Abstract: A method provides visual analysis of datasets. The method is performed at a computer system. A user selects a data source. In response, the system presents a natural language interface for analysis of data in the data source and presents a map data visualization within the graphical user interface for selecting geospatial data points from the data source. In response to receiving a first user input to select a first set of one or more geographic regions, the system calculates the similarity between the first set of one or more geographic regions and a second set of one or more geographic regions, based on a range of socio-economic, demographic, and/or geographic data fields from the data source, using one or more statistical techniques (e.g., Jensen-Shannon Divergence (JSD)). The system then updates and displays the map data visualization according to the calculated similarity.

Abstract: A method provides visual analysis of datasets. The method is performed at a computer system. A user selects a data source. In response, the system presents a natural language interface for analysis of data in the data source and presents a map data visualization within the graphical user interface for selecting geospatial data points from the data source. In response to receiving a first user input to select a first set of one or more geographic regions, the system calculates the similarity between the first set of one or more geographic regions and a second set of one or more geographic regions, based on a range of socio-economic, demographic, and/or geographic data fields from the data source, using one or more statistical techniques (e.g., Jensen-Shannon Divergence (JSD)). The system then updates and displays the map data visualization according to the calculated similarity.