Last data update: 2014.03.03
R: Run 'JAGS' from R
Run ‘JAGS’ from R
Description
The jags
function takes data and starting values as input. It
automatically writes a jags
script, calls the model, and
saves the simulations for easy access in R.
Usage
jags(data, inits, parameters.to.save, model.file="model.bug",
n.chains=3, n.iter=2000, n.burnin=floor(n.iter/2),
n.thin=max(1, floor((n.iter - n.burnin) / 1000)),
DIC=TRUE, working.directory=NULL, jags.seed = 123,
refresh = n.iter/50, progress.bar = "text", digits=5,
RNGname = c("Wichmann-Hill", "Marsaglia-Multicarry",
"Super-Duper", "Mersenne-Twister"),
jags.module = c("glm","dic")
)
jags.parallel(data, inits, parameters.to.save, model.file = "model.bug",
n.chains = 2, n.iter = 2000, n.burnin = floor(n.iter/2),
n.thin = max(1, floor((n.iter - n.burnin)/1000)),
n.cluster= n.chains, DIC = TRUE,
working.directory = NULL, jags.seed = 123, digits=5,
RNGname = c("Wichmann-Hill", "Marsaglia-Multicarry",
"Super-Duper", "Mersenne-Twister"),
jags.module = c("glm","dic"),
export_obj_names=NULL,
envir = .GlobalEnv
)
jags2(data, inits, parameters.to.save, model.file="model.bug",
n.chains=3, n.iter=2000, n.burnin=floor(n.iter/2),
n.thin=max(1, floor((n.iter - n.burnin) / 1000)),
DIC=TRUE, jags.path="",
working.directory=NULL, clearWD=TRUE,
refresh = n.iter/50)
Arguments
data
(1) a vector or list of the names of the data objects used by
the model, (2) a (named) list of the data objects themselves, or
(3) the name of a "dump" format file containing the data objects,
which must end in ".txt", see example below for details.
inits
a list with n.chains
elements; each element of the
list is itself a list of starting values for the BUGS
model,
or a function creating (possibly random) initial values. If inits is
NULL
, JAGS
will generate initial values for parameters.
parameters.to.save
character vector of the names of the
parameters to save which should be monitored.
model.file
file containing the model written in BUGS
code. Alternatively, as in R2WinBUGS , model.file
can be an R
function that contains a BUGS
model that is written to a
temporary model file (see tempfile
) using write.model
n.chains
number of Markov chains (default: 3)
n.iter
number of total iterations per chain (including burn in;
default: 2000)
n.burnin
length of burn in, i.e. number of iterations to
discard at the beginning. Default is n.iter/2
, that is,
discarding the first half of the simulations. If n.burnin is 0,
jags()
will run 100 iterations for adaption.
n.cluster
number of clusters to use to run parallel chains.
Default equals n.chains.
n.thin
thinning rate. Must be a positive integer. Set
n.thin
> 1 to save memory and computation time if
n.iter
is large. Default is max(1, floor(n.chains *
(n.iter-n.burnin) / 1000))
which will only thin if there are at
least 2000 simulations.
DIC
logical; if TRUE
(default), compute deviance, pD,
and DIC. The rule pD=var(deviance) / 2
is used.
working.directory
sets working directory during execution of
this function; This should be the directory where model file is.
jags.seed
random seed for JAGS
, default is 123. This function is used for jags.parallell() and does not work for jags(). Use set.seed() instead if you want to produce identical result with jags()
.
jags.path
directory that contains the JAGS
executable.
The default is “”.
clearWD
indicating whether the files ‘data.txt ’,
‘inits[1:n.chains].txt ’, ‘codaIndex.txt ’, ‘jagsscript.txt ’,
and ‘CODAchain[1:nchains].txt ’ should be removed after jags
has
finished, default=TRUE.
refresh
refresh frequency for progress bar, default is n.iter/50
progress.bar
type of progress bar. Possible values are “text”,
“gui”, and “none”. Type “text” is displayed
on the R console. Type “gui” is a graphical progress bar
in a new window. The progress bar is suppressed if progress.bar
is
“none”
digits
as in write.model
in the R2WinBUGS package: number of significant digits used for
BUGS
input, see formatC
. Only used if specifying a BUGS
model as an R function.
RNGname
the name for random number generator used in JAGS. There are four RNGS
supplied by the base moduale in JAGS: Wichmann-Hill
, Marsaglia-Multicarry
,
Super-Duper
, Mersenne-Twister
jags.module
the vector of jags modules to be loaded. Default are “glm” and “dic”. Input NULL if you don't want to load any jags module.
export_obj_names
character vector of objects to export to the clusters.
envir
default is .GlobalEnv
Details
To run:
Write a BUGS
model in an ASCII file.
Go into R .
Prepare the inputs for the jags
function and run it (see
Example section).
The model will now run in JAGS
. It might take awhile. You
will see things happening in the R console.
BUGS version support:
Author(s)
Yu-Sung Su suyusung@tsinghua.edu.cn ,
Masanao Yajima yajima@stat.columbia.edu
References
Plummer, Martyn (2003)
“JAGS: A program for analysis of Bayesian graphical models using Gibbs sampling.”
http://citeseer.ist.psu.edu/plummer03jags.html .
Gelman, A., Carlin, J. B., Stern, H.S., Rubin, D.B. (2003)
Bayesian Data Analysis , 2nd edition, CRC Press.
Sibylle Sturtz and Uwe Ligges and Andrew Gelman. (2005).
“R2WinBUGS: A Package for Running WinBUGS from R.”
Journal of Statistical Software 3 (12): 1–6.
