This function print the annotations of all variables used in this package.
readme()
A readme message will print on screen by default and explain the global variables used in this package, including:
CHECK |
convergent checking |
CLASS.spmd |
true id of each data, a vector of length N.spmd and has values from 1 to K |
COMM.RANK |
rank of current processor, obtained
from
comm.rank of pbdMPI |
COMM.SIZE |
total processors in MPI world,
obtained from
comm.size of pbdMPI |
CONTROL |
controls for EM iterations |
PARAM |
set or parameters |
SAVE.param |
(debug only) save parameters for every iterations |
SAVE.iter |
(debug only) save computing time for every iterations |
U.spmd |
temporary storage for density |
W.spmd |
temporary storage for
eta * density |
W.spmd.rowSums |
temporary storage for rowSums
of W.spmd |
X.spmd |
generated data set with dimension
with dimension
N.spmd * p |
Z.colSums |
temporary storage for rowSums
of Z.spmd |
Z.spmd |
posterior probabilities |
Each variable may contain several elements if it is a list, some variables
are used for temporary storages in order to optimize computing, and some
variables are used for constant variables. These variables may be restricted,
and only generated by the function set.global
.
One can access these variables via the global environment .pmclustEnv
such as .pmclustEnv$CONTROL
.
This package is optimized in the way by pre-specifying several global
variables in .pmclustEnv
.
These variables will be overwrote by EM algorithms. Users should
use these names to access the results and utilize them with cautions.
Programming with Big Data in R Website: https://pbdr.org/