C++ mat::empty方法代码示例

double mse(const mat & A, const mat & W, const mat & H, const mat & W1, const mat & H2)
{
	// compute mean square error of A and fixed A
	const int k = W.n_cols - H2.n_cols;

	mat Adiff = A;
	Adiff -= W.cols(0, k-1) * H.cols(0, k-1).t();
	if (!W1.empty())
		Adiff -= W1*H.cols(k, H.n_cols-1).t();
	if (!H2.empty())
		Adiff -= W.cols(k, W.n_cols-1)*H2.t();

	if (A.is_finite())
		return mean(mean(square(Adiff)));
	else
		return mean(square(Adiff.elem(find_finite(Adiff))));
}

inline void update_WtW(mat & WtW, const mat & W, const mat & W1, const mat & H2)
{
	// compute WtW = (W[:, 0:k-1], W1)^T (W[:, 0:k-1], W1)
	if (H2.empty())
		update_WtW(WtW, W, W1);
	else
	{
		int k = W.n_cols - H2.n_cols;
		update_WtW(WtW, W.cols(0, k-1), W1);
	}
}

inline void update_WtA(mat & WtA, const mat & W, const mat & W1, const mat & H2, const mat & A)
{
	// compute WtA = (W[:, 0:k-1], W1)^T (A - W[, k:end] H2^T)
	if (H2.empty())
		update_WtA(WtA, W, W1, A);
	else
	{
		int k = W.n_cols - H2.n_cols;
		//std::cout << "1.3" << std::endl;
		//A.print("A = ");
		//(W.cols(k, W.n_cols-1) * H2.t()).print("W[, k:] = ");
		update_WtA(WtA, W.cols(0, k-1), W1, A - W.cols(k, W.n_cols-1) * H2.t());
	}
}

//[[Rcpp::export]]
Rcpp::List nnmf(const mat & A, const unsigned int k, mat W, mat H, umat Wm, umat Hm,
	const vec & alpha, const vec & beta, const unsigned int max_iter, const double rel_tol, 
	const int n_threads, const int verbose, const bool show_warning, const unsigned int inner_max_iter, 
	const double inner_rel_tol, const int method, unsigned int trace)
{
	/******************************************************************************************************
	 *              Non-negative Matrix Factorization(NNMF) using alternating scheme
	 *              ----------------------------------------------------------------
	 * Description:
	 * 	Decompose matrix A such that
	 * 		A = W H
	 * Arguments:
	 * 	A              : Matrix to be decomposed
	 * 	W, H           : Initial matrices of W and H, where ncol(W) = nrow(H) = k. # of rows/columns of W/H could be 0
	 * 	Wm, Hm         : Masks of W and H, s.t. masked entries are no-updated and fixed to initial values
	 * 	alpha          : [L2, angle, L1] regularization on W (non-masked entries)
	 * 	beta           : [L2, angle, L1] regularization on H (non-masked entries)
	 * 	max_iter       : Maximum number of iteration
	 * 	rel_tol        : Relative tolerance between two successive iterations, = |e2-e1|/avg(e1, e2)
	 * 	n_threads      : Number of threads (openMP)
	 * 	verbose        : Either 0 = no any tracking, 1 == progression bar, 2 == print iteration info
	 * 	show_warning   : If to show warning if targeted `tol` is not reached
	 * 	inner_max_iter : Maximum number of iterations passed to each inner W or H matrix updating loop
	 * 	inner_rel_tol  : Relative tolerance passed to inner W or H matrix updating loop, = |e2-e1|/avg(e1, e2)
	 * 	method         : Integer of 1, 2, 3 or 4, which encodes methods
	 * 	               : 1 = sequential coordinate-wise minimization using square loss
	 * 	               : 2 = Lee's multiplicative update with square loss, which is re-scaled gradient descent
	 * 	               : 3 = sequentially quadratic approximated minimization with KL-divergence
	 * 	               : 4 = Lee's multiplicative update with KL-divergence, which is re-scaled gradient descent
	 * 	trace          : A positive integer, error will be checked very 'trace' iterations. Computing WH can be very expansive,
	 * 	               : so one may not want to check error A-WH every single iteration
	 * Return:
	 * 	A list (Rcpp::List) of 
	 * 		W, H          : resulting W and H matrices
	 * 		mse_error     : a vector of mean square error (divided by number of non-missings)
	 * 		mkl_error     : a vector (length = number of iterations) of mean KL-distance
	 * 		target_error  : a vector of loss (0.5*mse or mkl), plus constraints
	 * 		average_epoch : a vector of average epochs (one complete swap over W and H)
	 * Author:
	 * 	Eric Xihui Lin <[email protected]>
	 * Version:
	 * 	2015-12-11
	 ******************************************************************************************************/

	unsigned int n = A.n_rows;
	unsigned int m = A.n_cols;
	//int k = H.n_rows; // decomposition rank k
	unsigned int N_non_missing = n*m;

	if (trace < 1) trace = 1;
	unsigned int err_len = (unsigned int)std::ceil(double(max_iter)/double(trace)) + 1;
	vec mse_err(err_len), mkl_err(err_len), terr(err_len), ave_epoch(err_len);

