I have a dateset which consists of a timestamp and a column for some sensor data. Because the timestamp is of very high frequency(for example every millisecond), i downsampled the data ( to every 100 millisecond) with some averaging logic. Initially the number of rows was about 50k but after downsampling it is now 900 rows.
Now, I want to understand to what degree the new dataset resembles/represents to the original dataset. I want to understand if i have missed out overall vital data by downsampling. What techniques are available in python to compare these two dataset which are of different scales?