[jira] [Updated] (IGNITE-12685) [ML] [Umbrella] Unify Preprocessors and Pipeline approaches to collect common statistics
[ https://issues.apache.org/jira/browse/IGNITE-12685?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Maxim Muzafarov updated IGNITE-12685: - Fix Version/s: (was: 2.10) > [ML] [Umbrella] Unify Preprocessors and Pipeline approaches to collect > common statistics > -- > > Key: IGNITE-12685 > URL: https://issues.apache.org/jira/browse/IGNITE-12685 > Project: Ignite > Issue Type: Improvement > Components: ml >Reporter: Alexey Zinoviev >Assignee: Alexey Zinoviev >Priority: Major > > In the current implementation we have different behavior in Cross-Validation > during running on the experimental Pipeline and chain of Preprocessors. > > Look at the tutorial step 8 CV_Param_Grid and 8_CV_Param_Grid_and_pipeline > In the first example all preprocessors fits on the whole dataset and don't > use train/test filter (due to limited API in preprocessors), and collects the > stat on the whole initial dataset. > > In the second example, we have honest re-fitting on each cross-validation > fold three times with three different stats. As a result we could get a > different encoding values or Max/Min values for each column and so on. > > Should learn this question and be in consistency with the most popular > approaches. > -- This message was sent by Atlassian Jira (v8.3.4#803005)
[jira] [Updated] (IGNITE-12685) [ML] [Umbrella] Unify Preprocessors and Pipeline approaches to collect common statistics
[ https://issues.apache.org/jira/browse/IGNITE-12685?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Alexey Zinoviev updated IGNITE-12685: - Fix Version/s: (was: 2.9) 2.10 > [ML] [Umbrella] Unify Preprocessors and Pipeline approaches to collect > common statistics > -- > > Key: IGNITE-12685 > URL: https://issues.apache.org/jira/browse/IGNITE-12685 > Project: Ignite > Issue Type: Improvement > Components: ml >Reporter: Alexey Zinoviev >Assignee: Alexey Zinoviev >Priority: Major > Fix For: 2.10 > > > In the current implementation we have different behavior in Cross-Validation > during running on the experimental Pipeline and chain of Preprocessors. > > Look at the tutorial step 8 CV_Param_Grid and 8_CV_Param_Grid_and_pipeline > In the first example all preprocessors fits on the whole dataset and don't > use train/test filter (due to limited API in preprocessors), and collects the > stat on the whole initial dataset. > > In the second example, we have honest re-fitting on each cross-validation > fold three times with three different stats. As a result we could get a > different encoding values or Max/Min values for each column and so on. > > Should learn this question and be in consistency with the most popular > approaches. > -- This message was sent by Atlassian Jira (v8.3.4#803005)