Plotshop

Abstract

We introduce an interactive system to design 2D data sets on a scatter plot. 2D data sets are often used to obtain an intuition about the behavior of machine learning techniques or statistical modeling techniques . A traditional method for creating a data set is to use textural commands, such as generating a normal distribution with specific parameters. However, it is difficult to create an arbitrary data distribution from scratch or to edit an existing one using these methods. We therefore developed an interactive system for creating and editing a 2D data distribution on a scatter plot by using a graphics user interface. It also allows the user to observe the response of a data analysis method while the user is editing a distribution. We show that the proposed interface is effective for understanding characteristics of data analysis methods.