[SPARK-38546][EXAMPLES] Replace deprecated ChiSqSelector with UnivariateFeatureSelector

[dcoliversun]

What changes were proposed in this pull request?

This PR aims to replace deprecated ChiSqSelector with UnivariateFeatureSelector.

Why are the changes needed?

In #31160, ChiSqSelector was labeled as deprecated.

Does this PR introduce any user-facing change?

No

How was this patch tested?

Run JavaChiSqSelectorExample Before the PR

ChiSqSelector output with top 1 features selected
22/03/14 15:11:56 INFO CodeGenerator: Code generated in 6.124107 ms
22/03/14 15:11:56 INFO CodeGenerator: Code generated in 12.399323 ms
22/03/14 15:11:56 INFO CodeGenerator: Code generated in 6.305541 ms
22/03/14 15:11:56 INFO CodeGenerator: Code generated in 8.784765 ms
+---+------------------+-------+----------------+
| id|          features|clicked|selectedFeatures|
+---+------------------+-------+----------------+
|  7|[0.0,0.0,18.0,1.0]|    1.0|          [18.0]|
|  8|[0.0,1.0,12.0,0.0]|    0.0|          [12.0]|
|  9|[1.0,0.0,15.0,0.1]|    0.0|          [15.0]|
+---+------------------+-------+----------------+

Run JavaChiSqSelectorExample After the PR

UnivariateFeatureSelector for chi-squared output with top 1.0 features selected
22/03/14 19:36:54 INFO CodeGenerator: Code generated in 9.093969 ms
22/03/14 19:36:54 INFO CodeGenerator: Code generated in 15.667814 ms
22/03/14 19:36:54 INFO CodeGenerator: Code generated in 10.053778 ms
22/03/14 19:36:54 INFO CodeGenerator: Code generated in 12.287391 ms
+---+------------------+-------+----------------+
| id|          features|clicked|selectedFeatures|
+---+------------------+-------+----------------+
|  7|[0.0,0.0,18.0,1.0]|    1.0|          [18.0]|
|  8|[0.0,1.0,12.0,0.0]|    0.0|          [12.0]|
|  9|[1.0,0.0,15.0,0.1]|    0.0|          [15.0]|
+---+------------------+-------+----------------+

[dcoliversun]

@huaxingao @zhengruifeng @WeichenXu123
It would be good if you could take a look when you have time, thanks!

[huaxingao]

@dcoliversun Thanks for working on this. However, we already have an example for UnivariateFeatureSelector here. Your effort is appreciated!