Homework 4

From this page you can find a problem called "SensIT Vehicle (combined)." We consider the scaled data sets (training and testing).

In this homework, we would like to check the performance of 1-nearest neighbor. You then try to find some R packages for nearest neighbor.

Since this data set is in a "sparse format," you may need to use read.matrix.csr of the R e1071 package to read it.

If the nearest neighbor code you found is inefficient, you may need to find others. If somehow packages in R are not fast enough, you can work on a smaller subset.

Write a short report (<= 2 pages in English) to show what you find.


Last modified: Sun Feb 25 16:27:57 CST 2007