Examples
# An example model file is given in:
model.file <- system.file(package="R2jags", "model", "schools.txt")
# Let's take a look:
file.show(model.file)
# you can also write BUGS model as a R function, see below:
#=================#
# initialization #
#=================#
# data
J <- 8.0
y <- c(28.4,7.9,-2.8,6.8,-0.6,0.6,18.0,12.2)
sd <- c(14.9,10.2,16.3,11.0,9.4,11.4,10.4,17.6)
jags.data <- list("y","sd","J")
jags.params <- c("mu","sigma","theta")
jags.inits <- function(){
list("mu"=rnorm(1),"sigma"=runif(1),"theta"=rnorm(J))
}
## You can input data in 4 ways
## 1) data as list of character
jagsfit <- jags(data=list("y","sd","J"), inits=jags.inits, jags.params,
n.iter=10, model.file=model.file)
## 2) data as character vector of names
jagsfit <- jags(data=c("y","sd","J"), inits=jags.inits, jags.params,
n.iter=10, model.file=model.file)
## 3) data as named list
jagsfit <- jags(data=list(y=y,sd=sd,J=J), inits=jags.inits, jags.params,
n.iter=10, model.file=model.file)
## 4) data as a file
fn <- "tmpbugsdata.txt"
dump(c("y","sd","J"), file=fn)
jagsfit <- jags(data=fn, inits=jags.inits, jags.params,
n.iter=10, model.file=model.file)
unlink("tmpbugsdata.txt")
## You can write bugs model in R as a function
schoolsmodel <- function() {
for (j in 1:J){ # J=8, the number of schools
y[j] ~ dnorm (theta[j], tau.y[j]) # data model: the likelihood
tau.y[j] <- pow(sd[j], -2) # tau = 1/sigma^2
}
for (j in 1:J){
theta[j] ~ dnorm (mu, tau) # hierarchical model for theta
}
tau <- pow(sigma, -2) # tau = 1/sigma^2
mu ~ dnorm (0.0, 1.0E-6) # noninformative prior on mu
sigma ~ dunif (0, 1000) # noninformative prior on sigma
}
jagsfit <- jags(data=jags.data, inits=jags.inits, jags.params,
n.iter=10, model.file=schoolsmodel)
#===============================#
# RUN jags and postprocessing #
#===============================#
jagsfit <- jags(data=jags.data, inits=jags.inits, jags.params,
n.iter=5000, model.file=model.file)
# Run jags parallely, no progress bar. R may be frozen for a while,
# Be patient. Currenlty update afterward does not run parallelly
#
jagsfit.p <- jags.parallel(data=jags.data, inits=jags.inits, jags.params,
n.iter=5000, model.file=model.file)
# display the output
print(jagsfit)
plot(jagsfit)
# traceplot
traceplot(jagsfit.p)
traceplot(jagsfit)
# or to use some plots in coda
# use as.mcmmc to convert rjags object into mcmc.list
jagsfit.mcmc <- as.mcmc(jagsfit.p)
jagsfit.mcmc <- as.mcmc(jagsfit)
## now we can use the plotting methods from coda
#require(lattice)
#xyplot(jagsfit.mcmc)
#densityplot(jagsfit.mcmc)
# if the model does not converge, update it!
jagsfit.upd <- update(jagsfit, n.iter=100)
print(jagsfit.upd)
print(jagsfit.upd, intervals=c(0.025, 0.5, 0.975))
plot(jagsfit.upd)
# before update parallel jags object, do recompile it
recompile(jagsfit.p)
jagsfit.upd <- update(jagsfit.p, n.iter=100)
# or auto update it until it converges! see ?autojags for details
# recompile(jagsfit.p)
jagsfit.upd <- autojags(jagsfit.p)
jagsfit.upd <- autojags(jagsfit)
# to get DIC or specify DIC=TRUE in jags() or do the following#
dic.samples(jagsfit.upd$model, n.iter=1000, type="pD")
# attach jags object into search path see "attach.bugs" for details
attach.jags(jagsfit.upd)
# this will show a 3-way array of the bugs.sim object, for example:
mu
# detach jags object into search path see "attach.bugs" for details
detach.jags()
# to pick up the last save session
# for example, load("RWorkspace.Rdata")
recompile(jagsfit)
jagsfit.upd <- update(jagsfit, n.iter=100)
recompile(jagsfit.p)
jagsfit.upd <- update(jagsfit, n.iter=100)
#=============#
# using jags2 #
#=============#
## jags can be run and produces coda files, but cannot be updated once it's done
## You may need to edit "jags.path" to make this work,
## also you need a write access in the working directory:
## e.g. setwd("d:/")
## NOT RUN HERE
## Not run:
jagsfit <- jags2(data=jags.data, inits=jags.inits, jags.params,
n.iter=5000, model.file=model.file)
print(jagsfit)
plot(jagsfit)
# or to use some plots in coda
# use as.mcmmc to convert rjags object into mcmc.list
jagsfit.mcmc <- as.mcmc.list(jagsfit)
traceplot(jagsfit.mcmc)
#require(lattice)
#xyplot(jagsfit.mcmc)
#densityplot(jagsfit.mcmc)
## End(Not run)
Results
R version 3.3.1 (2016-06-21) -- "Bug in Your Hair"
Copyright (C) 2016 The R Foundation for Statistical Computing
Platform: x86_64-pc-linux-gnu (64-bit)
R is free software and comes with ABSOLUTELY NO WARRANTY.
You are welcome to redistribute it under certain conditions.
Type 'license()' or 'licence()' for distribution details.
R is a collaborative project with many contributors.
Type 'contributors()' for more information and
'citation()' on how to cite R or R packages in publications.
Type 'demo()' for some demos, 'help()' for on-line help, or
'help.start()' for an HTML browser interface to help.
Type 'q()' to quit R.
