Final answer:
Good exploratory visualizations provide a broad understanding of data, while a good explanatory visualization is focused and communicates a clear message or answer. To go from exploratory to explanatory, visuals should make use of abductive inferences and explanatory virtues, creating visuals that are simple, clear, purpose-driven, and well-labeled.
Step-by-step explanation:
A good exploratory visualization should allow you to understand the data and identify patterns, trends, and outliers. To take visualization from exploratory to explanatory, it should clearly communicate a defined message or answer specific questions. This transition involves refining the visualization to focus the audience's attention on key insights and excluding less relevant information.
Exploratory visualizations are typically used during the data analysis phase. They are used by the data analyst or scientist to understand the data and find patterns that require further exploration. This means that these visuals are often more flexible and less polished, sometimes covering a broader range of data to gain a complete understanding of the subject.
An explanatory visualization, on the other hand, is more focused. It's the end product that communicates the findings to others, typically with a specific narrative or point. Explanatory visuals often use abductive inferences, incorporating explanatory virtues such as being simple, conservative, and having depth, to make strong arguments about the data.
In conclusion, good abductive inferences and application of explanatory virtues can help refine an exploratory visual into an effective explanatory one.