Summary
In this chapter, we have worked on the exploration of structured, semi-structured, and unstructured data in the Power Query Editor. We have imported text and images and have made sure that Power BI knows how to interpret this data so that we can later use AI features to extract insights from this rich data. We have looked at the three common problems with data when it is used for AI: missing data, bias, and outliers. We have discussed the different considerations for each of these problems where it is important to understand what causes them and whether they will cause problems for what you want to do with your data. We also covered how we can fix missing data, bias, and outliers, if needed, to make sure we have a representative dataset that will result in building accurate models.
In the next chapter, we will discover the first type of model we can work with in Power BI: forecasting.
