Use bst_float consistently throughout (#1824)

* Fix various typos

* Add override to functions that are overridden

gcc gives warnings about functions that are being overridden by not
being marked as oveirridden. This fixes it.

* Use bst_float consistently

Use bst_float for all the variables that involve weight,
leaf value, gradient, hessian, gain, loss_chg, predictions,
base_margin, feature values.

In some cases, when due to additions and so on the value can
take a larger value, double is used.

This ensures that type conversions are minimal and reduces loss of
precision.

plugin/dense_parser/dense_libsvm.cc

@@ -28,7 +28,7 @@ class DensifyParser : public dmlc::Parser<IndexType> {
     LOG(INFO) << batch.size;
     dense_index_.resize(num_col_ * batch.size);
     dense_value_.resize(num_col_ * batch.size);
-    std::fill(dense_value_.begin(), dense_value_.end(), 0.0f);
+    std::fill(dense_value_.begin(), dense_value_.end(), 0.0);
     offset_.resize(batch.size + 1);
     offset_[0] = 0;
 
@@ -66,7 +66,7 @@ class DensifyParser : public dmlc::Parser<IndexType> {
   uint32_t num_col_;
   std::vector<size_t> offset_;
   std::vector<IndexType> dense_index_;
-  std::vector<float> dense_value_;
+  std::vector<xgboost::bst_float> dense_value_;
 };
 
 template<typename IndexType>