> library(R2jags)
Loading required package: rjags
Loading required package: coda
Linked to JAGS 4.1.0
Loaded modules: basemod,bugs
Attaching package: 'R2jags'
The following object is masked from 'package:coda':
traceplot
> png(filename="/home/ddbj/snapshot/RGM3/R_CC/result/R2jags/jags.Rd_%03d_medium.png", width=480, height=480)
> ### Name: jags
> ### Title: Run 'JAGS' from R
> ### Aliases: rjags-class rjags.parallel-class jags jags2 jags.parallel
> ### Keywords: interface models
>
> ### ** Examples
>
> # An example model file is given in:
> model.file <- system.file(package="R2jags", "model", "schools.txt")
> # Let's take a look:
> file.show(model.file)
# Bugs model file for 8 schools analysis from Section 5.5 of "Bayesian Data
# Analysis". Save this into the file "schools.bug" in your R working directory.
model {
for (j in 1:J){ # J=8, the number of schools
y[j] ~ dnorm (theta[j], tau.y[j]) # data model: the likelihood
tau.y[j] <- pow(sd[j], -2) # tau = 1/sigma^2
}
for (j in 1:J){
theta[j] ~ dnorm (mu, tau) # hierarchical model for theta
}
tau <- pow(sigma, -2) # tau = 1/sigma^2
mu ~ dnorm (0.0, 1.0E-6) # noninformative prior on mu
sigma ~ dunif (0, 1000) # noninformative prior on sigma
}
> # you can also write BUGS model as a R function, see below:
>
> #=================#
> # initialization #
> #=================#
>
> # data
> J <- 8.0
> y <- c(28.4,7.9,-2.8,6.8,-0.6,0.6,18.0,12.2)
> sd <- c(14.9,10.2,16.3,11.0,9.4,11.4,10.4,17.6)
>
>
> jags.data <- list("y","sd","J")
> jags.params <- c("mu","sigma","theta")
> jags.inits <- function(){
+ list("mu"=rnorm(1),"sigma"=runif(1),"theta"=rnorm(J))
+ }
>
> ## You can input data in 4 ways
> ## 1) data as list of character
> jagsfit <- jags(data=list("y","sd","J"), inits=jags.inits, jags.params,
+ n.iter=10, model.file=model.file)
module glm loaded
Compiling model graph
Resolving undeclared variables
Allocating nodes
Graph information:
Observed stochastic nodes: 8
Unobserved stochastic nodes: 10
Total graph size: 50
Initializing model
>
> ## 2) data as character vector of names
> jagsfit <- jags(data=c("y","sd","J"), inits=jags.inits, jags.params,
+ n.iter=10, model.file=model.file)
Compiling model graph
Resolving undeclared variables
Allocating nodes
Graph information:
Observed stochastic nodes: 8
Unobserved stochastic nodes: 10
Total graph size: 50
Initializing model
>
> ## 3) data as named list
> jagsfit <- jags(data=list(y=y,sd=sd,J=J), inits=jags.inits, jags.params,
+ n.iter=10, model.file=model.file)
Compiling model graph
Resolving undeclared variables
Allocating nodes
Graph information:
Observed stochastic nodes: 8
Unobserved stochastic nodes: 10
Total graph size: 50
Initializing model
>
> ## 4) data as a file
> fn <- "tmpbugsdata.txt"
> dump(c("y","sd","J"), file=fn)
> jagsfit <- jags(data=fn, inits=jags.inits, jags.params,
+ n.iter=10, model.file=model.file)
Compiling model graph
Resolving undeclared variables
Allocating nodes
Graph information:
Observed stochastic nodes: 8
Unobserved stochastic nodes: 10
Total graph size: 50
Initializing model
> unlink("tmpbugsdata.txt")
>
> ## You can write bugs model in R as a function
>
> schoolsmodel <- function() {
+ for (j in 1:J){ # J=8, the number of schools
+ y[j] ~ dnorm (theta[j], tau.y[j]) # data model: the likelihood
+ tau.y[j] <- pow(sd[j], -2) # tau = 1/sigma^2
+ }
+ for (j in 1:J){
+ theta[j] ~ dnorm (mu, tau) # hierarchical model for theta
+ }
+ tau <- pow(sigma, -2) # tau = 1/sigma^2
+ mu ~ dnorm (0.0, 1.0E-6) # noninformative prior on mu
+ sigma ~ dunif (0, 1000) # noninformative prior on sigma
+ }
>
> jagsfit <- jags(data=jags.data, inits=jags.inits, jags.params,
+ n.iter=10, model.file=schoolsmodel)
Compiling model graph
Resolving undeclared variables
Allocating nodes
Graph information:
Observed stochastic nodes: 8
Unobserved stochastic nodes: 10
Total graph size: 50
Initializing model
>
>
> #===============================#
> # RUN jags and postprocessing #
> #===============================#
> jagsfit <- jags(data=jags.data, inits=jags.inits, jags.params,
+ n.iter=5000, model.file=model.file)
Compiling model graph
Resolving undeclared variables
Allocating nodes
Graph information:
Observed stochastic nodes: 8
Unobserved stochastic nodes: 10
Total graph size: 50
Initializing model
>
> # Run jags parallely, no progress bar. R may be frozen for a while,
> # Be patient. Currenlty update afterward does not run parallelly
> #
> jagsfit.p <- jags.parallel(data=jags.data, inits=jags.inits, jags.params,
+ n.iter=5000, model.file=model.file)
>
> # display the output
> print(jagsfit)
Inference for Bugs model at "/home/ddbj/local/lib64/R/library/R2jags/model/schools.txt", fit using jags,
3 chains, each with 5000 iterations (first 2500 discarded), n.thin = 2
n.sims = 3750 iterations saved
mu.vect sd.vect 2.5% 25% 50% 75% 97.5% Rhat n.eff
mu 8.283 5.250 -2.546 5.090 8.402 11.748 18.141 1.002 1100
sigma 7.265 5.940 0.262 2.874 6.028 10.141 22.009 1.003 760
theta[1] 12.292 8.516 -2.159 6.889 11.255 16.444 32.125 1.003 1000
theta[2] 8.271 6.535 -4.883 4.294 8.490 12.464 21.533 1.003 960
theta[3] 6.198 8.339 -12.728 1.775 7.022 11.637 20.903 1.001 3700
theta[4] 7.877 6.719 -6.389 3.825 8.143 12.145 20.983 1.001 3800
theta[5] 5.284 6.928 -10.283 1.103 6.012 10.189 16.532 1.001 3800
theta[6] 6.245 7.168 -9.519 2.031 6.987 11.191 18.653 1.001 3100
theta[7] 11.189 6.958 -1.956 6.511 10.845 15.111 26.792 1.005 430
theta[8] 9.017 8.180 -7.128 4.358 9.013 13.489 27.227 1.001 3800
deviance 60.453 2.221 56.907 59.069 60.085 61.471 66.066 1.002 1700
For each parameter, n.eff is a crude measure of effective sample size,
and Rhat is the potential scale reduction factor (at convergence, Rhat=1).
