natas_hw
/
jidt
mirror of https://github.com/jlizier/jidt
0
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity
825 Commits 5 Branches 6 Tags 65 MiB
Commit Graph

414 Commits

Author SHA1 Message Date
Joseph Lizier b02760ddd3 Adding overloads on setObservations and addObservations for MI and TE calculators to handle one variable univariate and one variable multivariate 2021-11-15 10:58:59 +11:00
Joseph Lizier 7d7291fb9d Implementing Analytic null distributions for discrete conditional TE estimator 2021-11-02 23:11:45 +11:00
Joseph Lizier 6f43dfb620 Altering the python-java jpype data conversion in AutoAnalyser to work properly with jpype 0.7 and upwards 2021-10-08 16:03:14 +11:00
Joseph Lizier 21ae0bdeaa Fixing logic error in printing whether GPU calculation was falling back to CPU 2021-10-08 11:28:37 +11:00
Joseph Lizier 650159661d Patching conditional MI calculator to properly allow null or empty conditionals if dimension of conditionals is 0 2021-09-06 10:23:31 +10:00
Joseph Lizier aa8148eca9 Updates to KL entropy estimator: removing NORMALISE property, and adding method for cross entropy 2021-08-23 09:09:49 +10:00
Joseph Lizier ef7cfbb525 Fixed missing " in comment 2021-08-06 17:43:56 +10:00
Joseph Lizier 3222b5a629 Implementation and unit test for KSG MI calculation with new samples (both algorithms 1 and 2) 2020-10-30 16:21:10 +11:00
Joseph Lizier 0606f8ab39 Cleaning up CMI Kraskov for new samples, including fixing some comments, logic of not using GPU for this, and if no conditional counting all point as a conditional match 2020-10-30 16:19:31 +11:00
Joseph Lizier b5a6fa92c2 Fixing min and max of local CMI values 2020-10-29 13:45:25 +11:00
Joseph Lizier 44e53bc846 Updating error messages for kdTree 2020-10-29 13:39:40 +11:00
Joseph Lizier 34161a2e6d Adding non-overloaded method signatures for multivariate arrays, so that the jpype python-java bridge can resolve which method signature to use more directly via these 2020-05-22 14:42:26 +10:00
Joseph Lizier bf207f866e Patched error in computing start and end times for valid observation sequences in conditional TE calculators (with validity booleans) 2020-05-21 00:57:34 +10:00
Joseph Lizier d0a0fca40c Added non-overloaded method calls for conditionalTE continuous' addObservations() method calls with validity booleans - this is for JPype from Python which seems unable to resolve overloads of double[] and double[][], when more than one variable changes in this way 2020-05-16 12:18:57 +10:00
Joseph Lizier cbcca8d0ff fixing addedMoreThanOneObservationSet for the MultiInfoCalculator 2020-05-15 17:35:54 +10:00
Joseph Lizier 510f999d2e Adds addObservations calls with validity arrays for conditional transfer entropy 2020-05-15 17:34:00 +10:00
Joseph Lizier 61ae6fb40b Minor updates to AutoAnalyser to put fixtures in place for array conversion to Python with eventual handling of 2D arrays (code isn't really changed at the moment, but has methods to make this easy later) 2019-07-25 23:56:56 +10:00
Joseph Lizier 2ab3ac01bb Adding non-overloaded method signatures for adding 1D vs 2D observations for common class for continuous MI and CMI estimators, since JPype 0.7 does not seem able to resolve overloaded 1D vs 2D arrays any longer 2019-07-25 23:11:44 +10:00
Joseph Lizier 1667b9fe7a Added utility for subsampling rows from 2D matrix 2019-07-25 14:36:54 +10:00
