remaining steps without changing fields, and click Launch.

After a short while, the explainer should become available.

Get Explanation for a Prediction

1. Navigate to the Requests page using the left navigation drawer.

2. Click on the View explanation button to generate explanations for the request.

   Anchor ExplainerKernel SHAP Explainer

   

Congratulations, you’ve created an explanation for the request! 🥳