DIC info (using the rule, pD = var(deviance)/2)
pD = 2.5 and DIC = 62.9
DIC is an estimate of expected predictive error (lower deviance is better).
> plot(jagsfit)
>
> # traceplot
> traceplot(jagsfit.p)
> traceplot(jagsfit)
>
> # or to use some plots in coda
> # use as.mcmmc to convert rjags object into mcmc.list
> jagsfit.mcmc <- as.mcmc(jagsfit.p)
> jagsfit.mcmc <- as.mcmc(jagsfit)
> ## now we can use the plotting methods from coda
> #require(lattice)
> #xyplot(jagsfit.mcmc)
> #densityplot(jagsfit.mcmc)
>
> # if the model does not converge, update it!
> jagsfit.upd <- update(jagsfit, n.iter=100)
> print(jagsfit.upd)
Inference for Bugs model at "/home/ddbj/local/lib64/R/library/R2jags/model/schools.txt", fit using jags,
3 chains, each with 100 iterations (first 0 discarded)
n.sims = 300 iterations saved
mu.vect sd.vect 2.5% 25% 50% 75% 97.5% Rhat n.eff
mu 7.846 5.229 -1.867 3.812 8.146 10.870 17.368 1.052 100
sigma 4.953 5.859 0.181 0.975 2.714 6.147 20.279 1.242 12
theta[1] 10.395 7.811 -1.199 4.954 8.794 15.013 33.524 1.052 54
theta[2] 7.453 6.173 -3.307 3.412 7.256 10.825 18.544 1.039 140
theta[3] 6.636 7.380 -11.524 3.385 7.334 11.051 18.837 1.049 140
theta[4] 8.025 5.771 -2.394 3.919 7.788 11.092 18.337 1.048 200
theta[5] 6.524 6.097 -5.623 3.271 6.864 9.808 17.291 1.032 120
theta[6] 6.926 6.655 -9.884 3.466 7.571 10.718 17.758 1.068 57
theta[7] 10.093 6.240 0.104 5.866 8.882 14.311 24.388 1.048 44
theta[8] 8.559 7.353 -6.273 3.846 8.056 11.874 26.072 1.018 300
deviance 60.619 1.913 57.453 59.395 60.246 61.544 64.660 1.135 19
For each parameter, n.eff is a crude measure of effective sample size,
and Rhat is the potential scale reduction factor (at convergence, Rhat=1).
DIC info (using the rule, pD = var(deviance)/2)
pD = 1.6 and DIC = 62.3
DIC is an estimate of expected predictive error (lower deviance is better).
> print(jagsfit.upd, intervals=c(0.025, 0.5, 0.975))
Inference for Bugs model at "/home/ddbj/local/lib64/R/library/R2jags/model/schools.txt", fit using jags,
3 chains, each with 100 iterations (first 0 discarded)
n.sims = 300 iterations saved
mu.vect sd.vect 2.5% 50% 97.5% Rhat n.eff
mu 7.846 5.229 -1.867 8.146 17.368 1.052 100
sigma 4.953 5.859 0.181 2.714 20.279 1.242 12
theta[1] 10.395 7.811 -1.199 8.794 33.524 1.052 54
theta[2] 7.453 6.173 -3.307 7.256 18.544 1.039 140
theta[3] 6.636 7.380 -11.524 7.334 18.837 1.049 140
theta[4] 8.025 5.771 -2.394 7.788 18.337 1.048 200
theta[5] 6.524 6.097 -5.623 6.864 17.291 1.032 120
theta[6] 6.926 6.655 -9.884 7.571 17.758 1.068 57
theta[7] 10.093 6.240 0.104 8.882 24.388 1.048 44
theta[8] 8.559 7.353 -6.273 8.056 26.072 1.018 300
deviance 60.619 1.913 57.453 60.246 64.660 1.135 19
For each parameter, n.eff is a crude measure of effective sample size,
and Rhat is the potential scale reduction factor (at convergence, Rhat=1).
DIC info (using the rule, pD = var(deviance)/2)
pD = 1.6 and DIC = 62.3
DIC is an estimate of expected predictive error (lower deviance is better).
