Model Explanations with Anchor Tabular

Launch an income prediction model and get explanations on tabular data.

In this demo we will:

Launch an income classification model which has tabular training features
Send a request to get a predicton
Create an explainer for the model
Send the same request and then get an explanation for it

This model provides a model trained to predict high or low income based on demographic features from a 1996 US census.

Create Model

Use the model url:

gs://seldon-models/sklearn/income/model-0.23.2

load

Get Predictions

Run a single prediction using the JSON below.

{
  "data": {
    "names": [
      "Age",
      "Workclass",
      "Education",
      "Marital Status",
      "Occupation",
      "Relationship",
      "Race",
      "Sex",
      "Capital Gain",
      "Capital Loss",
      "Hours per week",
      "Country"
    ],
    "ndarray": [
      [
        53,
        4,
        0,
        2,
        8,
        4,
        2,
        0,
        0,
        0,
        60,
        9
      ]
    ]
  }
}

load

Add an Anchor Tabular Explainer

Create an model explainer using the URL below for the saved explainer.

gs://seldon-models/sklearn/income/explainer-py36-0.5.2

load

Get Explanation for one Request

Resend a single request and then explain it using the JSON below:

{
  "data": {
    "names": [
      "Age",
      "Workclass",
      "Education",
      "Marital Status",
      "Occupation",
      "Relationship",
      "Race",
      "Sex",
      "Capital Gain",
      "Capital Loss",
      "Hours per week",
      "Country"
    ],
    "ndarray": [
      [
        53,
        4,
        0,
        2,
        8,
        4,
        2,
        0,
        0,
        0,
        60,
        9
      ]
    ]
  }
}

explain

Last modified November 4, 2020: Adding demo for monitoring accuracy metrics (ee9f228)