373ebbdd56
Enabling AIS KSG calculator to have underlying KSG algorithm changed via the "ALG_NUM" property
2018-08-24 14:47:21 +10:00
7f4dfa7970
Added bias correction property for Gaussian MI to AutoAnalyser GUI
2018-08-22 16:00:52 +10:00
323ef47475
Adding auto-embedding properies to AutoAnalyser GUI Active Info Storage for all continuous calculators (was only in KSG before)
2018-08-22 15:53:09 +10:00
4b6fc39c72
Fixed tool tip pop-ups for Discrete and Binned estimators in AutoAnalyser GUI (they were using spurious values from a continuous calculator before)
2018-08-21 20:56:58 +10:00
8c5aa51f57
AutoAnalyser: Added drop-down menus (aka comboboxes) for parameters whose values are amenable to selection in this way. All child classes updated to be compatible. GUI size adjusted here also.
2018-06-26 12:22:05 +10:00
7fafabe451
Extending MI discrete calculator to allow different bases for each variable. This necessitates immediate removal of the (int,int) constructor (where the 2nd argument was the time difference), this will now be confusing between (base, timeDiff) and (base1, base2). In time we may bring it back, after we can be reasonably comfortable people have switched away from using (base, timeDiff).
2018-06-20 10:55:21 +10:00
4170339426
Moving check of dimensionality for continuous variables in mixed CMI calculator common to the main setObservations() method
2018-06-19 23:57:41 +10:00
ca909dc60f
Adding check of dimensionality of observations supplied to multivariate AIS calculators when univariate is expected.
2018-06-19 23:45:00 +10:00
5bde6f295b
Fixes issue #70 by providing setObservations(double[], int[], double[]) methods for the mixed CMI calculators (i.e. allowing univariate arrays to be passed in if dimension 1 was defined for both the continuous data and conditional). Unit test validating is included.
2018-06-19 23:08:13 +10:00
643212840a
Making indenting style consistent through file
2018-05-18 08:56:47 +10:00
dfe7ef0334
Altering AIS Multivariate Via Mutual Info calculator -- and child classes, now including kernel estimator -- to support auto-embedding primarily via the parent methods of the univariate AIS calculator.
...
Also includes patching functionality when dimension == 1 to always use the underlying AIS univariate calculator consistently, and adding missing methods on adding observations with validity array.
Also includes some minor alterations to error messages.
Gaussian and Kernel Multivariate AIS calculators have the computeAdditionalBiasToRemove() method implemented now to allow this; Gaussian calculator also adds the analytic computeSignificance() method, whilst Kernel calculator also adds a property for the number of surrogates to use in bias correction.
2018-05-16 22:42:32 +10:00
fcd30c6716
Minor changes to Javadocs for AIS kernel
2018-05-16 22:28:19 +10:00
a649b38270
Patched new section of AIS calculator via MI, whereby addObservationsWithGivenParams() when called with a validity[] array did not compute valid start and end time pairs for the candidate k and tau, but did so for the k and tau set in the properties. Fixed so that the candidate k and tau can be supplied.
2018-05-16 14:39:54 +10:00
e8603b08f8
Moving auto-embedding for AIS (Ragwitz and maximum bias-corrected AIS methods) from out of Gaussian and KSG calculators and into the common AIS calculator via MI class. The common implementation then allows us to introduce auto-embedding for the AIS kernel estimator as well (included requiring adding a property for the number of surrogates to use to compute the bias for this one).
...
These changes now incorporate auto-embedding for all AIS continuous calculators, partially addressing issue #38
2018-05-16 14:20:08 +10:00
1c591925bd
Added auto-embedding to Gaussian AIS calculator, with both Ragwitz and maximum bias-corrected AIS methods. Bias-correction implemented via the Gaussian analytic surrogates. Involves defining new properties, setProperty, getProperty and preFinaliseAddObservations() to do the embedding. Unit test included also, mirroring unit testing for KSG AIS (which used linear Gaussian variables).