> plot(jagsfit.upd)
>
> # before update parallel jags object, do recompile it
> recompile(jagsfit.p)
Compiling model graph
Resolving undeclared variables
Allocating nodes
Graph information:
Observed stochastic nodes: 8
Unobserved stochastic nodes: 10
Total graph size: 50
Initializing model
Compiling model graph
Resolving undeclared variables
Allocating nodes
Graph information:
Observed stochastic nodes: 8
Unobserved stochastic nodes: 10
Total graph size: 50
Initializing model
> jagsfit.upd <- update(jagsfit.p, n.iter=100)
>
>
>
> # or auto update it until it converges! see ?autojags for details
> # recompile(jagsfit.p)
> jagsfit.upd <- autojags(jagsfit.p)
> jagsfit.upd <- autojags(jagsfit)
>
> # to get DIC or specify DIC=TRUE in jags() or do the following#
> dic.samples(jagsfit.upd$model, n.iter=1000, type="pD")
Mean deviance: 60.52
penalty 2.855
Penalized deviance: 63.38
>
> # attach jags object into search path see "attach.bugs" for details
> attach.jags(jagsfit.upd)
>
> # this will show a 3-way array of the bugs.sim object, for example:
> mu
[,1]
[1,] 14.881464571
[2,] 3.604098011
[3,] 15.978212680
[4,] 4.959063873
[5,] 3.151922559
[6,] 5.782175675
[7,] 2.047465119
[8,] 8.678511782
[9,] 5.654278389
[10,] 7.344493749
[11,] 5.782657710
[12,] 11.436401939
[13,] 14.090212575
[14,] 14.496716772
[15,] 8.899458286
[16,] 3.960753808
[17,] 7.681111588
[18,] 8.776018331
[19,] 7.230958446
[20,] 15.503152856
[21,] 3.337025812
[22,] 7.441212500
[23,] 11.572551700
[24,] 7.141389653
[25,] 5.970881192
[26,] 11.516674412
[27,] 9.907720219
[28,] 7.638678098
[29,] 7.440112271
[30,] 7.449259317
[31,] 12.551402640
[32,] 20.496298267
[33,] 7.997844720
[34,] 2.528411333
[35,] 4.708914468
[36,] 8.731331171
[37,] 6.501914071
[38,] 5.925110663
[39,] 5.519476276
[40,] 7.626505880
[41,] 7.346637301
[42,] 14.400361473
[43,] 10.868374241
[44,] 4.209502314
[45,] 3.653545690
[46,] 12.820979314
[47,] 5.294160840
[48,] 11.035957712
[49,] 9.532682836
[50,] 17.130237346
[51,] 14.248520245
[52,] 16.732664022
[53,] 3.332926590
[54,] 5.900265166
[55,] 7.939522140
[56,] 15.899177878
[57,] 9.239121149
[58,] 2.319339925
[59,] 11.789126204
[60,] 7.870244087
[61,] 1.479283867
[62,] 8.636186989
[63,] 4.515985092
[64,] 7.775149012
[65,] 7.477989163
[66,] 10.905278571
[67,] 6.386348532
[68,] 10.184845353
[69,] 6.972813128
[70,] -1.204632133
[71,] 12.290723046
[72,] 5.336024790
[73,] 5.629053137
[74,] 12.911307524
[75,] 4.263402388
[76,] 11.756942175
[77,] 6.851328701
[78,] 6.694269463
[79,] 11.231916631
[80,] 11.420441026
[81,] 16.056803464
[82,] 5.439035101
[83,] 10.717188466
[84,] 7.267940890
[85,] 4.094834409
[86,] 5.360866882
[87,] 14.522174998
[88,] 9.857490869
[89,] 4.176488846
[90,] 17.942807242
[91,] 12.066728764
[92,] 4.979643715
[93,] 4.127549412
[94,] 7.703299903
[95,] 4.715101284
[96,] 9.053416477
[97,] -4.999941251
[98,] 10.006114228
[99,] 12.764989490
[100,] 19.122006828
[101,] 2.654536643
[102,] 7.830745126
[103,] 1.973625602
[104,] 16.570034980
[105,] 8.271698087
[106,] 6.816608991
[107,] 5.707964386
[108,] 8.113976474
[109,] 11.769146129
[110,] 0.617720007
[111,] 15.057564291
[112,] 6.323683265
[113,] 0.965988055
[114,] 9.594935048
[115,] 2.160081592
[116,] 2.261093221
[117,] 11.976691215
[118,] 17.222454300
[119,] 10.654743549
[120,] 6.769094417
[121,] 10.092302882
[122,] 10.768852550
[123,] -2.358310837
[124,] 10.573310348
[125,] 6.247757836
[126,] 12.495278808
[127,] 7.088953321
[128,] 6.285821302
[129,] 5.507057298
[130,] 7.614299732
[131,] 10.978317563
[132,] 3.762842904
[133,] 13.409898589
[134,] 11.821535470
[135,] 11.429157058
[136,] 7.744475049
[137,] 6.246927047
[138,] 11.031233458
[139,] 6.304796636
[140,] 19.426646061
[141,] 9.128101232
[142,] 5.234263648
[143,] 13.589464006
[144,] 1.541153840
[145,] 7.839288375
[146,] 2.767323284
[147,] 17.792663712
[148,] 6.021471645
[149,] 12.409795046
[150,] 12.203883822
[151,] 4.751318563
[152,] 9.018151383
[153,] 11.571750820
[154,] 5.815662165
[155,] 1.386828510
[156,] 13.535240593
[157,] 4.320370242
[158,] 13.924488796
[159,] 1.577965523
[160,] -8.322290685
[161,] 9.868397892
[162,] 5.000694533
[163,] 12.340246687
[164,] 5.666417076
[165,] 3.934961667
[166,] 6.626158800
[167,] 1.262014677
[168,] 13.619702068
[169,] 2.314211832
[170,] 13.836454936
[171,] 12.266859085
[172,] 7.843994479
[173,] 11.120693663
[174,] 6.744297665
