DESCRIPTION

Students:  This is a group quiz.  You are allowed to talk to your
teammates (but no one else), use the Internet and so on.

To get credit, you MUST be logged in under an e-mail address of the form

ajones@ucdavis.edu_jsmith@ucdavis.edu_gyu@ucdavis.edu

where the individual components must EXACTLY MATCH what you have been using
in the quizzes.

QUESTION -ext .R -run 'Rscript omsi_answer1.R'

(100 pts, code) In this problem you will implement the approach
described in Sec. 4.5.2.3 in the revised book, Forming Neighborhoods
Using Matrix Factorization.  The call form will be

predict.knnMF(recoOut,newCase,k=5)

where recoOut is a return value from trainReco(); newCase is a single
case of the form (userID,itemID); and k is the number of neighbors.
Both the user and item are assumed to be in the original data.  
Covariates and item categories will NOT be used.


predict.knnMF <- function(recoOut,newCase,k=5)
{



}

library(rectools)
load('~/ML100K')
ud <- udata[,1:3]
set.seed(9999)  # important!
z <- trainReco(ud,nmf=T)
print(predict.knnMF(z,c(5,12)))