I am still a beginner and I am trying to understand the time series dataset: “M4 comepition dataset” .
The M4 dataset consists of time series of yearly, quarterly, monthly and other (weekly, daily and hourly) data, from various domain, which are divided into training and test sets . Here is the composition of the M4 dataset: the number of TS based on their sampling frequency and type:
M4 dataset is supposed to be univariate dataset, but if I see in the .csv files that are available for download: https://github.com/Mcompetitions/M4-methods/tree/master/Dataset/Train , has Multiple columns too , which should not be the case for the univariate dataset as for my understanding.
I am not understanding what exactly do the rows and column mean in this dataset? I also tried going through the info file given at https://github.com/Mcompetitions/M4-methods/blob/master/Dataset/M4-info.csv but still could not draw any conclusion.
I tried looking at other place and forums too but I could not find any explaination,Can anyone help me with understanding this dataset?