[SPARK-16260][ML][EXAMPLE] PySpark ML Example Improvements and Cleanup

## What changes were proposed in this pull request?
1). Remove unused import in Scala example;

2). Move spark session import outside example off;

3). Change parameter setting the same as Scala;

4). Change comment to be consistent;

5). Make sure that Scala and python using the same data set;

I did one pass and fixed the above issues. There are missing examples in python, which might be added later.

TODO: For some examples, there are comments on how to run examples; But there are many missing. We can add them later.

## How was this patch tested?

(Please explain how this patch was tested. E.g. unit tests, integration tests, manual tests)

Manually test them

Author: wm624@hotmail.com <wm624@hotmail.com>

Closes #14021 from wangmiao1981/ann.

0 files changed, 0 insertions, 0 deletions