	// check progression
	bool show_progress = false;
	if (verbose == 1) show_progress = true;
	Progress prgrss(max_iter, show_progress);

	double rel_err = rel_tol + 1;
	double terr_last = 1e99;
	uvec non_missing;
	bool any_missing = !A.is_finite();
	if (any_missing) 
	{
		non_missing = find_finite(A);
		N_non_missing = non_missing.n_elem;
		mkl_err.fill(mean((A.elem(non_missing)+TINY_NUM) % log(A.elem(non_missing)+TINY_NUM) - A.elem(non_missing)));
	}
	else
		mkl_err.fill(mean(mean((A+TINY_NUM) % log(A+TINY_NUM) - A))); // fixed part in KL-dist, mean(A log(A) - A)

	if (Wm.empty())
		Wm.resize(0, n);
	else
		inplace_trans(Wm);
	if (Hm.empty())
		Hm.resize(0, m);

	if (W.empty())
	{
		W.randu(k, n);
		W *= 0.01;
		if (!Wm.empty())
			W.elem(find(Wm > 0)).fill(0.0);
	}
	else
		inplace_trans(W);

	if (H.empty())
	{
		H.randu(k, m);
		H *= 0.01;
		if (!Hm.empty())
			H.elem(find(Hm > 0)).fill(0.0);
	}

	if (verbose == 2)
	{
		Rprintf("\n%10s | %10s | %10s | %10s | %10s\n", "Iteration", "MSE", "MKL", "Target", "Rel. Err.");
//.........这里部分代码省略.........

mat nnls_solver_with_missing(const mat & A, const mat & W, const mat & W1, const mat & H2, const umat & mask, 
	const double & eta, const double & beta, int max_iter, double rel_tol, int n_threads)
{
	// A = [W, W1, W2] [H, H1, H2]^T.
	// Where A may have missing values
	// Note that here in the input W = [W, W2]
	// compute x = [H, H1]^T given W, W2
	// A0 = W2*H2 is empty when H2 is empty (no partial info in H)
	// Return: x = [H, H1]

	int n = A.n_rows, m = A.n_cols;
	int k = W.n_cols - H2.n_cols;
	int kW = W1.n_cols;
	int nH = k+kW;

	mat x(nH, m, fill::zeros);

	if (n_threads < 0) n_threads = 0;
	bool is_masked = !mask.empty();

	#pragma omp parallel for num_threads(n_threads) schedule(dynamic)
	for (int j = 0; j < m; j++)
	{
		// break if all entries of col_j are masked
		if (is_masked && arma::all(mask.col(j))) 
			continue;
		
		uvec non_missing = find_finite(A.col(j));
		mat WtW(nH, nH); // WtW
		update_WtW(WtW, W.rows(non_missing), W1.rows(non_missing), H2);
		if (beta > 0) WtW += beta;
		if (eta > 0) WtW.diag() += eta;

		mat mu(nH, 1); // -WtA
		uvec jv(1);
		jv(0) = j;
		//non_missing.t().print("non_missing = ");
		//std::cout << "1.1" << std::endl;
		if (H2.empty())
			update_WtA(mu, W.rows(non_missing), W1.rows(non_missing), H2, A.submat(non_missing, jv));
		else
			update_WtA(mu, W.rows(non_missing), W1.rows(non_missing), H2.rows(j, j), A.submat(non_missing, jv));
		//std::cout << "1.5" << std::endl;

		vec x0(nH);
		double tmp;
		int i = 0;
		double err1, err2 = 9999;
		do {
			x0 = x.col(j);
			err1 = err2;
			err2 = 0;
			for (int l = 0; l < nH; l++)
			{
				if (is_masked && mask(l,j) > 0) continue;
				tmp = x(l,j) - mu(l,0) / WtW(l,l);
				if (tmp < 0) tmp = 0;
				if (tmp != x(l,j))
				{
					mu.col(0) += (tmp - x(l,j)) * WtW.col(l);
				}
				x(l,j) = tmp;
				tmp = std::abs(x(l,j) - x0(l));
				if (tmp > err2) err2 = tmp;
			}
		} while(++i < max_iter && std::abs(err1 - err2) / (err1 + 1e-9) > rel_tol);
	}
	return x;
}