[
https://issues.apache.org/jira/browse/SPARK-18226?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=16096007#comment-16096007
]
Kirti commented on SPARK-18226:
---
This code retrieves values of probability column:
fileP <- predict(model,
[
https://issues.apache.org/jira/browse/SPARK-18226?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=16094318#comment-16094318
]
Kirti commented on SPARK-18226:
---
Hi Felix,
Subsetting the collecting data.frame does not help, I am still
[
https://issues.apache.org/jira/browse/SPARK-18226?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=16094277#comment-16094277
]
Felix Cheung commented on SPARK-18226:
--
I agree, usability is poor, though I think if you subset the
[
https://issues.apache.org/jira/browse/SPARK-18226?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=16093483#comment-16093483
]
Kirti commented on SPARK-18226:
---
Hi Felix,
After collecting output of predict in R, probability column
[
https://issues.apache.org/jira/browse/SPARK-18226?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=16093466#comment-16093466
]
Felix Cheung commented on SPARK-18226:
--
if you collect on what's returned by predict(), you should
[
https://issues.apache.org/jira/browse/SPARK-18226?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=16091382#comment-16091382
]
Kirti commented on SPARK-18226:
---
Is there any way around to handle this issue in SparkR?
> SparkR
[
https://issues.apache.org/jira/browse/SPARK-18226?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=15649026#comment-15649026
]
Felix Cheung commented on SPARK-18226:
--
We discussed this as a part of the GBT PR, from here
[
https://issues.apache.org/jira/browse/SPARK-18226?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel=15630623#comment-15630623
]
Felix Cheung commented on SPARK-18226:
--
Thanks, this is actually the issue outlined in