2018-05-15 17:35:06 +10:00
48b48ab845
Changing AIS Via Mutual Info internal addObservationsAfterParamsDetermined method to addObservationsWithGivenParams - taking k and tau as arguments rather than using the internal ones. This allows the method to be called by auto-embedding in the child classes as well (better code re-use ready for extending auto-embedding)
2018-05-15 17:32:50 +10:00
9552091fca
Adding Javadoc on header for neighbour counts method in KSG MI estimator 1
2018-05-15 17:28:39 +10:00
0b70e92efc
Added Bias-correction property to Gaussian MI and conditional MI calculators, including set and getProperty and an implementation in the calculations. This implements bias-correction by substracting the bias (of the analytic chi^2 based null distribution) from the calculations.
2018-05-13 22:29:17 +10:00
c0b9d736d7
Added methods to retrieve mean and standard deviation of the Chi^2 null distribution, as well as (empirical) unit test for this.
2018-05-13 22:02:46 +10:00
46a9785da2
In surrogates for MI and CMI also turning adding noise off since this will have been done in the initial calculation already, and will just broaden the noise here.
2018-05-12 22:35:54 +10:00
28ba409ff6
Turning off normalisation when computing surrogates in Common CMI and MI calculators, because normalisation has already been carried out (and if one variable had no variance, this will inflate the values back to original scale)
2018-05-12 21:30:39 +10:00
0e4455b2fd
Corrects the access at one point to the bins for the data points in the multivariate kernel estimator, which should use an IntArray object but did use an int[] object to access . Fixes #69 .
2018-05-10 20:20:02 +10:00
860d43dbca
Adding additional error message for Exception during KSG Active Info Storage auto-embedding
2018-05-07 23:15:33 +10:00
1f625b59f0
AutoAnalyser: fixing bug where column numbers for data are all set to zero if the user unclicks the "compute result?" button
2018-05-07 22:57:10 +10:00
d1bba0e4c1
Adding computeLocalOfPreviousObservations() to continuous Entropy estimator interface and all underlying implementations. Added unit tests that locals should average back ok. Also fixing multivariate Entropy estimator interface to implement the univariate interface also (and fixing underlying implementations to comply)
2018-04-27 11:20:25 +10:00
bf0062b902
Switching new debug method in KSG conditional MI calculator 1 to be publicly accessible
2018-04-26 11:43:04 +10:00
7d76f82bb2
Adding partialNeighbourCountFromObservations() method to KSG conditional MI calculator 1 for debugging investigations into the neighbour counts
2018-04-26 11:24:56 +10:00
df8eec27cd
Added MAX_CORR_AIS_AND_TE embedding to univariate KSG TE calculator.
2018-04-22 22:25:05 +01:00
f8bca3275d
Fixed docs for new MAX_CORR_AIS_AND_TE embedding method.
2018-04-22 20:45:06 +01:00
02dad26a94
Added brief mention of AUTO_EMBED_METHOD_MAX_CORR_AIS_AND_TE to javadocs.
2018-02-27 20:29:39 +00:00
5f6671aa2b
Added AUTO_EMBED_METHOD_MAX_CORR_AIS_AND_TE to multivariate KSG TE.
2018-02-27 20:18:04 +00:00
550ff793eb
Fixed bug in KSG TE multivariate embeddings and setObservations.
2018-02-27 20:14:08 +00:00
8be6a037af
Added auto-embedding methods to multivariate KSG TE calculator.
2018-02-25 19:23:09 +00:00
ce4b1599c6
Added MAX_CORR_AIS embedding method to multivariate KSG AIS.
2018-02-25 18:57:15 +00:00
75bb2c814a
Added addObservations-related methods to multivariate TE calculators.
...
This is needed to implement auto-embedding methods later.
2018-02-25 18:54:36 +00:00
b0fc309d6a
Add overloadings for 1d continuous variables in KSG mixed calc.
2018-01-12 22:22:46 +00:00
0278f95ae9
Enabled use of USE_GPU property for KSG calculators in the AutoAnalysers for CMI, TE, CTE and AIS
2017-12-30 12:03:17 +11:00
64f1142b40
Added argument to choose which variable to reorder in GPU CMI code.
