basic doc

Signed-off-by: Manish Amde <[email protected]>

Author: manishamde

mllib/src/main/scala/org/apache/spark/mllib/tree/README.md

@@ -1,15 +1,17 @@
 This package contains the default implementation of the decision tree algorithm.
 
 The decision tree algorithm supports:
-+ information loss calculation with entropy and gini for classification and variance for regression
-+ node model pruning
-+ printing to dot files
-+ unit tests
++ Binary classification
++ Regression
++ Information loss calculation with entropy and gini for classification and variance for regression
++ Both continuous and categorical features
 
-#Performance testing
+# Tree improvements
++ Node model pruning
++ Printing to dot files
 
-#Future Extensions
+# Future Ensemble Extensions
 
 + Random forests
 + Boosting
-+ Extremely randomized trees
++ Extremely randomized trees