// Predict the rating for a group of user/item combinations.
void CF::Predict(const arma::Mat<size_t>& combinations,
arma::vec& predictions) const
{
// First, for nearest neighbor search, stretch the H matrix.
arma::mat l = arma::chol(w.t() * w);
arma::mat stretchedH = l * h; // Due to the Armadillo API, l is L^T.
// Now, we must determine those query indices we need to find the nearest
// neighbors for. This is easiest if we just sort the combinations matrix.
arma::Mat<size_t> sortedCombinations(combinations.n_rows,
combinations.n_cols);
arma::uvec ordering = arma::sort_index(combinations.row(0).t());
for (size_t i = 0; i < ordering.n_elem; ++i)
sortedCombinations.col(i) = combinations.col(ordering[i]);
// Now, we have to get the list of unique users we will be searching for.
arma::Col<size_t> users = arma::unique(combinations.row(0).t());
// Assemble our query matrix from the stretchedH matrix.
arma::mat queries(stretchedH.n_rows, users.n_elem);
for (size_t i = 0; i < queries.n_cols; ++i)
queries.col(i) = stretchedH.col(users[i]);
// Now calculate the neighborhood of these users.
neighbor::KNN a(stretchedH);
arma::mat distances;
arma::Mat<size_t> neighborhood;
a.Search(queries, numUsersForSimilarity, neighborhood, distances);
// Now that we have the neighborhoods we need, calculate the predictions.
predictions.set_size(combinations.n_cols);
size_t user = 0; // Cumulative user count, because we are doing it in order.
for (size_t i = 0; i < sortedCombinations.n_cols; ++i)
{
// Could this be made faster by calculating dot products for multiple items
// at once?
double rating = 0.0;
// Map the combination's user to the user ID used for kNN.
while (users[user] < sortedCombinations(0, i))
++user;
for (size_t j = 0; j < neighborhood.n_rows; ++j)
rating += arma::as_scalar(w.row(sortedCombinations(1, i)) *
h.col(neighborhood(j, user)));
rating /= neighborhood.n_rows;
predictions(ordering[i]) = rating;
}
}
std::vector<double> extract_row_vector(const arma::Mat<double>& data, long index) {
if (index<0 || index >= long(data.n_rows))
throw std::range_error(join("Index out of range: ", index));
const arma::Row<double> row(data.row(index));
const double* memptr = row.memptr();
std::vector<double> result(memptr, memptr + row.n_elem);
return std::move(result);
}
//This function is specific to a single problem
void calculateDependentVariables(const arma::Mat<std::complex<double> >& myOffsets,
const arma::Col<std::complex<double> >& myCurrentGuess,
arma::Col<std::complex<double> >& targetsCalculated)
{
//Evaluate a dependent variable for each iteration
//The arma::Col allows this to be expressed as a vector operation
for(int i = 0; i < NUMDIMENSIONS; i++)
{
targetsCalculated[i] = arma::sum(pow(myCurrentGuess.subvec(0,1) - myOffsets.row(i).subvec(0,1).t(),2.0));
targetsCalculated[i] = targetsCalculated[i] + myCurrentGuess[2]*pow(-1.0, i) - myOffsets.row(i)[2];
//std::cout << targetsCalculated[i] << std::endl;
}
//std::cout << "model evaluated *************************" << std::endl;
//std::cout << targetsCalculated << std::endl;
//std::cout << myOffsets << std::endl;
}
/**
* Given a Reber string, return a Reber string with all reachable next symbols.
*
* @param transitions The Reber transistion matrix.
* @param reber The Reber string used to generate all reachable next symbols.
* @param nextReber All reachable next symbols.
*/
void GenerateNextReber(const arma::Mat<char>& transitions,
const std::string& reber, std::string& nextReber)
{
size_t idx = 0;
for (size_t grammer = 1; grammer < reber.length(); grammer++)
{
const int grammerIdx = arma::as_scalar(arma::find(
transitions.row(idx) == reber[grammer], 1, "first"));
idx = arma::as_scalar(transitions.submat(idx, grammerIdx + 2, idx,
grammerIdx + 2)) - '0';
}
nextReber = arma::as_scalar(transitions.submat(idx, 0, idx, 0));
nextReber += arma::as_scalar(transitions.submat(idx, 1, idx, 1));
}
