From the course: Python for Time Series Forecasting
Join today to access over 24,800 courses taught by industry experts.
Model fit and forecast - Python Tutorial
From the course: Python for Time Series Forecasting
Model fit and forecast
- [Instructor] Let's start with loading the dataset of the passengers as usual. And in the model fit, to compute the numbers of the mathematical equation, the coefficient, we'll go inside the statsmodels.tsa.holtwinters method to import the exponential smoothing. Let's check for the parameters. Having the most important ones such as the endog, the time series, which we will have on the data frame values. There is no need to apply the log transformation in this case because the exponential smoothing can handle this data perfectly. Can capture the stationarity very well by using the parameters for the trend and the seasonal in its form. The trend, in this case, the trends will be additive because it doesn't grow over time, and the seasonal will be multiplicative as we discussed in other lessons, because the amplitude of the seasonal pattern, as we can see in the plot, is growing as we move into the future. Therefore, multiplicative on the seasonal. And finally, the seasonal periods will…
Download courses and learn on the go
Watch courses on your mobile device without an internet connection. Download courses using your iOS or Android LinkedIn Learning app.