2017-12-19 20:42:58 +00:00
65ac0e9ff8
Removed unnecesary overloaded method in KSG CMI calc.
2017-12-19 20:41:11 +00:00
2f1cd192b8
Fixed small typo in Java KSG CMI calculator.
2017-12-18 17:50:37 +00:00
d0304ae0c4
Added Java-side JNI functions and ensureKdTreesConstructed to KSG CMI.
2017-12-12 11:19:40 +00:00
f4ca442de4
Now KSG MI calc does not build KdTrees if GPU is going to be used.
2017-12-12 11:10:50 +00:00
d010f32635
Updated getProperty and removed spurious dependency in KSG MI calc.
2017-12-12 11:04:32 +00:00
eabd7f3701
Fixed typo in Kozachenko entropy calculator.
2017-11-28 16:58:13 +00:00
444fb70801
Added addObservations-type functions to Kozachenko entropy calculator.
2017-11-28 16:56:51 +00:00
e290040d8d
Added docs to Kozachenko entropy calculator.
2017-11-28 16:26:46 +00:00
35df6ca3da
Kozachenko entropy estimator now adds noise to data by default.
2017-11-28 16:04:09 +00:00
9c96ceb850
Fixed logic for when parameter values (in particular auto-embedded properties) are written back into the properties table after the calculation. This was happening only when we had the "all pairs" option selection, when it should only happen when this is not selected.
2017-11-28 12:36:06 +11:00
589d51674e
Altering the escaped data filename in AutoAnalyser to be properly escaped using non-regex replace, and also rolling back the use of escaping to only Java (Matlab and Python on windows seem fine with the non-escaped filenames, for e.g. the paths earlier in the generated code)
2017-11-27 10:19:36 +11:00
3bfbaa7ad3
In AutoAnalyser escaping data filenames when they are written to the generated code. This is important for windows filenames. Am not sure why it didn't come up before as an issue though.
2017-11-27 09:57:07 +11:00
61f4bf3276
Adding getProperty lines to handle USE_GPU property for KSG MI calculator
2017-11-27 09:26:19 +11:00
db0503d763
Having AutoAnalyser continue with the calculation where the generated code cannot be written
2017-11-26 18:04:29 +11:00
df8724b872
Altered AutoAnalyserLauncher to either auto-detect jar location or assume demos/AutoAnalyser folder is current location (if a command line argument is given). Similarly, altered AutoAnalyser to either take location of demos/AutoAnalyser folder, or assume it is the current folder.
2017-11-26 01:10:30 +11:00
fd804d0d0c
Added properties for running GPU calculation to MI AutoAnalyser
2017-11-26 01:07:19 +11:00
69af7252cd
Added debug print on working directory to AutoAnalyser startup
2017-11-25 00:15:37 +11:00
ddf3b4de0a
Moving AutoAnalyser java files into the main source location rather than in the demos location. This commit includes the moving of the files themselves. Further commits will alter the ant script and run scripts to have correct classpath, etc.
2017-11-24 21:07:33 +11:00
142fbb4541
Merge branch 'master' of github.com:jlizier/jidt
...
Merging in Pedro's mixed Kraskov changes, plus further work on GPU for Kraskov MI
2017-11-24 15:30:20 +11:00
9e77ebdadf
Tweak to method to print out an array of ints
2017-11-22 20:49:05 +11:00
1bb67f0840
Adding neighbour search utilities in preparation for attempting fast surrogate generation (performing multiple neighbour searches at once where we can); in particular adding a countPointsWithinR with a remapping of the point's indices. Unit test added as well for this.
2017-11-22 20:48:30 +11:00
446ac4ae59
Merge branch 'master' into gpu
2017-11-21 14:58:15 +00:00
c5c38335ef
Merge pull request #58 from pmediano/master
...
Major improvements to KSG mixed (continuous-discrete) MI calculator.
2017-11-22 00:23:10 +11:00
ecda70f8e9
Hard-setting dynCorrExclTime to 0 in KSG mixed calc.
...
