Data Cleaning - Filter

Learn how to filter numbers, words, and just about anything in order to reduce bias in your dataset. Filtering through data is a very common transformation; it takes in a conditional and checks through all the data to keep only the data that meets the condition. By filtering you can improve your machine learning models by training on a specific subset of data to specialize the model, remove incorrect data and outliers, or prune biased features. To start off with what filtering does, it takes in a pile of data and turns it into something smaller and (hopefully) easier to work with. When you create a filter, you start from what will stay, not what will go.