In this chapter, the time-series examples we used were annual sunspot cycles data, sales data, and beer production. We learned that it's common to try to derive a relationship between a value and another data point or a combination of data points with a fixed number of periods in the past in the same time series. We learned how moving averages convert the random variation trend into a smooth trend using a window size. We learned how the DataFrame.rolling() function provides win_type string parameters for different window functions. Cointegration is similar to correlation and is a metric to define the relatedness of two time series. We also focused on STL decomposition, autocorrelation, autoregression, the ARMA model, Fourier analysis, and spectral analysis filtering.
The next chapter, Chapter 9, Supervised Learning – Regression Analysis, will focus on the important topics of regression analysis and logistic regression in Python. The chapter starts with multiple linear...