[175,] 3.585802069
[176,] 7.321624777
[177,] 2.094406327
[178,] -0.294174117
[179,] 14.436633549
[180,] 9.716926697
[181,] -3.912464254
[182,] 3.752578507
[183,] 14.871971092
[184,] 11.274895920
[185,] 12.067925283
[186,] 4.403516765
[187,] 9.931941317
[188,] 4.803427812
[189,] 26.090362784
[190,] 9.405920734
[191,] 9.149483497
[192,] 8.858134867
[193,] 4.654785327
[194,] 2.265116433
[195,] 6.124460413
[196,] 2.903906150
[197,] 8.549873574
[198,] 9.153340189
[199,] 7.928051049
[200,] 17.462782373
[201,] 11.489485983
[202,] 8.713461558
[203,] 5.018729594
[204,] 6.201147268
[205,] -1.830172463
[206,] 6.122455960
[207,] 2.823561684
[208,] 3.787108337
[209,] 10.938049725
[210,] 2.726714951
[211,] 0.323435541
[212,] 2.190983029
[213,] 3.498495116
[214,] 5.490279338
[215,] 12.117083726
[216,] -0.332120694
[217,] 12.760160054
[218,] 3.791381720
[219,] 5.749741987
[220,] 9.244606323
[221,] 12.959163176
[222,] 8.620183863
[223,] 11.049689548
[224,] 7.010150137
[225,] 11.608888234
[226,] 12.306529689
[227,] 16.883345260
[228,] 4.760341128
[229,] 12.060640793
[230,] 7.212559660
[231,] 4.451273383
[232,] 14.339276288
[233,] 11.329628574
[234,] 12.874715685
[235,] 5.058239480
[236,] 14.149536546
[237,] 8.012159132
[238,] 0.447122460
[239,] 7.470179113
[240,] 16.277616227
[241,] 7.592785040
[242,] 9.926939575
[243,] 7.214833384
[244,] 10.852421869
[245,] 7.476682012
[246,] 19.254965525
[247,] 8.361414087
[248,] 9.799555634
[249,] 4.167733203
[250,] 2.649888908
[251,] 5.625724768
[252,] 5.325137197
[253,] -1.249486477
[254,] 12.378116877
[255,] 8.342229113
[256,] 5.222929109
[257,] 3.343783719
[258,] 9.719874111
[259,] 11.026153510
[260,] 5.387207387
[261,] 13.049198948
[262,] 6.716633689
[263,] 12.570195807
[264,] 13.448441960
[265,] 6.130981713
[266,] 2.304380407
[267,] 9.889528817
[268,] 1.869260150
[269,] 7.680910217
[270,] 8.366676472
[271,] 10.326436197
[272,] 5.935243045
[273,] 6.617063534
[274,] 13.216972886
[275,] 5.348969717
[276,] 7.000491775
[277,] 9.768365018
[278,] 12.442448183
[279,] 4.686781346
[280,] 7.400069619
[281,] 2.314524040
[282,] 3.401011335
[283,] 7.925307733
[284,] 11.855121876
[285,] 13.037268839
[286,] -3.375445353
[287,] 5.980776586
[288,] 5.278946362
[289,] 7.651033981
[290,] 9.123041851
[291,] 11.961697488
[292,] -1.354494199
[293,] 5.352099491
[294,] 13.428175053
[295,] 6.271358051
[296,] 6.657126507
[297,] 5.294231872
[298,] 7.764427544
[299,] 12.381464820
[300,] 13.696520727
[301,] 6.683545422
[302,] 8.042073253
[303,] 7.003689649
[304,] 5.697189170
[305,] 1.882493175
[306,] 2.777972105
[307,] 5.177833511
[308,] 10.261720923
[309,] -3.409046016
[310,] 7.656419459
[311,] 14.036140423
[312,] 5.712859241
[313,] 11.465519347
[314,] 7.235838363
[315,] 5.699701843
[316,] 4.249170762
[317,] 8.530844125
[318,] 7.602598842
[319,] 2.173865125
[320,] 7.983254249
[321,] 3.671330033
[322,] 7.836147356
[323,] 2.542621977
[324,] 20.448186597
[325,] 18.133688091
[326,] 15.507082797
[327,] -0.436254326
[328,] 15.210122617
[329,] 13.861137304
[330,] 13.660174223
[331,] 1.017447056
[332,] 15.774154481
[333,] 21.217582923
[334,] 11.148076007
[335,] 7.567370812
[336,] 12.355355558
[337,] 10.448545689
[338,] 12.436931024
[339,] 7.356817734
[340,] 12.665576421
[341,] 13.892822194
[342,] 2.104879071
[343,] 11.465468748
[344,] 9.093268402
[345,] 11.155135283
[346,] 9.582609168
[347,] 4.911200998
[348,] 5.626666366
[349,] 6.683536391
[350,] 7.602850042
[351,] 5.518661012
[352,] 13.028742149
[353,] 17.167418917
[354,] 14.395406261
[355,] 6.029748922
[356,] 13.754782587
[357,] 8.004543145
[358,] 9.821269455
[359,] 9.358858788
[360,] 22.917197757
[361,] 5.420546759
[362,] 10.686322473
[363,] 19.293009419
[364,] 7.681757876
[365,] 15.610641870
[366,] 9.352014664
[367,] 12.941934557
[368,] 1.533006335
[369,] 2.585045760
[370,] 7.728079684
[371,] 14.586927419
[372,] 6.025334745
[373,] 0.557745398
[374,] 7.920875592
[375,] 13.569628178
[376,] 11.850458910
[377,] 6.860065020
[378,] 9.607627812
[379,] -7.137127369
[380,] 12.546188289
[381,] 6.927676826
[382,] 2.100369214
[383,] 5.759973972
[384,] 4.056890143
[385,] 6.916803700
[386,] 9.875742858
[387,] 13.011498909
[388,] 11.438487944
[389,] 10.618013723
[390,] 15.320267458
[391,] 5.102716259
[392,] 11.448699455
[393,] 14.122961044
[394,] 7.611040776
[395,] 14.298650226
[396,] 15.475913789
[397,] 11.283383082
[398,] 14.987665259
