From the course: Python for Time Series Forecasting

Unlock this course with a free trial

Join today to access over 25,300 courses taught by industry experts.

ACF and PACF

ACF and PACF - Python Tutorial

From the course: Python for Time Series Forecasting

Start my 1-month free trial Buy for my team

ACF and PACF

“

- [Instructor] To configure the p and q parameters in the ARIMA model, we visualize the partial autocorrelation function and the autocorrelation function to determine the autoregressive and moving average components. The ultimate goal is to establish which are the best numbers for the ARIMA model order. So from statsmodels in the graphics.tsaplots, we will import the plot_acf, and also the plot_pacf, the partial. First the partial, which is the autoregressive part, in the parameters, they ask for the x, which is the series. Remember that it must be the differentiated one, values_diff, we execute, and then we see the plot, which is being duplicated. To keep only one, let's put a semicolon, and there we have it. Now the same for the autocorrelation function, which is plot_acf, and the differentiated values. And then we see the other plot, which is very similar to the partial. Now, let me tell you that this interpretation is very subjective because it can go in many directions. For…

Contents