# configure dataset

The `configure dataset` command configures a dataset and defines its features. In the notebook, you will be guided through a template form that will prompt you for various inputs, such as the name of the data source, each feature name, and type and definition parameters, such as the source data sink for that feature.

## Syntax

```
configure dataset
```

## Parameters

1. To create a new dataset, select **New** from the **Dataset** drop-down list, and specify a name for the dataset.

   Or:

   To change an existing dataset, select the name of the dataset from the **Dataset** drop-down list.
2. To create a new feature, select **Create New** from the **Feature** drop-down list, and specify a name for the feature.

   Or:

   To change an existing feature, select the name of the feature from the **Feature** drop-down list.
3. Select the feature type.
4. Specify a name for the feature and optionally a description.
5. For basis features:
   1. Select the data sink from the drop-down list.
   2. Select the required feature.
6. For contextual features:
   1. If the feature will use an expression, select the **Expression** checkbox.

      <div data-gb-custom-block data-tag="hint" data-style="info" class="hint hint-info"><p>This checkbox is only enabled if you installed an Aizen license that allows expressions.</p></div>

      * If you want to use one of Aizen's built-in expressions, select them from the **Built-in Expressions** drop-down menu.
      * If you want to specify your own expression, leave the **Built-in Expressions** field blank, or select **None** and specify the required expression in the expression field.
   2. For aggregate features:
      1. Make sure to clear the **Expression** checkbox.
      2. Select the input **Datasink**.
      3. Specify the source column from the data sink.
      4. Select the aggregate function.
      5. Select the timestamp column from the drop-down list.
      6. As needed, specify the appropriate missing strategy to handle missing data for the input feature.
      7. Specify the window start and end values to compute the windowed aggregate values.
      8. Specify the required join key and the feature to map to that key.
7. Select if the input feature will be treated as a label or output feature.
8. Select the **Materialize** checkbox if the feature needs to be materialized and stored in the dataset. If you leave the materialize checkbox cleared, then the feature is only created in memory during dataset creation and used in the computation of other features.
9. Click on **Add Feature** to add the feature to the dataset configuration.
10. Repeat the previous steps to define all the dataset features.
11. Click the **Save Configuration** button to start saving the dataset configuration.
12. Click **OK** to persist the configuration.

## Example

<figure><img src="/files/wfCUKvJsLL21vyuD0sIu" alt=""><figcaption></figcaption></figure>


---

# Agent Instructions: Querying This Documentation

If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter:

```
GET https://aizen-corp.gitbook.io/docs/model-building-commands/dataset-commands/configure-dataset.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.