Previous implementation was incomplete due to a mismatch between the
sample indices in the full and marginal KdTrees. Some code has been left
to guide future development.
2017-11-20 14:47:00 +00:00
25df49fa5a
KSG mixed calc now allocates memory for locals only if requested.
2017-11-20 14:26:25 +00:00
8f169171e1
Fixed small bug in KSG mixed calc surrogates.
...
Surrogate calculator was applying timeDiff twice, so surrogate
dataset had abs(timeDiff) less observations than it should.
2017-11-20 14:14:49 +00:00
d40024e1cd
Allow negative timeDiff in KSG mixed calc.
2017-11-20 14:02:00 +00:00
0e27dbcbc2
Fixed default value of dynamic exclusion window in Kernel MI calculator to be 0. Technically it is zero (because dynCorrExcl boolean is set to false, but gets reported as 100 because the integer value of dynCorrExclTime was not set to 0 itself)
2017-09-02 20:18:36 +10:00
ed71502bc2
Remove old cudaLibraryLoad code and unnecessary dependencies.
2017-08-31 16:22:12 +01:00
83e77e8b3a
Merge Joe's master into Pedro's master with KSG mixed changes.
2017-08-30 17:36:32 +01:00
f56ac6e69e
Fix bug with Theiler window in KSG mixed calc.
2017-08-30 13:30:30 +01:00
5961fb6246
Add Theiler window and jitter to KSG mixed calc.
2017-08-30 12:17:02 +01:00
d36c803e41
Added utilities to convert between estimate values and p-values for an analytic null distribution in bulk (array calls)
2017-08-30 16:24:17 +10:00
626293b84d
More docs for KSG mixed calc.
2017-08-30 01:19:54 +01:00
e11218631e
Added myself as author of KSG mixed calculator.
2017-08-29 23:56:28 +01:00
49afa343fc
Removed old variables and functions from KSG mixed, added docs.
2017-08-29 23:55:10 +01:00
19f2c5abbc
Performance tweaks for TE Discrete, which should make a difference when the state space is large in comparison to the number of samples.
2017-08-28 00:36:24 +10:00
c59d932a44
Misc spacing/comment patches
2017-08-23 00:19:43 +10:00
b2e3ae1ca0
Added missing getProperty() method to Conditional TE calculator Kraskov
2017-08-23 00:19:09 +10:00
0e40ec2401
Initialising conditional TE calculator to have one conditional dimension by default instead of none. Also fixing the way the conditional parameters are printed via getProperty() when they are null.
2017-08-23 00:18:41 +10:00
4db008ce33
For Conditional MI calculators (sontinuous), adding setObservations and addObservations method signatures which take univariate arrays (only work if initialised dimensionalities are univariate) into the interface, and the common base class. This is in preparation for the CMI AutoAnalyser
2017-08-22 21:26:44 +10:00
4d6fc1a572
Updated Kozachenko-Leonenko multivariate Entropy calculator to implement EntropyCalculator interface, in preparation for Entropy AutoAnalyser
2017-08-21 14:56:20 +10:00
086bee5945
Making continuous MultiInfoCalculator classes implement the InfoMeasureCalculatorContinuous interface. For the interfaces, this means removing methods where duplicated. For implementing classes, this means adding the missing methods.
2017-08-18 23:42:43 +10:00
057f17e338
Making continuous PredictiveInfoCalculator classes implement the InfoMeasureCalculatorContinuous interface. For the interfaces, this means removing methods where duplicated. And fixed the common implementing class to have the missing getProperty method.
2017-08-18 23:11:37 +10:00
65c7cd99cc
Making continuous EntropyCalculator and EntropyCalculatorMultiVariate classes implement the InfoMeasureCalculatorContinuous interface. For the interfaces, this means removing methods where duplicated. Also added NUM_DIMENSIONS property to EntropyCalculatorMultiVariate interface, so that these calculators can have an initialise() method which takes no parameters. Fixed all implementing classes to have any methods that they were missing.
