[SPARK-7518][ML] Tests for comparing probability and prediction in binary logistic regression against R

[dbtsai]

Adding more tests for comparing probability and prediction in binary logistic regression against R

[AmplabJenkins]

Merged build triggered.

[AmplabJenkins]

Merged build started.

[SparkQA]

Test build #32356 has started for PR 6045 at commit 3e9631d.

[AmplabJenkins]

Merged build triggered.

[AmplabJenkins]

Merged build started.

[SparkQA]

Test build #32357 has started for PR 6045 at commit cb0a17b.

[SparkQA]

Test build #32356 has finished for PR 6045 at commit 3e9631d.

• This patch fails Spark unit tests.
• This patch merges cleanly.
• This patch adds no public classes.

[AmplabJenkins]

Merged build finished. Test FAILed.

[AmplabJenkins]

Test FAILed.
Refer to this link for build results (access rights to CI server needed):
https://amplab.cs.berkeley.edu/jenkins/job/SparkPullRequestBuilder/32356/
Test FAILed.

[dbtsai]

@mengxr @jkbradley @srowen This is relatively simple change in test. Will help me to have confidence to refactor for MLOR in ML.

[SparkQA]

Test build #32357 has finished for PR 6045 at commit cb0a17b.

• This patch passes all tests.
• This patch merges cleanly.
• This patch adds the following public classes (experimental):
  • class PCA(val k: Int)
  • class Evaluator(Params):

[AmplabJenkins]

Merged build finished. Test PASSed.

[AmplabJenkins]

Test PASSed.
Refer to this link for build results (access rights to CI server needed):
https://amplab.cs.berkeley.edu/jenkins/job/SparkPullRequestBuilder/32357/
Test PASSed.

[mengxr]

Though this is a private class, the doc should be Returns the numbers of training samples. in order to show up automatically as the method summary in the generated doc. Users have to make one click to see return ...