Now we've made some observations when looking at the time-series data which is currently recorded every minute. As you might tell, the data does look a little noisy at times and we might want to smooth this out so we don't have to look at as much data, but still retain the overall trends. This is where we are introduced to a technique known as 'Upsampling'. Upsampling means you wish to aggregate the data at a higher frequency (i.e. Instead of every 1 minute, we might want the data to be sampled every 5 minutes instead) Now we're going to combine this with another technique known as a rolling mean / rolling standard deviation. When dealing with time series data, if we want to remove some of the 'noisiness' of the data, we can apply a rolling mean or rolling standard deviation transformation. Earlier we covered the Mean and the Standard Deviation. The mean let's us know what the average is with the Standard Deviation letting us know how much 'dispersion' we are seeing over a data series. A rolling mean and rolling deviation is essentially a window function that enables us to better understand what the dispersion of the