[Backport] Rename data to X in predict_proba. (#6555) (#6586)

* [Breaking] Rename `data` to `X` in `predict_proba`. (#6555)

New Scikit-Learn version uses keyword argument, and `X` is the predefined
keyword.

* Use pip to install latest Python graphviz on Windows CI.

* Suppress health check.

python-package/xgboost/dask.py

@@ -1210,10 +1210,10 @@ class DaskXGBClassifier(DaskScikitLearnBase, XGBClassifierBase):
                                 early_stopping_rounds=early_stopping_rounds,
                                 verbose=verbose)
 
-    async def _predict_proba_async(self, data, output_margin=False,
+    async def _predict_proba_async(self, X, output_margin=False,
                                    base_margin=None):
         test_dmatrix = await DaskDMatrix(
-            client=self.client, data=data, base_margin=base_margin,
+            client=self.client, data=X, base_margin=base_margin,
             missing=self.missing
         )
         pred_probs = await predict(client=self.client,
@@ -1223,11 +1223,11 @@ class DaskXGBClassifier(DaskScikitLearnBase, XGBClassifierBase):
         return pred_probs
 
     # pylint: disable=arguments-differ,missing-docstring
-    def predict_proba(self, data, output_margin=False, base_margin=None):
+    def predict_proba(self, X, output_margin=False, base_margin=None):
         _assert_dask_support()
         return self.client.sync(
             self._predict_proba_async,
-            data,
+            X=X,
             output_margin=output_margin,
             base_margin=base_margin
         )

python-package/xgboost/sklearn.py

@@ -995,10 +995,9 @@ class XGBClassifier(XGBModel, XGBClassifierBase):
             return self._le.inverse_transform(column_indexes)
         return column_indexes
 
-    def predict_proba(self, data, ntree_limit=None, validate_features=False,
+    def predict_proba(self, X, ntree_limit=None, validate_features=False,
                       base_margin=None):
-        """
-        Predict the probability of each `data` example being of a given class.
+        """ Predict the probability of each `X` example being of a given class.
 
         .. note:: This function is not thread safe
 
@@ -1008,21 +1007,22 @@ class XGBClassifier(XGBModel, XGBClassifierBase):
 
         Parameters
         ----------
-        data : array_like
+        X : array_like
             Feature matrix.
         ntree_limit : int
-            Limit number of trees in the prediction; defaults to best_ntree_limit if defined
-            (i.e. it has been trained with early stopping), otherwise 0 (use all trees).
+            Limit number of trees in the prediction; defaults to best_ntree_limit if
+            defined (i.e. it has been trained with early stopping), otherwise 0 (use all
+            trees).
         validate_features : bool
-            When this is True, validate that the Booster's and data's feature_names are identical.
-            Otherwise, it is assumed that the feature_names are the same.
+            When this is True, validate that the Booster's and data's feature_names are
+            identical.  Otherwise, it is assumed that the feature_names are the same.
 
         Returns
         -------
         prediction : numpy array
             a numpy array with the probability of each data example being of a given class.
         """
-        test_dmatrix = DMatrix(data, base_margin=base_margin,
+        test_dmatrix = DMatrix(X, base_margin=base_margin,
                                missing=self.missing, nthread=self.n_jobs)
         if ntree_limit is None:
             ntree_limit = getattr(self, "best_ntree_limit", 0)