---
title: Datasets
description: The Datasets tab lists each dataset that has been added to your Use Case and provides the ability interact with those datasets, by exploring features, managing feature lists, wrangling data, or creating an experiment.

---

# Datasets {: #datasets }

The **Datasets** tab lists all datasets currently linked to the selected Use Case by you and other team members. To access this tab, open a Use Case and click **Datasets**.

From this tab, you can:

![](images/wb-data-tab-5.png)

|          | Element   | Description |
|----------|-----------|-------------|
| <div class="table-label">1</div> | Add new      | Add a dataset, experiment, or notebook to your Use Case, or create a new Use Case. |
| <div class="table-label">2</div> | Search       | Search for a specific dataset. |
| <div class="table-label">3</div> | Sort         | Sort the dataset columns. |
| <div class="table-label">4</div> | More options | Click **More options** to interact with a dataset:<br><ul><li>**Explore**: View [exploratory data insights](#view-exploratory-data-insights).</li><li>**Wrangle/Continue Wrangling**: [Perform data wrangling](wb-wrangle-data/index) on datasets retrieved from a data connection.</li><li>**Start modeling**: Set up an experiment using the dataset.</li><li>**Remove from Use Case**: Removes the dataset from the Use Case, also removing access for any team members. The dataset is still available via the [Data Registry](wb-data-registry).</li></ul> |

## View exploratory data insights {: #view-exploratory-data-insights }

While a dataset is being registered in Workbench, DataRobot also performs exploratory data analysis [(EDA1)](eda-explained#eda1){ target=_blank }&mdash;analyzing and profiling every feature to detect feature types, automatically transform date-type features, and assess feature quality. Once registration is complete, you can explore the information uncovered while computing EDA1.

{% include 'includes/workbench/wb-pp-dynamic.md' %}

To view exploratory data insights:

1. In a Use Case, navigate to the **Datasets** tab.
2. Click the **More options** icon next to the dataset you want to view and select **Explore**. Alternatively, click the dataset name to view its insights.

    ![](images/wb-data-tab-1.png)

3. For each feature in the dataset, DataRobot displays various [feature details](histogram){ target=_blank }, including a [histogram](histogram#histogram-chart){ target=_blank } and summary statistics.

    ![](images/wb-data-tab-2.png)

4. To drill down into a specific feature, click its histogram chart along the top.

    ![](images/wb-data-tab-3.png)

## View wrangling recipe SQL {: #view-wrangling-recipe-sql }

If you performed wrangling on a registered dataset, you can see the final compiled form of the operations executed by the cloud data platform after pushdown. To view the SQL queries executed by the cloud data platform, select the dataset and click **Recipe SQL**.

![](images/rn-view-sql.png)

## Feature lists {: #feature-lists }

!!! info "Public preview"
     Support for feature lists in Workbench is on by default.

     <b>Feature flag:</b> Enable Feature Lists in Workbench Preview

After adding a dataset to your Use Case, DataRobot generates feature lists as part of [EDA](eda-explained). Feature lists control the subset of features that DataRobot uses to build models and make predictions. Each model has a feature list associated to it.

You might want to use feature lists to:

- Remove features that cannot be used in the model for any reason, for example, a feature that is causing target leakage.
- Make predictions faster by removing unimportant features (i.e., ones that don't improve the model's performance).

You can use one of the [automatically created lists](feature-lists#automatically-created-feature-lists){ target=_blank }&mdash;Informative and Raw&mdash;or [create a custom feature list](#create-a-feature-list). 

### View feature lists {: #view-feature-lists }

Before setting up an experiment, use exploratory data insights to explore different feature lists before choosing the appropriate one to use for modeling.

To explore insights for a feature list:

1. In the **Datasets** tab, click the **More options** icon next to the dataset you want to view and select **Explore**. Alternatively, click the dataset name.

    ![](images/wb-data-tab-1.png)

2. To access your feature lists, click the dropdown at the top of the page and select an available feature list. The preview updates to show only the features in the selected list.

    ![](images/wb-ft-list-1.png)

### Create a feature list {: #create-a-feature-list }

To create a custom feature list:

1. While exploring a dataset, click the dropdown at the top of the page and select **+ New feature list**. This opens the **Features** view.

    ![](images/wb-ft-list-2.png)

2. Select the box next to each feature you want to include in your custom list. Then, click **Create feature list**.

    ![](images/wb-ft-list-3.png)

3. Enter a name and description (optional) for the new feature list. 

    ![](images/wb-ft-list-4.png)

4. Click **Save changes**. You can now access the new feature list in the dropdown.

## Next steps {: #next-steps }

From here, you can:

- [Add more data.](wb-add-data/index){ target=_blank }
- [Perform data wrangling for datasets added via a data connection.](wb-wrangle-data/wb-add-operation){ target=_blank }
- [Use the dataset to set up an experiment and start modeling.](wb-experiment/index){ target=_blank }
