> For the complete documentation index, see [llms.txt](https://docs.bdb.ai/data-science-lab-4/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.bdb.ai/data-science-lab-4/repo-sync-project/tabs-for-a-data-science-lab-project/tabs-for-tensorflow-and-pytorch-environment/dataset/dataset-list-page/create-experiment.md).

# Create Experiment

This option helps the users to create an Auto ML experiment on the selected Dataset.

*A user can create a supervised learning (data science) experiment by choosing the **Create Experiment** option.*

{% hint style="success" %}
*Check out the given illustration on how to create an experiment based on the selected dataset.*
{% endhint %}

{% embed url="<https://files.gitbook.com/v0/b/gitbook-x-prod.appspot.com/o/spaces%2F1QeOywZjV1cHo55cMW8u%2Fuploads%2FAmY78p88tcTHFc4jNdXb%2FCreating%20an%20Experiment_RSP.mp4?alt=media&token=1b307dab-d17e-40e7-9941-6438c31d8418>" %}
***Creating an  Dataset based Experiment***
{% endembed %}

{% hint style="info" %}
*<mark style="color:green;">Please Note:</mark> The Create Experiment icon is provided on the **Dataset List** page under the **Dataset tab** of a Data Science Project.*&#x20;
{% endhint %}

* Navigate to the **Dataset List** page for a Repo Sync Project.
* Select a ***Dataset*** from the list.
* Click the ***Create Experiment*** icon.

<figure><img src="https://4082649235-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2F1QeOywZjV1cHo55cMW8u%2Fuploads%2FAwufMXnrJZ2bsOH2RjaD%2Fimage.png?alt=media&amp;token=1fff3c39-6272-4e7a-90b6-48e4774ca3ac" alt=""><figcaption><p><em><strong>Accessing the Create Experiment option for a Dataset</strong></em></p></figcaption></figure>

{% hint style="info" %}
*<mark style="color:green;">Please Note:</mark> An experiment gets initiated in two steps:*

* ***Configure**: Enter Experiment name, Description, and Target column.*

* ***Select Experiment Typ**e: Classification for discrete data and Regression for continuous data (numeric value).*
  {% endhint %}

* The ***Configure*** tab opens (by default) while opening the ***Create Experiment form***.

* Provide the following information:
  * Provide a name for the experiment.
  * Provide Description (optional).
  * Select a Target Column.
  * Select a Data Preparation from the drop-down menu.
    * Use check-box to select a Data Preparation from the displayed drop-down.

<figure><img src="https://4082649235-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2F1QeOywZjV1cHo55cMW8u%2Fuploads%2Fioye0tSKB8bISw9gqC5h%2Fimage.png?alt=media&amp;token=50d8c2fb-3fcb-4058-831e-e0bbd7dcf4db" alt=""><figcaption><p><em>Selecting Data Preparation</em></p></figcaption></figure>

* Select columns that need to be excluded from the experiment.
  * Use check-box to select a field to be excluded from the experiment.

{% hint style="info" %}
*<mark style="color:green;">Please Note:</mark> The selected fields will not be considered while training the Auto ML model experiment.*
{% endhint %}

<figure><img src="https://4082649235-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2F1QeOywZjV1cHo55cMW8u%2Fuploads%2FQfodqcUwVLwvwYJJUsMm%2Fimage.png?alt=media&amp;token=c54a5338-f70c-4c21-8e94-18ec899b4308" alt=""><figcaption><p><em><strong>Selecting Columns to be excluded from the model training</strong></em></p></figcaption></figure>

* Click the ***Next*** option.             &#x20;

<figure><img src="https://4082649235-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2F1QeOywZjV1cHo55cMW8u%2Fuploads%2FJURtdtP1DNjA7sAH4Edu%2Fimage.png?alt=media&amp;token=12fc3d4c-b975-4326-ab1f-6296595c6c3f" alt=""><figcaption><p><em><strong>Configure tab with selected Data Preparations and excluded fields</strong></em></p></figcaption></figure>

* The user gets redirected to the ***Select Experiment Type*** tab.
* Select a prediction model using the checkbox.
* *Based on the selected experiment type a validation notification message appears.*
* Click the ***Done*** option.

<figure><img src="https://4082649235-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2F1QeOywZjV1cHo55cMW8u%2Fuploads%2FVmo08lrxllSsRpkBDlQY%2Fimage.png?alt=media&amp;token=c495dc3c-99f8-4c64-a660-6de208e6caf1" alt=""><figcaption></figcaption></figure>

* A notification message appears.
* The user gets redirected to the Auto ML list page.
* The newly created experiment gets added to the list.

<figure><img src="https://4082649235-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2F1QeOywZjV1cHo55cMW8u%2Fuploads%2FyncfNRG3lH9FVyIGQVTZ%2Fimage.png?alt=media&amp;token=e8c27883-510c-4cbf-8935-92f3ee2e5a82" alt=""><figcaption><p><em><strong>Experiment gets added under the AutoML tab</strong></em></p></figcaption></figure>

{% hint style="info" %}
*<mark style="color:green;">Please Note:</mark> Refer the* [***Data Science Lab Quick Start Flow*** ](https://docs.bdb.ai/data-science-lab-4/data-science-lab-quick-start-flow)*page to get an overview of the **Data Science Lab** module in nutshell.*&#x20;
{% endhint %}