#read in the data
A = mmread('data/yelpData.mtx');

#extract the ratings of each review
ratings = full(A(:,1));
A(:,1) = [];

#split into test/train, should replace with better julia way of doing it
data = randperm(numData);
ind = floor(numData*0.7);
training = data(1:ind);
test = data(ind+1:end);
trainReviews = A(training,:);
trainRatings = ratings(training,:);
testReviews = A(test,:);
testRatings = ratings(test,:);

#pick some value of lambda i think 100 should work
lambda = 100

#CVX fails here, i used matrix stuffing in actual code, but lsq should be better
cvx_begin
variables w(1000) v(1)
minimize sum_square(trainReviews*w + v - trainRatings) + lambda*sum_square(w)
cvx_end

#calculate root mean squared error for test/train
yhat = trainReviews*w + v;
trainRMS = sqrt(mean((trainRatings - yhat).^2));

yhat2 = testReviews*w + v;
testRMS = sqrt(mean((testRatings - yhat2).^2));