Data2Vis: Automatic Generation of Data Visualizations Using Sequence-to-Sequence Recurrent Neural Networks

04/09/2018
by   Victor Dibia, et al.
0

Rapidly creating effective visualizations using expressive grammars is challenging for users who have limited time and limited skills in statistics and data visualization. Even high-level, dedicated visualization tools often require users to manually select among data attributes, decide which transformations to apply, and specify mappings between visual encoding variables and raw or transformed attributes. In this paper, we introduce Data2Vis, a neural translation model, for automatically generating visualizations from given datasets. We formulate visualization generation as a sequence to sequence translation problem where data specification is mapped to a visualization specification in a declarative language (Vega-Lite). To this end, we train a multilayered Long Short-Term Memory (LSTM) model with attention on a corpus of visualization specifications. Qualitative results show that our model learns the vocabulary and syntax for a valid visualization specification, appropriate transformations (count, bins, mean) and how to use common data selection patterns that occur within data visualizations. Our model generates visualizations that are comparable to manually-created visualizations in a fraction of the time, with potential to learn more complex visualization strategies at scale.

READ FULL TEXT

page 4

page 6

page 8

research
12/28/2022

VegaProf: Profiling Vega Visualizations

Vega is a popular domain-specific language (DSL) for visualization speci...
research
12/13/2014

A Canonical Representation of Data-Linear Visualization Algorithms

We introduce linear-state dataflows, a canonical model for a large set o...
research
08/06/2021

Learning Objectives, Insights, and Assessments: How Specification Formats Impact Design

Despite the ubiquity of communicative visualizations, specifying communi...
research
08/14/2018

VizML: A Machine Learning Approach to Visualization Recommendation

Data visualization should be accessible for all analysts with data, not ...
research
07/29/2020

Advancing Visual Specification of Code Requirements for Graphs

Researchers in the humanities are among the many who are now exploring t...
research
01/18/2022

Demonstration of VegaPlus: Optimizing Declarative Visualization Languages

While many visualization specification languages are user-friendly, they...
research
01/08/2020

Surfacing Visualization Mirages

Dirty data and deceptive design practices can undermine, invert, or inva...

Please sign up or login with your details

Forgot password? Click here to reset