Using trained models in Power Query
As you already saw in Chapter 4, Importing Unhandled Data Objects, you used to share objects that were the result of complex, time-consuming processing (thus also a machine learning model) in a serialized format specific to the language you were using. At that point, it was very simple to deserialize the file and get the model ready to be used in Power Query to predict the target variable of new observations. However, it is important to know the dependencies needed by the scoring function (which gets the new observations as input and returns the predictions), since they are closely related to how the training of the model took place. For this reason, we recommend the following:
Important Note
When you need to use a serialized machine learning model provided by a third party, make sure that whoever developed it also provides you with a working scoring function in order to avoid unnecessary headaches when predicting target values for unknown...
