Easy Bake Data

Easy Bake Data is an on-premise, web-based data preprocessing tool that allows users to have their datasets cleaned up without writing a single line of code. The user just needs to bring in the data, choose what standard data preprocessing steps to perform, and the application will handle the rest. Target users are internal State Farm employees who do not have technical backgrounds, but still are interested in having the data prepared in a way that is ready to be consumed. Users who would like to have a quick scan through the data to find anomalies may also find this tool beneficial.

Feature implemented:

  • Log in screen
  • Upload structural data (support .csv or .xlsx)
  • Preview the data (backed by pandas-profiling) and choose standard data preprocessing steps (e.g. standardization, filling missing values, one-hot encoding)
  • Review the processed data (backed by pandas-profiling) and download

I led a team of 8 and implemented the preprocessing page. Our hack won 2021 Fan Favorite.

Rose Lin
Rose Lin
Data Scientist @ State Farm

Data Wrangler & Storyteller.

Related