Author(s): Kirill Lepchenkov

Originally published on Towards AI.

For those doing exploratory data analysis on tabular data: there is Sketch, a code-writing assistant that seamlessly integrates bits of your dataframes into prompts
I’ve made this map using Sketch, Jupyter, Geopandas, and Keplergl

For us, data professionals, AI advancements bring new workflows and enhance our toolset. In this article I’ll share my experience with using one of these new tools to solve practical problems.

Sketch is a PyPI package that brings the power of OpenAI API to the traditional exploratory data analysis with Pandas and Jupyter. According to the official documentation, Sketch is an AI code-writing assistant for pandas users that understands the context of your data, greatly improving the relevance of suggestions. Sketch is usable in seconds and doesn’t require adding a plugin to your IDE.

Sketch is an AI code-writing assistant for pandas users that understands the context of your data, greatly improving…

github.com

Sketch can be installed in seconds and does not require messing up with API keys or a complicated setup procedure. Just install it via pip install sketch and run import to plug it in.

import pandas as pdimport geopandas as gpdimport sketch

In a nutshell, Sketch augments your prompts with the context of the actual dataframe, greatly improving the quality of responses. I’ve tried it and I’m really impressed.

df.sketch.ask() syntax is a way to use the question-answer system on Sketch. To test if it… Read the full blog for free on Medium.

Join thousands of data leaders on the AI newsletter. Join over 80,000 subscribers and keep up to date with the latest developments in AI. From research to projects and ideas. If you are building an AI startup, an AI-related product, or a service, we invite you to consider becoming a sponsor.

Published via Towards AI