[399,] 2.504082500
[400,] 4.309008086
[401,] 13.121005700
[402,] 13.557766910
[403,] 9.274929128
[404,] 6.732364129
[405,] 2.503153126
[406,] 7.324559615
[407,] 11.440138509
[408,] 16.401488955
[409,] 5.937846711
[410,] 7.936680398
[411,] 14.936692870
[412,] 8.332742272
[413,] 8.699932097
[414,] 0.831131555
[415,] 4.759541896
[416,] 4.989411251
[417,] 4.769176076
[418,] 26.629981642
[419,] 8.038562179
[420,] 11.159314230
[421,] 3.758080513
[422,] 10.903438265
[423,] 23.413037799
[424,] 6.682276975
[425,] 6.421103831
[426,] 5.679228453
[427,] 12.944304215
[428,] -1.250197371
[429,] 12.020139054
[430,] 12.891633530
[431,] 11.067919024
[432,] 3.619425712
[433,] 8.533998294
[434,] -4.085689054
[435,] 13.533201384
[436,] 12.377937668
[437,] 5.422448918
[438,] 24.571494480
[439,] 3.386549941
[440,] 1.178792921
[441,] 8.162021469
[442,] 9.581839304
[443,] 10.199202714
[444,] 11.731678568
[445,] 2.115768662
[446,] 5.625165271
[447,] 7.800775750
[448,] 9.955990687
[449,] 9.536171554
[450,] 6.612453343
[451,] 8.476379614
[452,] 6.169295547
[453,] 8.679486319
[454,] 11.640208942
[455,] 0.338740498
[456,] 8.454063021
[457,] 5.079606078
[458,] 12.530752130
[459,] 7.425114293
[460,] 15.950185826
[461,] 10.184467145
[462,] 10.374504082
[463,] 3.094123424
[464,] 17.881284630
[465,] 1.844105682
[466,] 8.684986529
[467,] 14.273205189
[468,] 12.378561389
[469,] 12.186834076
[470,] 9.995738687
[471,] 0.794081765
[472,] 10.057161547
[473,] 10.200399064
[474,] 10.436420794
[475,] 6.228783243
[476,] 13.499060466
[477,] 13.607805253
[478,] 0.022269523
[479,] 4.811820217
[480,] 7.246329643
[481,] 15.124237612
[482,] 7.178434873
[483,] 4.920856523
[484,] 2.598446732
[485,] 11.254361874
[486,] 10.601025474
[487,] 4.788200665
[488,] 16.554904888
[489,] 11.656189255
[490,] 10.662066257
[491,] 11.802073872
[492,] 9.770672333
[493,] 8.035370884
[494,] 8.582979788
[495,] 6.524186865
[496,] 14.732673723
[497,] 5.127567394
[498,] 8.472008603
[499,] 2.214199088
[500,] 11.913525868
[501,] 11.778254646
[502,] 6.661852485
[503,] 7.738821093
[504,] 5.805445548
[505,] 2.617156449
[506,] 7.914772628
[507,] 5.700056585
[508,] 7.451601498
[509,] 9.320569788
[510,] 6.375759296
[511,] 9.672845650
[512,] 2.043586534
[513,] 0.627798354
[514,] 12.881791362
[515,] 9.818019451
[516,] 9.286628447
[517,] 11.042494966
[518,] 1.560063887
[519,] 4.052644088
[520,] 10.595845441
[521,] 20.681398388
[522,] 0.605383085
[523,] 9.277854964
[524,] 4.735300383
[525,] 6.745252365
[526,] 6.394711339
[527,] 1.636869928
[528,] 13.884589885
[529,] 10.919537139
[530,] 7.393643089
[531,] 5.845272266
[532,] 17.281982740
[533,] 10.676928907
[534,] 2.142095689
[535,] 9.262469302
[536,] 11.461951764
[537,] 5.947172023
[538,] 5.895700559
[539,] 7.993652879
[540,] 9.076046941
[541,] -0.093103703
[542,] 5.674132809
[543,] 7.130745765
[544,] 16.290016055
[545,] 3.379247554
[546,] 3.616586833
[547,] 9.276043872
[548,] 10.995677253
[549,] 9.728204655
[550,] 13.267519673
[551,] 1.424369604
[552,] 14.996763445
[553,] 1.209443414
[554,] 1.983833231
[555,] 16.341578472
[556,] 8.226945041
[557,] 8.401420401
[558,] 7.673930558
[559,] 5.409550036
[560,] 8.812233306
[561,] 10.867706666
[562,] 8.529668391
[563,] 10.830518747
[564,] 15.112474713
[565,] 3.390827747
[566,] 8.737295450
[567,] 11.274031968
[568,] 18.385668743
[569,] 3.507016068
[570,] 26.211277477
[571,] -1.774539074
[572,] 0.776595844
[573,] 9.942932652
[574,] 6.201369326
[575,] 7.888315311
[576,] 16.508842536
[577,] 4.200559892
[578,] 4.270422625
[579,] 11.984110608
[580,] 14.213580023
[581,] 15.199666738
[582,] 5.967781863
[583,] 4.615361567
[584,] 5.999844475
[585,] 7.707405540
[586,] -1.254633377
[587,] 14.053097044
[588,] 9.656391238
[589,] 11.719370600
[590,] 11.666034019
[591,] 7.086450661
[592,] 5.023164282
[593,] 5.610870617
[594,] 4.005109092
[595,] 8.875269892
[596,] 5.231874586
[597,] 7.210014731
[598,] 15.682360786
[599,] 4.815310151
[600,] 7.964103700
[601,] 7.544628714
[602,] 17.042083123
[603,] 10.165947316
[604,] 8.837507314
[605,] 14.523010617
[606,] 3.434021875
[607,] 3.107220312
[608,] 10.738500107
[609,] 3.813530079
[610,] 5.118344639
[611,] 8.528388945
[612,] 3.665594359
[613,] 11.952188115
[614,] 8.001419255
[615,] 5.644260319
[616,] 11.473914077
[617,] 5.449813680
[618,] 3.536837796
[619,] 4.762791635
[620,] 12.141190546
[621,] 16.955866831
[622,] 9.267367039
