summaryrefslogtreecommitdiff
path: root/ot/da.py
AgeCommit message (Collapse)Author
2017-09-01Move norm out of fit to init for deprecated OTDAaje
2017-09-01Move normalize function in utils.pyaje
2017-09-01Fix name erroraje
2017-09-01Changes:aje
- Rename numItermax to max_iter - Default value to 100000 instead of 10000 - Add max_iter to class SinkhornTransport(BaseTransport) - Add norm to all BaseTransport
2017-09-01Changes to LP solver:aje
- Allow to modify the maximal number of iterations - Display an error message in the python console if the solver encountered an issue
2017-09-01check input parameters with helper functionsSlasnista
2017-09-01handling input arguments in fit, transform... methods + remove old examplesSlasnista
2017-09-01move no da objects into utils.pySlasnista
2017-09-01solving log issues to avoid errors and adding further testsSlasnista
2017-09-01added deprecation warning on old classesSlasnista
2017-09-01test functions for MappingTransport ClassSlasnista
2017-09-01out of samples transform and inverse transform by batchSlasnista
2017-09-01make doc strings compliant with numpy / modif according to AG reviewSlasnista
2017-09-01added new class MappingTransport to support linear and kernel mapping, not ↵Slasnista
yet tested
2017-09-01out of samples by Ferradans supported for transform and inverse_transformSlasnista
2017-09-01reformat doc strings + remove useless log / verbose parameters for emdSlasnista
2017-09-01correction of semi supervised modeSlasnista
2017-09-01semi supervised mode supportedSlasnista
2017-09-01added new class SinkhornL1l2Transport() + dedicated testSlasnista
2017-09-01added new class SinkhornLpl1Transport() + dedicated testSlasnista
2017-09-01added test for fit_transform + correction of fit_transform bug (missing ↵Slasnista
return self)
2017-09-01added EMDTransport Class from NG's code + added dedicated testSlasnista
2017-09-01update SinkhornTransport class + added test for classSlasnista
2017-09-01own BaseEstimator class written + rflamary comments addressedSlasnista
2017-09-01integrate AG commentsSlasnista
2017-09-01small modifs according to NG proposalsSlasnista
2017-09-01first proposal for OT wrappersSlasnista
2017-09-01remove linewidth error messageSlasnista
2017-07-26pep8Rémi Flamary
2017-07-26add license and authors on all modulesRémi Flamary
2017-07-20pep8Alexandre Gramfort
2017-07-11add documentationRémi Flamary
2017-04-24Remove unnecessary parameterLeo gautheron
2017-04-21performance improvement sinkhorn lpl1Leo gautheron
- instead of updating individually for each target examples, update for all target examples at once using numpy functions. This allows for a faster computation (for me, divided by 4 on 3000*100 random matricies and random labels in [0,1]). - if I understoud correctly, a value of -1 in the array labels_a meant that we didn't have a label for this example. But in machine learning, we often encounter the binary case where we say we have the positive class (+1) and negative class (-1); thus with a dataset like this, the algorithm wouldn't work as expected. I replaced the default value for 'no label' to '-99' instead of '-1', and I added a parameter to modify it.
2017-04-21small normalization bugRémi Flamary
2017-04-20more changes from feebackLeo gautheron
in addition add the posibility to normalize the cost matrix through the function fit
2017-04-20sinkhorn GPU implementationLeo gautheron
2016-11-08da with GLNicolas Courty
2016-11-04workingRémi Flamary
2016-11-04etter doc for classesRémi Flamary
2016-11-04doc nonlinear mapping estimationRémi Flamary
2016-11-04doc linear mapping estimationRémi Flamary
2016-11-04add demo mappingRémi Flamary
2016-11-04add mapping estimation with kernels works!Rémi Flamary
2016-11-03add mapping estimation with kernels (smaller bugs)Rémi Flamary
2016-11-03add mapping estimation with kernels (still debugging)Rémi Flamary
2016-11-03add mapping estimation with kernels (still debugging)Rémi Flamary
2016-11-03add mapping estimation (still debugging)Rémi Flamary
2016-11-02add mapping estimation (still debugging)Rémi Flamary
2016-10-31v0.1.7Rémi Flamary