Smarter Data Discovery using Lumira 1.31
Data discovery is a user-driven process of searching for patterns or specific items in a data set. Data discovery applications use visual tools such as geographical maps, pivot-tables, and heat-maps to make the process of finding patterns or specific items rapid and intuitive – Wikipedia
Data visualization tools make this job easier with a simple flat file structure to prepare data and drag drop functionality to build visualizations. But Lumira has two other additional functionalities to make smarter data discovery,
1) Related Visualizations
This option is available in the Visualize room next to the chart builder. Based on the underlying dataset, Lumira suggests a bunch of charts from a combination of dimensions and measures. This can be selected and further modified if required.
This gives us pretty good options of column charts, stacked column charts, scatter plots, etc.
2) Top Influencers
The predictive capabilities in Lumira can also help you find influencers (dimensions) for a particular measure. This can be accessed by selecting the Related Visualization option and then the Measure that needs to be influenced from the left panel.
When you Run the Analysis, we can see the list of Top Influencers and the other chart suggestions.
We can find out the correlation of the measure with each of the top dimensions. Correlation refers to the quantity measuring the extent of interdependence of variable quantities. The top influencer is only for reference and cannot be used as a visualization in the storyboards.
Certain condition to take note while using Influencers are,