Computation time for auto-correlation: Bruteforce is O(n^2) and FFT is O(n.logn)
http://stackoverflow.com/questions/12239096/computing-autocorrelation-with-fft-using-jtransforms-library
https://mvnrepository.com/artifact/edu.emory.mathcs/JTransforms/2.4
- JTransforms is the first, open source, multithreaded FFT library written in pure Java. Currently, four types of transforms are available: Discrete Fourier Transform (DFT), Discrete Cosine Transform (DCT), Discrete Sine Transform (DST) and Discrete Hartley Transform (DHT). The code is derived from General Purpose FFT Package written by Takuya Ooura and from Java FFTPack written by Baoshe Zhang.
http://projecteuclid.org/euclid.ejs/1427990071
- High-dimensional autocovariance matrices and optimal linear prediction
ACF lag calculation
- http://stackoverflow.com/questions/35705001/r-time-series-whats-the-lag-unit-for-autocorrelation-function-acf?rq=1
Good explanation on ACF and its meaning
- http://www.itl.nist.gov/div898/handbook/eda/section3/eda35c.htm
Interpreting acf
- http://stats.stackexchange.com/questions/140673/interpreting-acf-and-pacf-plot
stats:acf source code
- https://github.com/SurajGupta/r-source/blob/master/src/library/stats/R/acf.R
microbenchmark for measuring time
- http://stackoverflow.com/questions/20689650/how-to-append-rows-to-an-r-data-frame
microbenchmark
from the "microbenchmark" package will give us more comprehensive insight thansystem.time
:
lapply
- https://nicercode.github.io/guides/repeating-things/
댓글 없음:
댓글 쓰기