SHAP values for feature contributions (#2438)

* SHAP values for feature contributions

* Fix commenting error

* New polynomial time SHAP value estimation algorithm

* Update API to support SHAP values

* Fix merge conflicts with updates in master

* Correct submodule hashes

* Fix variable sized stack allocation

* Make lint happy

* Add docs

* Fix typo

* Adjust tolerances

* Remove unneeded def

* Fixed cpp test setup

* Updated R API and cleaned up

* Fixed test typo

python-package/xgboost/core.py

@@ -990,7 +990,7 @@ class Booster(object):
         return self.eval_set([(data, name)], iteration)
 
     def predict(self, data, output_margin=False, ntree_limit=0, pred_leaf=False,
-                pred_contribs=False):
+                pred_contribs=False, approx_contribs=False):
         """
         Predict with data.
 
@@ -1018,9 +1018,12 @@ class Booster(object):
 
         pred_contribs : bool
             When this option is on, the output will be a matrix of (nsample, nfeats+1)
-            with each record indicating the feature contributions of all trees. The sum of
-            all feature contributions is equal to the prediction. Note that the bias is added
-            as the final column, on top of the regular features.
+            with each record indicating the feature contributions (SHAP values) for that
+            prediction. The sum of all feature contributions is equal to the prediction.
+            Note that the bias is added as the final column, on top of the regular features.
+
+        approx_contribs : bool
+            Approximate the contributions of each feature
 
         Returns
         -------
@@ -1033,6 +1036,8 @@ class Booster(object):
             option_mask |= 0x02
         if pred_contribs:
             option_mask |= 0x04
+        if approx_contribs:
+            option_mask |= 0x08
 
         self._validate_features(data)