Data Wrangler Gets Copilot Integration
Written by Kay Ewbank   
Monday, 11 November 2024

Microsoft has announced that Copilot is being integrated into Data Wrangler. The move will give data scientists the ability to use natural language to clean and transform data, and to get help with fixing errors in data transformation code.

The Data Wrangler Extension for Visual Studio Code has been available since the end of 2023. It is designed for data scientists and analysts who work with tabular data in Python, and provides data viewing, cleaning and preparation for tabular datasets that is integrated into VS Code and VS Code Jupyter Notebooks. Wrangler provides a rich user interface to view and analyze your data and show insightful column statistics and visualizations.

Data Wrangler comes with a library of built-in transformations and visualizations, and tool generates code using open-source Python libraries for the data transformation operations the user performs.

copilotbanner

GitHub Copilot is described as "Your AI pair programmer". It the OpenAI Codex to suggest code and entire functions in real-time from your editor. The AI-based system takes notice of what you are coding and make suggestions for what it is you are about to type.

Microsoft says that until now, AI tools for exploratory data analysis tasks struggle because of the lack of data context provided to the AI. This results in more generalized responses that are not tailored to the specific task or data at hand. 

Copilot with Data Wrangler lets users provide Copilot with the data context, enabling it to generate more relevant and specific code for the exact dataset that is open. It also lets developers preview the exact behavior of the code on their dataset with the Data Wrangler interface to visually validate Copilot's response.

copilot data wrangler

Copilot in Data Wrangler can be asked to perform ambiguous, open-ended transformations or a specific task. Announcing the new integration, Jeffrey Mew, Senior Product Manager, gave examples of its use including formatting a datetime column by giving an example of the pattern you want "like Nov 8 2024"; removing any column(s) with over 40% missing values; and fixing an error in a data transformation that Data Wrangler has identified as problematic.

To use Copilot with Data Wrangler, users first have to have the Data Wrangler extension for VS Code installed, along with the GitHub Copilot extension for VS Code. They also need an active subscription for GitHub Copilot in their personal account, or have been assigned a seat by their organization. Copilot for Data Wrangler is available now.

copilotbanner

More Information

Data Wrangler On GitHub

Related Articles

GitHub Universe AI Announcements - Copilot And Spark

VS Code Extension For Python Data Science

VS Code Extensions Can Now Use Copilot APIs

GitHub Announces AI-Powered Changes

Microsoft And GitHub Announce Copilot Extensions At Build 2024

Microsoft Launches Copilot Pro

To be informed about new articles on I Programmer, sign up for our weekly newsletter, subscribe to the RSS feed and follow us on Twitter, Facebook or Linkedin.

Banner


OpenAI Releases Swarm
25/10/2024

OpenAI has released an experimental educational framework for exploring ergonomic, lightweight multi-agent orchestration. Swarm is managed by the OpenAI Solution team, but is not intended to be used i [ ... ]



The Feds Want Us To Move On From C/C++
13/11/2024

The clamour for safe programming languages seems to be growing and becoming official. We have known for a while that C and C++ are dangerous languages so why has it become such an issue now and is it  [ ... ]


More News

espbook

 

Comments




or email your comment to: comments@i-programmer.info