Joseph Lizier 1dc2dc8b86 Updating all discrete calculators (except SeparableInfo, since it's outmoded) to have a default empty constructor, with an overloaded initialise method added that provides all relevant properties. Fixes #77, and provides a first step for #66. Also aligned PredictiveInfo and ConditionalTE calculators to use the appropriate super classes. 2019-07-25 14:29:51 +10:00
Joseph Lizier 17bf0e0be7 Updating octave-java interface to use non-overloaded method signatures for int and boolean arrays (this seemed to have caused an issue on some versions with ints being converted to boolean first, thus losing all values except 0-1) 2019-07-23 11:33:04 +10:00
Joseph Lizier 1db8a2ac63 Making local computation for CMI Gaussian calculator store the lastAverage if it was called with the previous observations 2019-05-17 22:47:16 +10:00
Joseph Lizier 681c9196ee Added methods to MatrixUtils (plus unit tests) for adding/removing/swapping sample points into existing means and covariances 2019-05-17 22:27:30 +10:00
Joseph Lizier 9f9c79bc95 Handling infinites in Chi square CDF function properly 2019-05-17 22:24:54 +10:00
Joseph Lizier 8542d217ea Added support for Chi^2 analytic distribution to support degrees of freedom 0 (this will handle e.g. where a source had no independent dimensions) 2019-05-17 22:20:54 +10:00
Joseph Lizier fce1b34a5c Adding NORMALISE and NOISE_LEVEL_TO_ADD properties to all conditional mutual information calculators for continuous-valued data (extends this capability from only KSG to Gaussian as well) 2019-04-03 00:12:00 +11:00
Joseph Lizier d9db7a15ab Further clarifications for including NORMALISE and NOISE_LEVEL_TO_ADD properties to all mutual information calculators, and handling linear redundancy sub-cases 2019-04-03 00:07:05 +11:00
Joseph Lizier b1437452e4 Adding NORMALISE and NOISE_LEVEL_TO_ADD properties to all mutual information calculators for continuous-valued data (extends this capability from only KSG to Gaussian and kernel as well, the latter already had NORMALISE) 2019-04-02 12:38:17 +11:00
Joseph Lizier 988d32de70 Added bug fix within recent changes to MatrixUtils Cholesky decomposition calculation, along with unit testing of the linear dependency combinations for issue #17 2019-03-31 23:21:39 +11:00
Joseph Lizier 2a0024ad83 Fixes issue #17: Handling sub-cases for linear redundancy within and across variables in the linear-Gaussian mutual information estimator. This is done by detecting such redundancies and either returning 0 or infinity as the requisite result. Mirrors how this is done for conditional MI. 2019-03-29 00:01:36 +11:00
Joseph Lizier 66676a2692 A rewrite of parts of the linear Gaussian conditional MI estimator, in order to more deftly handle linear dependencies within variables 1 and 2, and between each of them and the conditional. Previously we removed sub-variables of those arbitrarily, now the removal is targetted to those sub-variables that are problematic. Also required some variable name changes to reflect different ordering of how variables and the conditionals are concatenated in arrays. 2019-03-28 23:58:53 +11:00
Joseph Lizier d58c393c53 Added methods to MatrixUtils to make a Cholesky decomposition of independent components only (useful for MI and conditional MI calculations), with a required update to the NonPositiveDefiniteMatrixException to include a field defining which row in the matrix was a problem. Also includes code to convert between native int[] arrays and ArrayList<Integers>, and new method signatures for column selection from matricies. 
Also added new unit tests for the Cholesky decomposition.
