Execution 1061119086

name

value

type

provided

enforcement

description

errors

annealSupport

boolean

false

default value: true

checkIsDAG

boolean

false

default value: true

engine

PosteriorInferenceEngine: SCM|PT|MCMC|AIS|Forward|Exact|None|fully qualified

false

default value: PT

engine.adaptFraction

double

false

default value: 0.5

Set to zero for disabling schedule adaptation

engine.initialization

InitType: COPIES|FORWARD|SCM

false

default value: SCM

engine.ladder

TemperatureLadder: Geometric|EquallySpaced|Polynomial|UserSpecified|fully qualified

false

default value: EquallySpaced

The annealing schedule to use or if adaptation is used, the initial value

engine.logNormalizationEstimator

LogNormalizationEstimator: thermodynamicIntegration|steppingStone

false

default value: steppingStone

engine.nChains

10

int

true

default value: 8

engine.nPassesPerScan

double

false

default value: 3

engine.nScans

10000

int

true

default value: 1_000

engine.nThreads

Cores: Single|Max|Dynamic|Fixed|fully qualified

false

default value: Dynamic

engine.nThreads.fraction

double

false

default value: 0.5

engine.nThreads.ignoreUtilizedCores

boolean

false

default value: true

engine.nThreads.verbose

boolean

false

default value: false

engine.random

Random

false

default value: 1

engine.reversible

boolean

false

default value: false

engine.scmInit.maxAnnealingParameter

double

false

default value: 1.0

Use higher values for likelihood maximization

engine.scmInit.nFinalRejuvenations

int

false

default value: 5

Number of rejuvenation passes to do after the change of measure.

engine.scmInit.nParticles

int

false

default value: 1_000

engine.scmInit.nThreads

Cores: Single|Max|Dynamic|Fixed|fully qualified

false

default value: Dynamic

engine.scmInit.nThreads.fraction

double

false

default value: 0.5

engine.scmInit.nThreads.ignoreUtilizedCores

boolean

false

default value: true

engine.scmInit.nThreads.verbose

boolean

false

default value: false

engine.scmInit.random

Random

false

default value: 1

Random seed used for proposals and resampling.

engine.scmInit.resamplingESSThreshold

double

false

default value: 0.5

If the (relative) Effective Sample Size (ESS) falls below, perform a resampling round.

engine.scmInit.resamplingScheme

ResamplingScheme: STRATIFIED|MULTINOMIAL

false

default value: STRATIFIED

engine.scmInit.temperatureSchedule

TemperatureSchedule: AdaptiveTemperatureSchedule|FixedTemperatureSchedule|fully qualified

false

default value: AdaptiveTemperatureSchedule

Algorithm selecting annealing parameter increments.

engine.scmInit.temperatureSchedule.nudgeFromZeroIfOutOfSupport

double

false

default value: 1e-10

If all particles are out of support at first iteration, nudge the temperature a bit so that support constraints kick in.

engine.scmInit.temperatureSchedule.threshold

double

false

default value: 0.9999

Annealing parameter is selected to get the (conditional) ESS decrease specified by this parameter.

engine.scmInit.temperatureSchedule.useConditional

boolean

false

default value: true

See Zhou, Johansen and Aston (2013).

engine.statisticRecordedMaxChainIndex

int

false

default value: 100

Use when huge number of chains are utilized. Statistics like energy, logLikelihood are only recorded for the first so many indices to avoid excessive output size.

engine.targetAccept

Double

false

optional

engine.thinning

10

int

true

default value: 1

Collect statistics every thinning iteration (=1 to always collect, >1 to save hard drive space)

engine.usePriorSamples

boolean

false

default value: true

excludeFromOutput

List: Space separated items or "file " to load from newline separated file

false

optional

experimentConfigs.configFile

File

false

optional

If set, use those arguments in provided file that do not appear in the provided arguments.

experimentConfigs.description

String

false

optional

Documentation for this run.

experimentConfigs.managedExecutionFolder

boolean

false

default value: true

Automatically organize results into subdirectories of 'results/all'?

experimentConfigs.maxIndentationToPrint

int

false

default value: inf

Use -1 to silence all output done through blang.System.*

experimentConfigs.recordExecutionInfo

boolean

false

default value: true

Record information such as timing, main class, code version, etc for this run?

