Using Minitab AI to clean your data

The Minitab Data Center provides a conversational interface that guides your data preparation.

In This Topic

Generate prep steps
Tips and requirements
Examples

Generate prep steps

Use the button to open and close the Minitab AI pane.

Enter your request and then select Generate

Important

AI technology may make mistakes. It is the user’s responsibility to ensure the output is accurate, appropriate, and meets your organization’s standards and requirements. For more information, see the Minitab Trust Center.

Tips and requirements

The data set must be open and must contain data

If any prior cleaning steps make the data set invalid, then the AI is not available.

Note

You must be in the Cleanup view to clean your data.

Be as clear as possible in your prompts

Prompts in English give the best results.

If the AI rate limit has been reached, you must wait a few moments before trying again.

Use a series of smaller prompts instead of one complex prompt

Minitab AI generates a maximum of 30 steps with one prompt. If a single prompt would generate more than 30 data prep steps, an error is issued and no steps are generated.

A series of simple prompts can help improve efficiency and accuracy of the generated steps.

The AI generated steps are added after the current selected step

To insert steps in a particular order, make sure the step is selected in the Steps pane.

Note

The AI generated steps can error in the Steps pane if they conflict with previous or subsequent steps.

Provide feedback if generated steps are not correct

Give a 'thumbs down" to provide anonymous feedback that indicates the created steps were not helpful.

Several data cleaning steps require that the data are in equal length columns

When you have unequal columns and try to use the following steps, the columns are populated with missing values to make column lengths equal.

Sort
Filter
Merge

Undo and redo AI steps

The AI generated steps can be edited or deleted.

If the AI produces multiple steps from the same prompt, they are undone or redone together.

Note

Only the steps in the Steps pane are undone/redone.

If you need more assistance for any of the supported steps, see the following links.

Examples

Example of replacing values

This column contains data about whether someone has interest in a hearing app. The data include five different values that could be summarized simply as Yes, No, or Maybe.

Use an AI prompt to quickly change these values. For example, enter for interest in a hearing app, use only yes no or maybe.

Example of filtering rows

This column contains data about whether someone has interest in a hearing app. Let's focus on the Maybe responses and find out more about these data points.

Use an AI prompt to quickly filter these values. For example, enter keep only rows with maybe for interest in hearing app

Example of extracting columns

The data set is now filtered by people who "might" be interested in a hearing app. The column that contains what features they have interest in has many levels. Let's extract values from the column to describe the primary reason more easily.

Use an AI prompt to quickly extract the primary reasons. For example, enter split the desired app features.

The original column was split into five new columns, using the comma as the delimiter. The first two new columns more clearly describe the primary reasons.