 2019-03-28 23:52:47 +11:00
Pedro Martinez Mediano c616ba55d4 Added link to wiki in GPU loader error message. 2018-11-25 19:25:33 +02:00
jlizier 16015e0f12 Nearest neighbour searchers now return number of points found for findPointsWithinR as well as marking them in input arrays. Also added new method sumDistanceAboveThresholdForPointsWithinRs() for the univariate searcher (to be used in spiking TE estimator under development) 2018-11-24 21:16:36 +11:00
jlizier 8909c23fcc Incorporated auto-embedding in the TE multivariate via conditional MI common class. Much of the code is moved up from the TE multivariate KSG estimator; now the functionality is provided for multivariate Gaussian as well. Also necessitated adding the max_cor_num_surrogates property to TE multivariate Gaussian, and took the opportunity to make much of the whitespace here consistent, and unit tests added for Gaussian (tweaked slightly for KSG) 2018-10-18 00:58:17 +11:00
jlizier 42f8d01e26 Adding property of number of dimensions for the AIS multivariate calculator (and implemented in the via MI common class). Needed this to make multivariate TE embedding a bit neater, and it should be there anyway. 2018-10-18 00:51:37 +11:00
jlizier e1bad39e4e Added proper full definitions for the methods of the AIS multivariate interface; much of this is achieved by extending the univariate AIS interface (which mandates that the univariate methods must be supported). No current child classes required any changes as they all supported these already. Removed superfluous documentation in the AIS multivariate via MI class (as well as fixing whitespace inconsistencies therein) 2018-10-17 23:37:43 +11:00
jlizier da418c31a0 Added new auto-embedding capability for TE Gaussian into the AutoAnalyser GUI demo. Also added new auto-embedding drop down option of Max corrected AIS + TE for KSG as well, and debugged the getProperty returning of the number of nearest neighbours for Ragwitz criteria now that this occurs in the common superclass instead of in KSG (and gave this a reasonable default of 4) 2018-10-17 14:23:20 +11:00
jlizier a34bce25ba Enabled auto-embedding for TE Gaussian. Did so by bringing up auto-embedding for TE functionality up from the KSG estimator to the via Conditional MI class. Also added new property to Gaussian TE for number of surrogates to use for bias correction in embedding (if not using analytic bias correction), like Gaussian AIS. This also necessitated adding an empty preFinaliseAddObservations() method to the TE Gaussian multivariate estimator, to ensure it did not yet try to autoembed until that is enabled in the multivariate calculator. Unit tests included here as well (included using more samples for TE KSG autoembedding to ensure we get the correct answer more reliably -- should probably add a stronger effect for that too). 2018-10-17 13:49:09 +11:00
jlizier efb8243ed7 Altering TE Kraskov to do auto-embedding properly when we have added multiple observations with validity vectors. Also taking the opportunity to re-engineer the internals to lay groundwork for auto-embedding function to be shared with the Gaussian estimator at a later stage. Unit tests added here as well for the above. 2018-10-15 20:56:50 +11:00
jlizier 2ff6d8aeec Added getProperty for AIS Kraskov multivariate. Need to re-engineer this class for proper code re-use anyway. 2018-10-15 14:38:46 +11:00
jlizier 3aa1493d7f Added addObservations() method with sourceValid and destValid boolean arrays to TransferEntropyCalculatorViacondMutualInfo class 2018-09-21 10:34:01 +10:00
jlizier af1173ba5b Patching local MI discrete computation when we have a time difference of > 0 (we were getting an ArrayIndexOutOfBoundsException before) 2018-09-05 13:43:21 +10:00
jlizier 9dbe2f8578 Added to AutoAnalyser GUI for AIS surrogate-based bias correction (parameter being the number of surrogates) for max AIS corrected auto embedding, for kernel estimator as well as Gaussian (as an alternative to analytic). Also includes the implementing code for AIS Gaussian (was already committed for kernel) 2018-08-27 14:24:05 +10:00
jlizier ad31af03a7 Added throws Exception for computeSignificance() on multivariate Gaussian AIS calculator, because of throws clause introduced on underlying MI estimator 2018-08-27 13:21:29 +10:00
jlizier f502497256 Added bias correction option to AutoAnalyser GUI for Gaussian AIS, TE and CTE estimators 2018-08-27 13:19:00 +10:00
jlizier 7f9b1c0812 Patching bias correction for Guassian MI and CMI (some for MI was in line with previous work for CMI, which required extending here). Unit tests included. 2018-08-27 13:17:58 +10:00
jlizier fdec72aeff Added tracking of bias correction to ChiSquaredMeasurementDistribution, so the distribution is adjusted with bias correction. Should have been sent with previous commit for patch to CMI Gaussian bias correction 2018-08-27 00:29:59 +10:00
jlizier c32b8de8b0 Fixed a hanging issue with analytic bias correction for Guassian CMI, and added to AutoAnalyser GUI 2018-08-27 00:22:02 +10:00
jlizier b1a02be7db Adding sanity check that discrete ContextOfPastMeasure (and child classes, including AIS and TE) have k >= 0. 2018-08-26 22:48:37 +10:00