Tabular Explanations

In this demo we will:

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

• Create an explainer that will offer insight into why a particular prediction was made for a given input

• Send a prediction request to the pipeline

• View the explanation

Note: This demo uses a model trained to predict high or low income based on demographic features from a 1996 US census.

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

1. Navigate to the Model Catalog page where the model was registered.

2. Find the model and under the Action dropdown list, select Deploy.

Deploy model

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

   • Name: income-classifier

   • Namespace: seldon

   • Type: Seldon ML Pipeline

Deploy pipeline

1. The default predictor should already be filled in from the model catalog. Click Next.

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

3. If your deployment is launched successfully, it will show an Available status in the Overview page.

Get Predictions

1. Click on the income-classifier 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]
    }
  ]
}

1. Click the Predict button.

A screenshot showing the Predict page with the text area pre-populated

Add an Explainer

There are currently 2 explainers available for tabular data classification:

• Anchor Explainer

• Kernel SHAP Explainer

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

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

Anchor Explainer

For step 2, set the following details:

   - Explainer Algorithm: Anchor

For step 3, set the following details:

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

Kernel SHAP Explainer

For step 2, set the following details:

   - Explainer Algorithm: KernelShap

For step 3, set the following details:

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

1. Skip step 4

2. For step 5, set following details

   - Memory: 1Gi

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

4. If your explainer is launched successfully, both the pipeline and the explainer will show an Available status.

Explain 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 Explainer

Anchor Explanation Part 1

Anchor Explanation Part 2

Anchor Explanation Part 3

Kernel SHAP Explainer

Shap Explanation Part 1

Shap Explanation Part 2

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

Next Steps

Why not try our other demos? Ready to dive in? Read our operations guide to learn more about how to use Enterprise Platform.