feat: add several parameters related to dart boosting type

[imatiach-msft]

Add several parameters for dart mode as requested by two internal data scientists:

• drop_rate, default = 0.1, type = double, aliases: rate_drop, constraints: 0.0 <= drop_rate <= 1.0

  • used only in dart

  • dropout rate: a fraction of previous trees to drop during the dropout

• max_drop, default = 50, type = int

  • used only in dart

  • max number of dropped trees during one boosting iteration

  • <=0 means no limit

• skip_drop, default = 0.5, type = double, constraints: 0.0 <= skip_drop <= 1.0

  • used only in dart

  • probability of skipping the dropout procedure during a boosting iteration

• xgboost_dart_mode, default = false, type = bool

  • used only in dart

  • set this to true, if you want to use xgboost dart mode

• uniform_drop, default = false, type = bool

  • used only in dart

  • set this to true, if you want to use uniform drop

[imatiach-msft]

/azp run

[azure-pipelines]

Azure Pipelines successfully started running 1 pipeline(s).

[codecov]

Codecov Report

Merging #1045 (0e8729f) into master (b7f29e8) will increase coverage by 0.02%.
The diff coverage is 100.00%.

@@            Coverage Diff             @@
##           master    #1045      +/-   ##
==========================================
+ Coverage   84.91%   84.94%   +0.02%     
==========================================
  Files         203      203              
  Lines        9648     9677      +29     
  Branches      548      588      +40     
==========================================
+ Hits         8193     8220      +27     
- Misses       1455     1457       +2     

Impacted Files	Coverage Δ
...com/microsoft/ml/spark/lightgbm/LightGBMBase.scala	92.68% <100.00%> (+0.09%)	⬆️
...crosoft/ml/spark/lightgbm/LightGBMClassifier.scala	91.01% <100.00%> (ø)
...m/microsoft/ml/spark/lightgbm/LightGBMParams.scala	90.45% <100.00%> (+1.10%)	⬆️
...m/microsoft/ml/spark/lightgbm/LightGBMRanker.scala	63.07% <100.00%> (ø)
...icrosoft/ml/spark/lightgbm/LightGBMRegressor.scala	72.22% <100.00%> (ø)
.../com/microsoft/ml/spark/lightgbm/TrainParams.scala	100.00% <100.00%> (ø)
...a/com/microsoft/ml/spark/io/http/HTTPClients.scala	83.33% <0.00%> (-3.34%)	⬇️

---

Continue to review full report at Codecov.

Legend - Click here to learn more
Δ = absolute <relative> (impact), ø = not affected, ? = missing data
Powered by Codecov. Last update b7f29e8...0e8729f. Read the comment docs.

[imatiach-msft]

/azp run

[azure-pipelines]

Azure Pipelines successfully started running 1 pipeline(s).