experimentConfigs.recordGitInfo

true

boolean

true

default value: false

experimentConfigs.resultsHTMLPage

boolean

false

default value: true

experimentConfigs.saveStandardStreams

boolean

false

default value: true

Save combined standard out and err into a file?

experimentConfigs.tabularWriter

TabularWriterFactory: CSV|Spark|fully qualified

false

default value: CSV

experimentConfigs.tabularWriter.compressed

boolean

false

default value: false

experimentConfigs.uniqueExperimentDirectoryName

results/all/ChallengerSpiked--1061119086

String

true

optional

initRandom

Random

false

default value: 1

model

ex.reg.ChallengerSpiked$Builder

ModelBuilder: fully qualified

true

model.incidents

file data/challenger/incidents.csv

List: Space separated items or "file " to load from newline separated file

true

model.intercept

RealVar: A number or NA

false

optional

model.prediction

IntVar: An integer or NA

false

optional

model.temperatures

file data/challenger/temperatures.csv

List: Space separated items or "file " to load from newline separated file

true

postProcessor

DefaultPostProcessor

PostProcessor: DefaultPostProcessor|NoPostProcessor|fully qualified

true

default value: NoPostProcessor

postProcessor.blangExecutionDirectory

File

false

optional

When called from Blang, this will be the latest run, otherwise point to the .exec folder created by Blang

postProcessor.boldTrajectory

Integer

false

optional

postProcessor.burnInFraction

double

false

default value: 0.5

postProcessor.eleDiagnostic

boolean

false

default value: false

postProcessor.essEstimator

EssEstimator: Batch|ACT|AR|fully qualified

false

default value: Batch

postProcessor.essEstimator.referenceFile

File

false

optional

csv file containing reference values for the mean and sd

postProcessor.essEstimator.referenceMeanColumn

String

false

default value: mean

Look for this column name for reference mean.

postProcessor.essEstimator.referenceSDColumn

String

false

default value: sd

Look for this column name for reference sd.

postProcessor.experimentConfigs.configFile

File

false

optional

If set, use those arguments in provided file that do not appear in the provided arguments.

postProcessor.experimentConfigs.description

String

false

optional

Documentation for this run.

postProcessor.experimentConfigs.managedExecutionFolder

boolean

false

default value: true

Automatically organize results into subdirectories of 'results/all'?

postProcessor.experimentConfigs.maxIndentationToPrint

int

false

default value: inf

Use -1 to silence all output done through blang.System.*

postProcessor.experimentConfigs.recordExecutionInfo

boolean

false

default value: true

Record information such as timing, main class, code version, etc for this run?

postProcessor.experimentConfigs.recordGitInfo

boolean

false

default value: false

postProcessor.experimentConfigs.resultsHTMLPage

boolean

false

default value: true

postProcessor.experimentConfigs.saveStandardStreams

boolean

false

default value: true

Save combined standard out and err into a file?

postProcessor.experimentConfigs.tabularWriter

TabularWriterFactory: CSV|Spark|fully qualified

false

default value: CSV

postProcessor.experimentConfigs.tabularWriter.compressed

boolean

false

default value: false

postProcessor.experimentConfigs.uniqueExperimentDirectoryName

String

false

optional

postProcessor.facetHeight

double

false

default value: 2.0

In inches

postProcessor.facetWidth

double

false

default value: 4.0

In inches

postProcessor.highestDensityIntervalValue

double

false

default value: 0.9

postProcessor.imageFormat

String

false

default value: pdf

postProcessor.rCmd

String

false

default value: Rscript

postProcessor.referenceSamples

File

false

optional

A directory containing means and variance estimates from a long run, used to improve ESS estimates; usually of the form /path/to/[longRunId].exec/summaries

postProcessor.runPxviz

boolean

false

default value: false

Run visualizations based on Processing (may need extra steps to perform in a 'headless' environment)

printAccessibilityGraph

boolean

false

default value: false

samplers.additional

SamplerSet: Fully qualified instances of blang.mcmc.Sampler

false

Samplers to be added.

samplers.excluded

SamplerSet: Fully qualified instances of blang.mcmc.Sampler

false

Samplers to be excluded (only useful if useAnnotation = true).

samplers.useAnnotation

boolean

false

default value: true

If the arguments of the annotations @Samplers should be used to determine a starting set of sampler types.

stripped

boolean

false

default value: false

Stripped means that the construction of forward simulators and annealers is skipped

treatNaNAsNegativeInfinity

boolean

false

default value: false