2017-08-18 20:18:29 +10:00
d6bd16546b
Added new interface InfoMeasureCalculatorContinuous to capture common methods for continuous calculators. Also adapted most continuous calculators to implement this, which involved in many cases removing duplicate definitions of these methods in the interfaces for these measures. For ConditionalMI calculator, this meant we needed to add an implementation of the zero-argument initialise() call also. Still need to do MultiInfo, PredictiveInfo and Entropy in future, as they're missing a few methods.
2017-08-18 16:54:55 +10:00
04351498aa
Changed my mind and pulled EmpiricalNullDistributionComputer in as being extended/implemented by ChannelCalculatorDiscrete. (This does make sense, since "extend" for an interface really means implements, it's not so much a child class). This necessitated removing the interface from explicitly being named in the definitions of the discrete MI and TE calculators since it's there implicitly.
2017-08-18 15:40:00 +10:00
3e64fd28bd
Altering various continuous calculators to implement the EmpiricalNullDistributionComputer interface (where they're already implementing computeSignificance() etc.). Also altered the EmpiricalNullDistributionComputer methods to throw Exceptions, since the continuous calculators generally do this (and doesn't harm the discrete ones). Also involved implementing the methods in ConditionalMIMultiVariateCommon by selecting to permute the first variable by default.
2017-08-18 15:31:27 +10:00
60105e6d10
ActiveInformationCalculatorDiscrete was stuck in the past and returning results computing with the log using the base of the alphabet size (everything else uses bits). I'm not sure how I missed this one. Fixed now.
2017-08-18 14:07:26 +10:00
d9e43d966a
Added implementation of EmpiricalNullDistributionComputer to various discrete calculators which implement computeSignificance() etc. Also involved removing the method from ChannelCalculatorDiscrete, as there's no way of having it (an interface) specify implementing an interface without extending it which I didn't think was completely logical. So ChannelCalculators can always be checked against implementing EmpiricalNullDistributionComputer if one wants to use computeSignificance with them. This also required adding the computeSignificance(int[][]) method to ConditionalTECalculatorDiscrete and TECalculatorDiscrete
2017-08-18 13:58:38 +10:00
d77a9f274e
Added interface ChannelCalculator for MutualInfoCalculatorMultiVariate; this should have always been there but not all calculators implemented the univariate methods. It previously only implemented ChannelCalculatorMultiVariate. Added those methods into MutualInfoMultiVariateCommon, which provides the base implementation for all required calculators, so all are now taken care of. This means MI and TE can both be fully used in one interface with the set/addObservations methods.
2017-08-18 13:54:10 +10:00
70740c9753
Added new interface EmpiricalNullDistributionComputer. Will separately alter discrete and continuous calculators to implement this class where they are implementing the required measures.
2017-08-18 13:49:09 +10:00
fa6307b4f2
Fixing javadoc reference in AnalyticNullDistributionComputer to correct class
2017-08-18 13:48:03 +10:00
bfe8156584
Add KDTrees to computeLocalUsingObservations in KSG mixed calc.
2017-08-16 19:28:24 +01:00
641d17ec24
Fix bug with normalisation in KSG mixed and change unittest accordingly.
2017-08-16 19:18:51 +01:00
7635cf8689
Added computeLocalOfPreviousObservations to KSG mixed.
...
It follows the same pattern as the continuous MI: there is a
computeFromObservations method that returns either locals or average
based on a flag.
2017-08-16 14:52:54 +01:00
2d42e6ebad
Removed unused function from KSG mixed.
2017-08-16 14:39:53 +01:00
23bb573bb1
Replace computeSignificance method in KSG mixed with new one based on clone().
2017-08-16 14:33:47 +01:00
8251bdc1cb
Removed unused variables from KSG mixed.
2017-08-16 13:35:03 +01:00
f55a7bd961
Add KdTrees to main compute() method in KSG mixed.
2017-08-16 13:31:18 +01:00
bad50ce663
KSG mixed now ignores batches of data shorter than timeDiff.
2017-08-16 13:27:05 +01:00
b5d2b7e367
KSG mixed now throws error if discrete data is out of range.
2017-08-16 13:25:44 +01:00
jlizier