I am currently trying to build a bivariate density model with a large data set. (matrix size - 400000+ rows 2 columns, there are a lot of repeats in the matrix)
Sample Data
X Y
531203.5 182832.1
525208.1 179391.9
532985.8 182001.6
530437.8 182912.0
528051.0 178742.0
528858.4 181542.9
I am aware of the package 'ks' and its function 'kde', but it only suitable for data size of less than 1000 rows, it took too long to compute on my data (30min +)
Should I look into mutlithreading packages such as snow? (I am using a window laptop)
Any tips and advice would be appreciated!
Andrew
