GitHub user dmitrievanthony opened a pull request: https://github.com/apache/ignite/pull/4124
IGNITE-8667 Splitting of dataset to test and training sets You can merge this pull request into a Git repository by running: $ git pull https://github.com/gridgain/apache-ignite ignite-8667 Alternatively you can review and apply these changes as the patch at: https://github.com/apache/ignite/pull/4124.patch To close this pull request, make a commit to your master/trunk branch with (at least) the following in the commit message: This closes #4124 ---- commit e392b6acafb3fa2752b77fcd942dc85b482b4bec Author: Anton Dmitriev <dmitrievanthony@...> Date: 2018-05-31T14:57:26Z IGNITE-8666 Add predicates into CacheBasedDatasetBuilder and LocalDatasetBuilder. commit c50a645e3f3a0e277f98e02916eaf4b62731ff52 Author: Anton Dmitriev <dmitrievanthony@...> Date: 2018-05-31T15:08:58Z IGNITE-8666 Add dataset predicate support to examples. commit efa7e33ced5e9f313f4b9521aef76568f0e9d1bf Author: Anton Dmitriev <dmitrievanthony@...> Date: 2018-05-31T15:09:08Z IGNITE-8666 Add dataset predicate support to examples. commit 737738febe0bedd8ceb362f6204b6a0d79679579 Author: Anton Dmitriev <dmitrievanthony@...> Date: 2018-05-31T15:26:13Z IGNITE-8666 Add constructor with default predicate to CacheBased and Local Dataset Builders. commit 28565c356057bc36c09fc17c8daf7aa3e2827eb5 Author: Anton Dmitriev <dmitrievanthony@...> Date: 2018-05-31T16:18:17Z IGNITE-8666 Use default ScanQuery filter instead of custom cursor wrapper. commit a7932692789b3ef59bfb713839bffb9b73aa0597 Author: dmitrievanthony <dmitrievanthony@...> Date: 2018-05-31T20:30:36Z IGNITE-8666 Use default transformer instead of UpstreamCursorAdapter. commit f77f13e9c7698be7bd0176d9f531875c572cd4d3 Author: dmitrievanthony <dmitrievanthony@...> Date: 2018-05-31T20:49:32Z IGNITE-8666 Use default constructs of CacheBased and Local Dataset Builders. commit e6eb7473645ed0bf248f7c4badd87ac4c20e34d4 Author: dmitrievanthony <dmitrievanthony@...> Date: 2018-05-31T20:52:58Z IGNITE-8666 Fix code style. commit b9e8a105a61912f9e7ceb6064d5528ba12f017b1 Author: Anton Dmitriev <dmitrievanthony@...> Date: 2018-06-01T08:06:49Z IGNITE-8666 Add KNNRegressionTrainer to trainers hierarchy. commit dd09c0a809c81c34a6ae8ac95278080565965b47 Author: Anton Dmitriev <dmitrievanthony@...> Date: 2018-06-01T08:23:34Z IGNITE-8666 Fix javadoc in ComputeUtils class. commit a004bf20342fef500045f830e821954616a2164b Author: Anton Dmitriev <dmitrievanthony@...> Date: 2018-06-01T09:10:04Z IGNITE-8666 Add concurrent modification checker to dataset builders. commit 88b2483cf3a601935140f43edafe2e13b03506eb Author: Anton Dmitriev <dmitrievanthony@...> Date: 2018-06-01T09:32:54Z Merge branch 'ignite-8666' into ignite-8667 commit c2291f3e01b98c3f22a57652ecab500e67e29aef Author: Anton Dmitriev <dmitrievanthony@...> Date: 2018-06-01T11:23:29Z IGNITE-8666 Rename pred -> filter. commit 05b527dd346cdedf3e2f823a6a5761d240ff381a Author: Anton Dmitriev <dmitrievanthony@...> Date: 2018-06-01T11:24:49Z Merge branch 'ignite-8666' into ignite-8667 commit 7bab5832d5a94f0f9f46f17286161b2738538179 Author: Anton Dmitriev <dmitrievanthony@...> Date: 2018-06-01T13:37:16Z IGNITE-8667 First version of TrainTest dataset splitter. commit 206a9cbaf132ea515b3e8aa7b3832df3332d2c71 Author: Anton Dmitriev <dmitrievanthony@...> Date: 2018-06-04T14:27:49Z IGNITE-8667 Add unified mapper for train test splitter and tests. commit fe6a7f05eb0926f8bfc07885c6f6ed3ab335956f Author: Anton Dmitriev <dmitrievanthony@...> Date: 2018-06-04T14:34:45Z Merge remote-tracking branch 'origin/master' into ignite-8667 # Conflicts: # modules/ml/src/main/java/org/apache/ignite/ml/dataset/impl/cache/util/ComputeUtils.java ---- ---