Github user srowen commented on the issue:
https://github.com/apache/spark/pull/14643
OK, we can close this PR then.
---
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 w
Github user zhengruifeng commented on the issue:
https://github.com/apache/spark/pull/14643
@srowen You can take it over.
---
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
Github user srowen commented on the issue:
https://github.com/apache/spark/pull/14643
Ping @zhengruifeng are you in a position to keep working on this or should
I take it over?
---
If your project is set up for it, you can reply to this email and have your
reply appear on GitHub as w
Github user srowen commented on the issue:
https://github.com/apache/spark/pull/14643
See https://github.com/apache/spark/pull/14949 -- I think we might want to
proceed with this with some modifications.
---
If your project is set up for it, you can reply to this email and have your
Github user srowen commented on the issue:
https://github.com/apache/spark/pull/14643
... for example,
```
/**
* Given a vector of class conditional probabilities, select the
predicted label.
* This returns the class, if any, whose probability is equal to o
Github user srowen commented on the issue:
https://github.com/apache/spark/pull/14643
If it's OK, I'll open a different PR which proposes a simpler behavior:
- Return the class with highest probability that is also >= threshold
- If no such class exists, return ... NaN? Thi
Github user srowen commented on the issue:
https://github.com/apache/spark/pull/14643
Thresholds are just that -- thresholds. The meaning is certainly as in
https://github.com/apache/spark/pull/14643#discussion_r75290480 While I kind
of like the idea of also treating them as a 'weigh
Github user zhengruifeng commented on the issue:
https://github.com/apache/spark/pull/14643
@srowen I though of `threshoulds` designed in ML just as a kind of
`weight`. This design is easy to understand. Is there some other librarys (like
sklearn) that support thresholds? We can refe
Github user AmplabJenkins commented on the issue:
https://github.com/apache/spark/pull/14643
Test PASSed.
Refer to this link for build results (access rights to CI server needed):
https://amplab.cs.berkeley.edu/jenkins//job/SparkPullRequestBuilder/63774/
Test PASSed.
---
Github user AmplabJenkins commented on the issue:
https://github.com/apache/spark/pull/14643
Merged build finished. Test PASSed.
---
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
e
Github user SparkQA commented on the issue:
https://github.com/apache/spark/pull/14643
**[Test build #63774 has
finished](https://amplab.cs.berkeley.edu/jenkins/job/SparkPullRequestBuilder/63774/consoleFull)**
for PR 14643 at commit
[`4ec606d`](https://github.com/apache/spark/commit/
Github user SparkQA commented on the issue:
https://github.com/apache/spark/pull/14643
**[Test build #63774 has
started](https://amplab.cs.berkeley.edu/jenkins/job/SparkPullRequestBuilder/63774/consoleFull)**
for PR 14643 at commit
[`4ec606d`](https://github.com/apache/spark/commit/4
12 matches
Mail list logo
