add type hints for data.py

python-package/xgboost/_typing.py

@@ -1,20 +1,24 @@
 """Shared typing definition."""
 import ctypes
 import os
-from typing import Optional, List, Any, TypeVar, Union
+from typing import Optional, List, Any, TypeVar, Union, Type
 
 # os.PathLike/string/numpy.array/scipy.sparse/pd.DataFrame/dt.Frame/
 # cudf.DataFrame/cupy.array/dlpack
+import numpy as np
+
 DataType = Any
 
 # xgboost accepts some other possible types in practice due to historical reason, which is
 # lesser tested.  For now we encourage users to pass a simple list of string.
 FeatureNames = Optional[List[str]]
+FeatureTypes = Optional[List[str]]
 
 ArrayLike = Any
 PathLike = Union[str, os.PathLike]
 CupyT = ArrayLike  # maybe need a stub for cupy arrays
 NumpyOrCupy = Any
+NumpyDType = Union[str, Type[np.number]]
 
 # ctypes
 # c_bst_ulong corresponds to bst_ulong defined in xgboost/c_api.h

python-package/xgboost/compat.py

@@ -21,7 +21,7 @@ def py_str(x: CStrPtr) -> str:
     return x.decode('utf-8')  # type: ignore
 
 
-def lazy_isinstance(instance: Type, module: str, name: str) -> bool:
+def lazy_isinstance(instance: Type[object], module: str, name: str) -> bool:
     """Use string representation to identify a type."""
 
     # Notice, we use .__class__ as opposed to type() in order