[
https://issues.apache.org/jira/browse/FLINK-2030?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=14708043#comment-14708043
]
ASF GitHub Bot commented on FLINK-2030:
---------------------------------------
Github user sachingoel0101 commented on the pull request:
https://github.com/apache/flink/pull/861#issuecomment-133707118
@tillrohrmann, thanks for the brilliant suggestions. Using a `TreeMap` and
`PriorityQueue` with invalidation, I've managed to bring down the complexity of
the `add` and `merge` operations to logarithmic time. Further, `quantile` and
`count` are also linear only, as they should be.
Further, I've decided to put both the Histograms in the `accumulator`
package since they're supposed to work like one anyway. There already was a
*discrete* histogram in the `accumulator` package. The *continuous* one now
resides in the same place.
Also, the `DataSetUtils` class now contains functions to create histograms,
providing access to these classes from the Java api itself instead of the ML
library. That was needed to be done sooner or later. Flink-2274 actually asks
for that.
@thvasilo @chiwanpark
> Implement an online histogram with Merging and equalization features
> --------------------------------------------------------------------
>
> Key: FLINK-2030
> URL: https://issues.apache.org/jira/browse/FLINK-2030
> Project: Flink
> Issue Type: Sub-task
> Components: Machine Learning Library
> Reporter: Sachin Goel
> Assignee: Sachin Goel
> Priority: Minor
> Labels: ML
>
> For the implementation of the decision tree in
> https://issues.apache.org/jira/browse/FLINK-1727, we need to implement an
> histogram with online updates, merging and equalization features. A reference
> implementation is provided in [1]
> [1].http://www.jmlr.org/papers/volume11/ben-haim10a/ben-haim10a.pdf
--
This message was sent by Atlassian JIRA
(v6.3.4#6332)
