All files uploaded to a folder have to have the same header. The folder represents a data set, possibly composed of several files. For example, you might train with a data set of a year’s worth of data. The data for that training could be in one file, containing entries across the entire year, or in many files where each file contains entries for a specific month. The entire folder will be treated as a single data set. An advantage of this approach is that you can modify your data set based on the files that you manage in the folder. For example, with a monthly file approach you can retrain with more recent data by deleting older monthly files and adding the latest monthly data.