This repository stores all the lab notes for implementing the methods covered in "Time Series Analysis (TSA)" taught by Patrick PUN Chi Seng (https://personal.ntu.edu.sg/cspun/).

"tsa-I.ipynb" refers mainly to the resources (Stationary Time Series) in "Forecasting: Principles and Practice" (3rd Ed), OTexts: Melbourne, Australia by Hyndman R. J. and Athanasopoulos G. (2021) - https://otexts.com/fpp2/ with conversion into Python (from R) programming language.

"tsa-II.ipynb" refers mainly to the resources (Stationary Time Series) in "Time Series: Applications to Finance with R and S-Plus" (2nd Ed), Wiley, New York by Chan N. H. (2010) - https://www.sta.cuhk.edu.hk/nhchan/TSBook2nd/book2.html with conversion into Python (from R) programming language.

"tsa-III.ipynb" refers mainly to the resources (Nonstationary Time Series) in "Time Series: Applications to Finance with R and S-Plus" (2nd Ed), Wiley, New York by Chan N. H. (2010) - https://www.sta.cuhk.edu.hk/nhchan/TSBook2nd/book2.html with conversion into Python (from R) programming language.

"dp-I.ipynb" covers the feed-forward neural networks (FFNN) with reference to "An Introduction to Statistical Learning with Applications in R/Python" (2nd Ed), Springer by James G., Witten D., Hastie T., and Tibshirani R. (2021) - https://www.statlearning.com/.

"dp-II.ipynb" covers the long short-term memory (LSTM) with reference to "An Introduction to Statistical Learning with Applications in R/Python" (2nd Ed), Springer by James G., Witten D., Hastie T., and Tibshirani R. (2021) - https://www.statlearning.com/.

"build_timeseries.py" is used to generate the datasets used in our group project.