search

goodboychan / goodboychan.github.io

jupyter blog
Apache License 2.0
129 stars 115 forks source link

Work with Multiple Time Series | Chan`s Jupyter #52

Closed utterances-bot closed 3 years ago

utterances-bot commented 3 years ago

Work with Multiple Time Series | Chan`s Jupyter

In the field of Data Science, it is common to be involved in projects where multiple time series need to be studied simultaneously. In this chapter, we will show you how to plot multiple time series at once, and how to discover and describe relationships between multiple time series. This is the Summary of lecture “Visualizing Time-Series data in Python”, via datacamp.

https://goodboychan.github.io/chans_jupyter/python/datacamp/time_series_analysis/visualization/2020/06/13/02-Work-with-Multiple-Time-Series.html

HumanFact commented 3 years ago

When dealing with the relationships within time series, neither pearson's nor spearman correlation coefficients works. You have to go check with series' stationarity and then apply augmented dickey fuller test.

goodboychan commented 3 years ago

Hi,

Thanks for the comment. Your comments is right. pearson and spearman correlation approach is not appropriate for time series comparison. I just want to show the result whether those approach works on. And Augmented dickey fuller test maybe reasonable approach for data with seasonality. If you interest, please check this another post, [link].(https://goodboychan.github.io/chans_jupyter/python/datacamp/time_series_analysis/2020/06/15/01-ARMA-Models.html)

Thanks!