Get the scores of PCA associated with an svd decomposition (class big_SVD).

# S3 method for big_SVD
predict(
  object,
  X = NULL,
  ind.row = rows_along(X),
  ind.col = cols_along(X),
  block.size = block_size(nrow(X)),
  ...
)

Arguments

object

A list returned by big_SVD or big_randomSVD.

X

An object of class FBM.

ind.row

An optional vector of the row indices that are used. If not specified, all rows are used. Don't use negative indices.

ind.col

An optional vector of the column indices that are used. If not specified, all columns are used. Don't use negative indices.

block.size

Maximum number of columns read at once. Default uses block_size.

...

Not used.

Value

A matrix of size \(n \times K\) where n is the number of samples corresponding to indices in ind.row and K the number of PCs computed in object. If X is not specified, this just returns the scores of the training set of object.

See also

Examples

set.seed(1) X <- big_attachExtdata() n <- nrow(X) # Using only half of the data ind <- sort(sample(n, n/2)) test <- big_SVD(X, fun.scaling = big_scale(), ind.row = ind) str(test)
#> List of 5 #> $ d : num [1:10] 178.5 114.5 91 87.1 86.3 ... #> $ u : num [1:258, 1:10] -0.1092 -0.0928 -0.0806 -0.0796 -0.1028 ... #> $ v : num [1:4542, 1:10] 0.00607 0.00739 0.02921 -0.01283 0.01473 ... #> $ center: num [1:4542] 1.34 1.63 1.51 1.64 1.09 ... #> $ scale : num [1:4542] 0.665 0.551 0.631 0.55 0.708 ... #> - attr(*, "class")= chr "big_SVD"
plot(test$u)
pca <- prcomp(X[ind, ], center = TRUE, scale. = TRUE) # same scaling all.equal(test$center, pca$center)
#> [1] TRUE
all.equal(test$scale, pca$scale)
#> [1] TRUE
# scores and loadings are the same or opposite # except for last eigenvalue which is equal to 0 # due to centering of columns scores <- test$u %*% diag(test$d) class(test)
#> [1] "big_SVD"
scores2 <- predict(test) # use this function to predict scores all.equal(scores, scores2)
#> [1] TRUE
dim(scores)
#> [1] 258 10
dim(pca$x)
#> [1] 258 258
tail(pca$sdev)
#> [1] 3.023287e+00 3.008386e+00 2.990514e+00 2.984375e+00 2.965688e+00 #> [6] 1.130391e-14
plot(scores2, pca$x[, 1:ncol(scores2)])
plot(test$v[1:100, ], pca$rotation[1:100, 1:ncol(scores2)])
# projecting on new data X2 <- sweep(sweep(X[-ind, ], 2, test$center, '-'), 2, test$scale, '/') scores.test <- X2 %*% test$v ind2 <- setdiff(rows_along(X), ind) scores.test2 <- predict(test, X, ind.row = ind2) # use this all.equal(scores.test, scores.test2)
#> [1] TRUE
scores.test3 <- predict(pca, X[-ind, ]) plot(scores.test2, scores.test3[, 1:ncol(scores.test2)])