Github user jkbradley commented on a diff in the pull request:
https://github.com/apache/spark/pull/7205#discussion_r36038228
--- Diff:
mllib/src/main/scala/org/apache/spark/ml/param/shared/SharedParamsCodeGen.scala
---
@@ -46,7 +46,10 @@ private[shared] object SharedParamsCodeGen {
Some("\"probability\"")),
ParamDesc[Double]("threshold",
"threshold in binary classification prediction, in range [0, 1]",
- isValid = "ParamValidators.inRange(0, 1)"),
+ isValid = "ParamValidators.inRange(0, 1)", finalMethods = false),
+ ParamDesc[Array[Double]]("thresholds",
+ "thresholds in multi-class classification prediction, must be
array with size of classes.",
--- End diff --
This needs more explanation. How about:
```
Thresholds for multi-class classification. Rather than predicting the
maximum rawPrediction value index as the class label, this re-weights the raw
prediction for each class: rawPrediction(class) / thresholds(class).
```
---
If your project is set up for it, you can reply to this email and have your
reply appear on GitHub as well. If your project does not have this feature
enabled and wishes so, or if the feature is enabled but not working, please
contact infrastructure at [email protected] or file a JIRA ticket
with INFRA.
---
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
