getOrder3Tensor {tensorsparse}

Generate a random order-3 tensor

Description

Generate an order-3 random tensor based on tensor block model.

Usage

getOrder3Tensor(
  n,
  p,
  q,
  k = NULL,
  r = NULL,
  l = NULL,
  error = 3,
  sort = TRUE,
  sparse.percent = 0,
  center = FALSE,
  seed = NULL,
  mumin = -3,
  mumax = 3
)

Arguments

n

the dimension at mode 1

p

the dimension at mode 2

q

the dimension at mode 3

k

an positive integer, the numbers of clusters at mode 1

r

an positive integer, the numbers of clusters at mode 2

l

an positive integer, the numbers of clusters at mode 3

error

a positive numeric value, noise level

sort

if TRUE, the tensor entries belonging to the same cluster would be assumed together

sparse.percent

the proportion of zero entries based on the Gaussian tensor block model

center

if True, the data tensor would be centered to zero-mean before clustering

seed

a positive integer, used to specify the random seed

mumin

a numeric value, the lower bound of the block mean

mumax

a numeric value, the upper bound of the block mean

Value

a list

x the tensor

truthX the underlying signal tensor following block model

truthCs true cluster label assignment at mode 1

truthDs true cluster label assignment at mode 2

truthEs true cluster label assignment at mode 3

mus the block means

binaryX the 0-1 tensor (0:the mean signal = 0; 1:the mean signal != 0)

Examples

getOrder3Tensor(20,20,20,2,2,2)$x