nestorFit.RdCore function of nestorFit
nestorFit( MO, SO, initList, maxIter = 20, eps = 0.01, alpha = 0.1, verbatim = 1, print.hist = FALSE, trackJ = FALSE )
| MO | Estimated means from norm_PLN. |
|---|---|
| SO | Estimated marginal vairances from norm_PLN. |
| initList | Result list from initVEM. |
| maxIter | Maximal number of iterations. |
| eps | Convergence precision parameter. |
| alpha | Tempering parameter, default to 0.1. |
| verbatim | Integer controlling verbosity in three levels, starting at 0. |
| print.hist | Prints edges weights histograms at each step if TRUE. |
| trackJ | Computes the lower bound at each parameter update if TRUE. Otherwise, the lower bound is only computed at each new VE step. |
M: estimated means.
S: estimated marginal variances.
Pg: edges probabilities.
Wg: edges variational weights.
W: edges weights.
Omega: matrix filled with precision terms common to all spanning trees.
lowbound: table containing the lowerbound trajectory.
features: table containing the parametes trajectory.
finalIter: number of iterations until convergence was reached.
time: running time of the VEM.
max.prec: boolean for reach of maximal precision reached during the VEM fit.
data=generate_missing_data(n=100,p=10,r=1,type="scale-free", plot=FALSE) PLNfit<-norm_PLN(data$Y) MO<-PLNfit$MO SO<-PLNfit$SO sigma_O=PLNfit$sigma_O #-- initialize with true clique for example initClique=data$TC #-- initialize the VEM initList=initVEM(cliqueList=initClique,sigma_O, MO,r=1 ) #-- run core function nestorFit fit=nestorFit( MO,SO, initList=initList, maxIter=5,verbatim=1)#> #> nestor ran in 0.271secs and 4 iterations.#> List of 11 #> $ M : num [1:100, 1:11] 2.3145 -0.536 1.4827 0.0809 0.793 ... #> $ S : num [1:100, 1:11] 0.0125 0.1691 0.028 0.1016 0.0537 ... #> $ Pg : num [1:11, 1:11] 0.00 9.64e-09 0.00 0.00 0.00 ... #> $ Wg : num [1:11, 1:11] 0.00 2.85e-01 1.13e-08 0.00 0.00 ... #> $ W : num [1:11, 1:11] 0 0.439 0 0 0 ... #> $ Omega : num [1:11, 1:11] 1.437 -0.339 -0.166 -0.289 -0.41 ... #> $ lowbound :'data.frame': 5 obs. of 5 variables: #> ..$ J : num [1:5] -745 -743 -744 -744 -744 #> ..$ T1 : num [1:5] -1028 -1068 -1076 -1077 -1078 #> ..$ T2 : num [1:5] -8.04e-03 -9.07e-04 -1.35e-04 -2.67e-05 -6.33e-06 #> ..$ T3 : num [1:5] 283 325 332 333 334 #> ..$ parameter: chr [1:5] "complete" "complete" "complete" "complete" ... #> $ features :'data.frame': 4 obs. of 4 variables: #> ..$ diffPg : num [1:4] 0.5 0.00273 0.000605 0.000112 #> ..$ diffW : num [1:4] 50486 709593 7342408 14667979 #> ..$ diffOmega: num [1:4] 0.62307 0.05675 0.01324 0.00369 #> ..$ diffWg : num [1:4] 2.99e+10 4.91e+09 7.47e+10 7.81e+11 #> $ finalIter: num 4 #> $ time : 'difftime' num 0.270549058914185 #> ..- attr(*, "units")= chr "secs" #> $ max.prec : logi FALSE