Feature Engineering for Time Series Analysis in Spark
In this video we will take a time series crypto currency data and will create a new feature which is 3 time steps ahead. This type of creating a label can be done in cases such as say you want to predict what the future price will be.
The data can be downloaded from here: https://www.kaggle.com/sudalairajkuma...
Code for this can be found here: https://github.com/infinite-Joy/datah....