Github user f-sander commented on the pull request:
https://github.com/apache/flink/pull/1565#issuecomment-180798486
Sorry for the long delay. I still don't really have time for this, but I
wan't to describe it anyways. That's why the writing and formatting is pretty
Github user f-sander commented on a diff in the pull request:
https://github.com/apache/flink/pull/1565#discussion_r51723047
--- Diff:
flink-libraries/flink-ml/src/main/scala/org/apache/flink/ml/regression/IsotonicRegression.scala
---
@@ -0,0 +1,282 @@
+/*
+ * Licensed to
Github user f-sander commented on the pull request:
https://github.com/apache/flink/pull/1565#issuecomment-179247125
There is one advantage of this over using a single-node ML-Lib: This
implementation contains the compression procedure used in Spark that combines
data points with
Github user f-sander commented on the pull request:
https://github.com/apache/flink/pull/1565#issuecomment-179177999
Thanks for your Feedback!
Yes, scalability is the main issue for us too. We are not aware of any
other parallel implementation
he main issue for us too
Github user f-sander commented on the pull request:
https://github.com/apache/flink/pull/1565#issuecomment-178487703
Are the build failures related to us? I don't really understand how...
The first failure happens in oraclejd8 with hadoop 2.7.1:
```
Tests r
GitHub user f-sander opened a pull request:
https://github.com/apache/flink/pull/1565
[FLINK-3128] [flink-ml] Add Isotonic Regression To ML Library
Adds isotonic regression to the ml library.
It's a port of the implementation in Apache Spark.
You can merge this pull re
