[Spark-15129][R][DOC]R API changes in ML

[GayathriMurali]

What changes were proposed in this pull request?

Make user guide changes to SparkR documentation for all changes that happened in 2.0 to Machine Learning APIs

[GayathriMurali]

@jkbradley @MLnick I have marked this WIP, as I want to get your thoughts on if you think the format looks ok. I can add examples to KMeans and SurvReg is the overall format looks fine.

[yanboliang]

@GayathriMurali
1, Please clear the change for ml-features.md which is irrelevant to this issue.
2, We can use include_example tag to directly include examples at examples/src/main/r/ml.R into the user guide. You can refer this PR #9713.

[GayathriMurali]

@yanboliang Thanks, thats a good idea. However, that would just include example code and not how the output of summary() looks like. It might be useful to include that

[yanboliang]

I think it's not necessary to include summary output of all models in the user guide, we can only show summary of GLM as an example. You need to copy the summary from your own running output.

[GayathriMurali]

@yanboliang Can you please help review?

[yanboliang]

We have rename these with functions to spark.glm, spark.naiveBayes, spark.kmeans, spark.survreg.

[yanboliang]

@GayathriMurali
1, Please clear the change for ml-features.md which is irrelevant to this issue.
2, Please also include examples of other machine learning algorithms (spark.survreg, spark.naiveBayes, spark.kmeans).

[GayathriMurali]

@yanboliang I have included ml.r using include-example, wouldn't that cover all the examples?

[yanboliang]

@GayathriMurali $example on$ and $example off$ will help us to extract only interested sections to be included in the user guide docs. You can run SKIP_API=1 jekyll build under directory ./docs to generate the html and check whether it works well.

[yanboliang]

FYI #10219

[GayathriMurali]

@yanboliang $example on$ and $example off$ needs to be included in ml.R. All the code encompassed within example on and off would be joined and a single code block will be produced in the html. It is used to remove comments and other cleanup in the code from appearing in examples. It is not possible to associate a label with example on and off and select a certain label. I could add example on and off at the beginning and end of ml.R or we need to rewrite ml.R so that certain portions like creating a DF remains common for all models. What do you think?

[GayathriMurali]

Also, #10219 uses include_example with different files , which is not the case here. @mengxr We need support for tags with include_example, or we need to reformat ml.R( or split every example into a different file) to be used here. I can create a JIRA and work on it, if this makes sense.

[yanboliang]

Move this line to L28, it's better we can include the annotation line spark.glm and glm which can help users to understand corresponding code.

[yanboliang]

@GayathriMurali I think what is there for include_example is OK. Please see my other inline comments.

[GayathriMurali]

@yanboliang Please let me know if there is anything else I can do to get this merged.

[SparkQA]

Test build #3078 has finished for PR 13285 at commit 8e7c4fe.

• This patch passes all tests.
• This patch merges cleanly.
• This patch adds no public classes.

[GayathriMurali]

@yanboliang Please let me know if there is anything else I can do to help get this merged.Thanks!

[jkbradley]

Organize better:

The examples below show how to build several models:
* GLM using the Gaussian and Binomial model families
* AFT survival regression model
* Naive Bayes model
* K-Means model

[jkbradley]

This looks good, though I had one small comment. Thanks for your patience!

[GayathriMurali]

@jkbradley I fixed for the review comment. Please let me know if there is anything else. Thanks!

[mengxr]

Merged into master and branch-2.0. Saw some very minor issues. I make another pass and fix them in a follow-up PR. Thanks!