Analyzing a time series dataset

To see how to perform a seasonality removal operation on a time series, we will use a dataset on monthly milk production (pounds per cow; January 1962 – December 1975). Here is some useful information about this dataset:

  • Units: Pounds per cow
  • Dataset metrics: 168 fact values in one time series
  • Time granularity: Month
  • Time range: January 1962 – December 1975
  • Source: Time Series Data Library

The Time Series Data Library (TSDL) was created by Rob Hyndman, a professor of statistics at Monash University, Australia.

The data is available in a .csv file named milk-production-pounds.csv. To start, let's see how to import the data into Python and then how to display it to identify the possible presence of seasonality. ...

Get Hands-On Machine Learning on Google Cloud Platform now with the O’Reilly learning platform.

O’Reilly members experience books, live events, courses curated by job role, and more from O’Reilly and nearly 200 top publishers.