[623,] 5.741625326
[624,] 7.387333814
[625,] 3.891973247
[626,] 11.079357204
[627,] 2.722792592
[628,] -2.644887865
[629,] 8.102374572
[630,] 7.250094734
[631,] 8.306452651
[632,] 12.017946462
[633,] 3.411310292
[634,] 3.896680084
[635,] -0.238738010
[636,] 2.582267497
[637,] 12.080039207
[638,] 10.646076612
[639,] 1.970855296
[640,] 11.399163738
[641,] 3.756856934
[642,] 3.924265077
[643,] 12.891191607
[644,] 5.018937475
[645,] 6.104651558
[646,] 3.597690553
[647,] 5.290735201
[648,] 5.003611672
[649,] 18.458585744
[650,] 3.211312972
[651,] 10.239747655
[652,] 3.865744229
[653,] 8.887659181
[654,] 11.369419934
[655,] 8.631379995
[656,] 10.189062868
[657,] 11.244488099
[658,] 11.611384960
[659,] 10.452198026
[660,] 11.355928740
[661,] 11.659766349
[662,] 8.227677978
[663,] 9.208289599
[664,] 12.350326165
[665,] 16.549342667
[666,] 1.031480688
[667,] 7.621502163
[668,] 6.962513919
[669,] 9.059113940
[670,] 11.274366802
[671,] 19.698765641
[672,] 11.564018102
[673,] 14.095402712
[674,] 8.736078669
[675,] 3.771886568
[676,] 14.225913709
[677,] 6.000859518
[678,] 10.799012928
[679,] 5.720568373
[680,] 8.578982383
[681,] 13.219865162
[682,] 11.994854644
[683,] 7.443446090
[684,] 12.411146767
[685,] 3.579284037
[686,] 14.546064723
[687,] 5.412138565
[688,] 1.685665331
[689,] 17.705538254
[690,] 11.615315149
[691,] 1.565180246
[692,] 3.206342124
[693,] 3.592574650
[694,] 8.956911321
[695,] 0.856765284
[696,] 13.559461212
[697,] 12.483666479
[698,] 15.882991689
[699,] 7.884286303
[700,] 9.026663956
[701,] 13.024867684
[702,] 4.334371521
[703,] -1.148700911
[704,] 16.168987235
[705,] 7.286899885
[706,] 5.482892900
[707,] 1.467328605
[708,] 10.429209707
[709,] 6.090774298
[710,] -1.618932241
[711,] 7.607696214
[712,] 13.965484823
[713,] 5.604435529
[714,] 3.380809973
[715,] 15.797034396
[716,] 6.097476754
[717,] 22.590235953
[718,] 0.358035149
[719,] 5.133468286
[720,] 12.194265924
[721,] 11.161464840
[722,] 3.456676608
[723,] 12.545786152
[724,] 4.438254834
[725,] 11.359782299
[726,] 3.305581255
[727,] 6.334427277
[728,] 0.108671823
[729,] 1.746430636
[730,] 3.146932091
[731,] 7.354197120
[732,] 7.590574100
[733,] 6.271658206
[734,] 10.211537712
[735,] 5.964114576
[736,] 0.568334732
[737,] 9.814777783
[738,] 14.761609410
[739,] 6.571341244
[740,] 4.718197830
[741,] 11.182109339
[742,] 12.425014140
[743,] 16.774735388
[744,] 0.816120332
[745,] 9.747954547
[746,] 8.991334913
[747,] 16.926710979
[748,] 5.386785702
[749,] 3.417410083
[750,] 6.476752064
[751,] 5.579845718
[752,] 7.210506958
[753,] 0.935288725
[754,] 7.542397133
[755,] 7.625789136
[756,] 10.581327234
[757,] 1.536763575
[758,] 15.258422498
[759,] 5.263272192
[760,] 8.073158525
[761,] 3.159309190
[762,] 2.574223917
[763,] 7.929814331
[764,] 3.011157539
[765,] 6.296495683
[766,] 6.585702211
[767,] 6.783069539
[768,] 3.221778893
[769,] 11.474452515
[770,] 4.126616984
[771,] 4.253921766
[772,] 8.195884171
[773,] 12.123992693
[774,] 1.137776022
[775,] 7.123041194
[776,] 7.521782402
[777,] 2.658547556
[778,] 15.050852674
[779,] 3.537197563
[780,] 6.259237658
[781,] 5.747775896
[782,] 4.365861477
[783,] 7.586411182
[784,] 6.622277740
[785,] 9.761850210
[786,] 7.919871056
[787,] 7.469328708
[788,] 7.768287160
[789,] 2.494205166
[790,] 3.464163793
[791,] 10.888763507
[792,] 9.367421084
[793,] 11.958863109
[794,] 8.824784183
[795,] 15.979097313
[796,] 2.280724018
[797,] 12.738249689
[798,] 1.892844749
[799,] 6.596093435
[800,] 3.303340077
[801,] 7.005810274
[802,] 23.697903160
[803,] 10.897914691
[804,] 3.662798535
[805,] 4.237600564
[806,] 11.276775511
[807,] 3.217512194
[808,] 20.936084210
[809,] 7.970274697
[810,] 4.655135985
[811,] 13.672232057
[812,] 11.551954505
[813,] 11.438172864
[814,] 0.704317144
[815,] 3.354270790
[816,] 2.816482558
[817,] 11.579452667
[818,] 6.162640060
[819,] 22.577311677
[820,] 3.998182162
[821,] 2.936981656
[822,] 16.742296334
[823,] -0.032155622
[824,] 8.002442833
[825,] 12.229217975
[826,] 6.115814733
[827,] 0.983513556
[828,] 10.927471492
[829,] 1.347029302
[830,] 3.737813315
[831,] 3.595823942
[832,] 17.622686392
[833,] 11.756241135
[834,] 8.486570911
[835,] 11.395336778
[836,] 14.776155738
[837,] 9.609598068
[838,] 13.330041840
[839,] 11.183233939
[840,] 1.562574336
[841,] 9.488757390
[842,] 10.301142922
[843,] 12.697205257
[844,] 4.262750270
[845,] 3.281692458
[846,] 21.5