diff --git a/xgboost_ray/__init__.py b/xgboost_ray/__init__.py
index 15cb68c8..c03df42f 100644
--- a/xgboost_ray/__init__.py
+++ b/xgboost_ray/__init__.py
@@ -3,7 +3,10 @@
     RayFileType, RayShardingMode, \
     Data, combine_data
 
+__version__ = "0.0.2"
+
 __all__ = [
-    "RayParams", "RayDMatrix", "RayDeviceQuantileDMatrix", "RayFileType",
-    "RayShardingMode", "Data", "combine_data", "train", "predict"
+    "__version__", "RayParams", "RayDMatrix", "RayDeviceQuantileDMatrix",
+    "RayFileType", "RayShardingMode", "Data", "combine_data", "train",
+    "predict"
 ]
diff --git a/xgboost_ray/main.py b/xgboost_ray/main.py
index 3665b253..324d7f8a 100644
--- a/xgboost_ray/main.py
+++ b/xgboost_ray/main.py
@@ -1,4 +1,3 @@
-import threading
 from typing import Tuple, Dict, Any, List, Optional, Callable, Union
 from dataclasses import dataclass, field
 
@@ -6,6 +5,7 @@
 import os
 import pickle
 import time
+import threading
 
 import numpy as np