Nothing
test_that("a genuinely compressed sparse sketch recovers a sparse low-rank matrix", {
# Disjoint feature blocks and pairs of opposite observations give an
# exactly rank-four matrix with 1.67% nonzeros. The seven sketch rows are
# far fewer than min(n, p) = 72, so this cannot pass via a full-width sketch.
n <- 120L
p <- 72L
k <- 4L
left <- matrix(0, n, k)
right <- matrix(0, p, k)
for (j in seq_len(k)) {
left[(2L * j - 1L):(2L * j), j] <- c(1, -1) / sqrt(2)
rows <- seq.int((j - 1L) * 18L + 1L, j * 18L)
right[rows, j] <- seq_along(rows) / sqrt(sum(seq_along(rows)^2))
}
X <- left %*% diag(c(30, 15, 7, 3)) %*% t(right)
sparse <- Matrix::Matrix(X, sparse = TRUE)
for (center in c(FALSE, TRUE)) for (scale in c(FALSE, TRUE)) {
# Base R supplies the explicit reference, independently of either
# sparsepca preprocessing path. Every column has a nonzero scale.
target <- base::scale(X, center = center, scale = scale)
for (q in c(0, 2)) {
set.seed(21)
fit <- rspca(sparse, k, alpha = 0, beta = 0, center = center,
scale = scale, o = 3, q = q, verbose = FALSE)
reconstruction <- tcrossprod(fit$scores, fit$transform)
expect_lt(norm(target - reconstruction, "F") / norm(target, "F"), 1e-10)
expect_equal(crossprod(fit$transform), diag(k), tolerance = 1e-10)
expect_equal(fit$var, sum(target^2) / (n - 1), tolerance = 1e-12)
}
}
})
test_that("power iterations improve a compressed sparse fit toward the spectral tail", {
n <- 120L
p <- 72L
k <- 4L
spectrum <- exp(seq(log(30), log(0.03), length.out = p))
sparse <- Matrix::sparseMatrix(i = seq_len(p), j = seq_len(p),
x = spectrum, dims = c(n, p))
for (center in c(FALSE, TRUE)) {
# This full-rank input cannot be reconstructed exactly at rank four.
# The SVD tail gives the optimal attainable Frobenius error, including
# the effect of centering when that changes the known diagonal spectrum.
target <- base::scale(as.matrix(sparse), center = center, scale = FALSE)
singular <- svd(target, nu = 0, nv = 0)$d
optimal_error <- sum(singular[-seq_len(k)]^2)
for (seed in c(8, 21, 235)) {
errors <- vapply(c(0, 4), function(q) {
set.seed(seed)
fit <- rspca(sparse, k, alpha = 0, beta = 0, center = center,
o = 3, q = q, verbose = FALSE)
sum((target - tcrossprod(fit$scores, fit$transform))^2)
}, numeric(1))
# Observed ratios were <= 1.011 across these seeds; 1.03 leaves a
# margin for numerical backends. No basis or sign is prescribed.
expect_lte(errors[2], 1.03 * optimal_error)
expect_gte(errors[2], (1 - 1e-10) * optimal_error)
expect_lt(errors[2], 0.99 * errors[1])
}
}
})
test_that("mixed sparse offsets and scales match an explicit independent operator", {
n <- 40L
X <- cbind(full = 1e12 + rep(c(-3, -1, 1, 3), length.out = n),
incomplete = c(0, 1e12 + seq_len(n - 1L)),
sparse = rep(c(0, -2, 0, 3), length.out = n),
tiny = rep(c(0, -1, 0, 1), length.out = n) * 1e-10,
zero = rep(0, n))
sparse <- Matrix::Matrix(X, sparse = TRUE)
original <- sparse
Y <- matrix(sin(seq_len(n * 3L)), n, 3L)
for (center in c(FALSE, TRUE)) for (scale in c(FALSE, TRUE)) {
target <- base::scale(X, center = center, scale = FALSE)
scales <- vapply(seq_len(ncol(X)), function(j) {
sqrt(sum(target[, j]^2) / (n - 1L))
}, numeric(1))
# Preserve the documented small-scale convention, including zero columns.
scales[scales < 1e-8] <- 1
if (scale) target <- sweep(target, 2, scales, "/")
prepared <- sparsepca:::.spca_preprocess(sparse, center, scale, sparse = TRUE)
forward <- prepared$forward(diag(ncol(X)))
adjoint <- prepared$adjoint(Y)
reference_adjoint <- crossprod(target, Y)
# Compare columns separately: the large incomplete column must not hide
# cancellation errors in the fully stored, explicitly centered column.
for (j in seq_len(ncol(X))) {
expect_equal(unname(forward[, j]), unname(target[, j]), tolerance = 1e-12)
expect_equal(unname(adjoint[j, ]), unname(reference_adjoint[j, ]),
tolerance = 1e-12)
}
expect_equal(prepared$energy, sum(target^2), tolerance = 1e-12)
}
expect_identical(sparse, original)
})
Any scripts or data that you put into this service are public.
Add the following code to your website.
For more information on customizing the embed code, read Embedding Snippets.