io.improbable.keanu.algorithms.mcmc

Class NetworkSamplesGenerator

java.lang.Object

io.improbable.keanu.algorithms.mcmc.NetworkSamplesGenerator

public class NetworkSamplesGenerator
extends java.lang.Object

Constructor Summary

Constructors

Constructor and Description
NetworkSamplesGenerator(SamplingAlgorithm algorithm, java.util.function.Supplier<StatusBar> statusBarSupplier)

Method Summary

Modifier and Type	Method and Description
NetworkSamplesGenerator	downSampleInterval(int downSampleInterval)
NetworkSamplesGenerator	dropCount(int dropCount)
NetworkSamples	generate(int totalSampleCount)
int	getDownSampleInterval()
int	getDropCount()
java.util.stream.Stream<NetworkSample>	stream()

Methods inherited from class java.lang.Object

clone, equals, finalize, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait

Constructor Detail

NetworkSamplesGenerator

public NetworkSamplesGenerator(SamplingAlgorithm algorithm,
                               java.util.function.Supplier<StatusBar> statusBarSupplier)

Method Detail

getDropCount

public int getDropCount()

dropCount

public NetworkSamplesGenerator dropCount(int dropCount)

Parameters:

dropCount - the number of samples to drop before collecting anything. If this is zero then no samples will be dropped before collecting.

Returns:

this NetworkSamplesGenerator set to drop the specified number of samples

Throws:

java.lang.IllegalArgumentException - when dropCount is less than zero

getDownSampleInterval

public int getDownSampleInterval()

downSampleInterval

public NetworkSamplesGenerator downSampleInterval(int downSampleInterval)

Parameters:

downSampleInterval - collect 1 sample for every downSampleInterval. If this is 1 then there will be no down-sampling. If this is 2 then every other sample will be taken. If this is 3 then 2 samples will be dropped before one is taken.

Returns:

this NetworkSamplesGenerator set to down-sample at the specified downSampleInterval

Throws:

java.lang.IllegalArgumentException - when downSampleInterval is less than or equal to zero

generate

public NetworkSamples generate(int totalSampleCount)

Parameters:

totalSampleCount - The total number of samples to generate. This is the total before any dropping or down-sampling is done. If you drop 10 and down sample 2 and request a totalSampleCount of 100 then you would take 100 samples, drop 10 and then take every other sample resulting in 45 samples returned.

Returns:

Samples after dropping and down-sampling.

stream

public java.util.stream.Stream<NetworkSample> stream()

Returns:

A stream of samples starting after dropping. Down-sampling is handled outside of the stream (i.e. the stream will be the final result after dropping and down-sampling)