Improve non-nanosecond warning (#7238)

* Point to Variable or DataArray constructor in non-nanosecond warning

* [test-upstream] Use find_stack_level function from pandas

Author: spencerkclark

xarray/core/utils.py

@@ -1,9 +1,44 @@
 """Internal utilities; not for external use"""
+# Some functions in this module are derived from functions in pandas. For
+# reference, here is a copy of the pandas copyright notice:
+
+# BSD 3-Clause License
+
+# Copyright (c) 2008-2011, AQR Capital Management, LLC, Lambda Foundry, Inc. and PyData Development Team
+# All rights reserved.
+
+# Copyright (c) 2011-2022, Open source contributors.
+
+# Redistribution and use in source and binary forms, with or without
+# modification, are permitted provided that the following conditions are met:
+
+# * Redistributions of source code must retain the above copyright notice, this
+#   list of conditions and the following disclaimer.
+
+# * Redistributions in binary form must reproduce the above copyright notice,
+#   this list of conditions and the following disclaimer in the documentation
+#   and/or other materials provided with the distribution.
+
+# * Neither the name of the copyright holder nor the names of its
+#   contributors may be used to endorse or promote products derived from
+#   this software without specific prior written permission.
+
+# THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
+# AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+# IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
+# DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT HOLDER OR CONTRIBUTORS BE LIABLE
+# FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
+# DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR
+# SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER
+# CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY,
+# OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
+# OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
 from __future__ import annotations
 
 import contextlib
 import functools
 import importlib
+import inspect
 import io
 import itertools
 import math
@@ -972,3 +1007,46 @@ def module_available(module: str) -> bool:
         Whether the module is installed.
     """
     return importlib.util.find_spec(module) is not None
+
+
+def find_stack_level(test_mode=False) -> int:
+    """Find the first place in the stack that is not inside xarray.
+
+    This is unless the code emanates from a test, in which case we would prefer
+    to see the xarray source.
+
+    This function is taken from pandas.
+
+    Parameters
+    ----------
+    test_mode : bool
+        Flag used for testing purposes to switch off the detection of test
+        directories in the stack trace.
+
+    Returns
+    -------
+    stacklevel : int
+        First level in the stack that is not part of xarray.
+    """
+    import xarray as xr
+
+    pkg_dir = os.path.dirname(xr.__file__)
+    test_dir = os.path.join(pkg_dir, "tests")
+
+    # https://stackoverflow.com/questions/17407119/python-inspect-stack-is-slow
+    frame = inspect.currentframe()
+    n = 0
+    while frame:
+        fname = inspect.getfile(frame)
+        if fname.startswith(pkg_dir) and (not fname.startswith(test_dir) or test_mode):
+            frame = frame.f_back
+            n += 1
+        else:
+            break
+    return n
+
+
+def emit_user_level_warning(message, category=None):
+    """Emit a warning at the user level by inspecting the stack trace."""
+    stacklevel = find_stack_level()
+    warnings.warn(message, category=category, stacklevel=stacklevel)

xarray/core/variable.py

@@ -71,7 +71,10 @@
 NON_NANOSECOND_WARNING = (
     "Converting non-nanosecond precision {case} values to nanosecond precision. "
     "This behavior can eventually be relaxed in xarray, as it is an artifact from "
-    "pandas which is now beginning to support non-nanosecond precision values."
+    "pandas which is now beginning to support non-nanosecond precision values. "
+    "This warning is caused by passing non-nanosecond np.datetime64 or "
+    "np.timedelta64 values to the DataArray or Variable constructor; it can be "
+    "silenced by converting the values to nanosecond precision ahead of time."
 )
 
 
@@ -191,14 +194,14 @@ def _as_nanosecond_precision(data):
         isinstance(dtype, pd.DatetimeTZDtype) and dtype.unit != "ns"
     )
     if non_ns_datetime64 or non_ns_datetime_tz_dtype:
-        warnings.warn(NON_NANOSECOND_WARNING.format(case="datetime"))
+        utils.emit_user_level_warning(NON_NANOSECOND_WARNING.format(case="datetime"))
         if isinstance(dtype, pd.DatetimeTZDtype):
             nanosecond_precision_dtype = pd.DatetimeTZDtype("ns", dtype.tz)
         else:
             nanosecond_precision_dtype = "datetime64[ns]"
         return data.astype(nanosecond_precision_dtype)
     elif dtype.kind == "m" and dtype != np.dtype("timedelta64[ns]"):
-        warnings.warn(NON_NANOSECOND_WARNING.format(case="timedelta"))
+        utils.emit_user_level_warning(NON_NANOSECOND_WARNING.format(case="timedelta"))
         return data.astype("timedelta64[ns]")
     else:
         return data

xarray/tests/test_utils.py

@@ -266,3 +266,13 @@ def test_infix_dims_errors(supplied, all_):
 )
 def test_iterate_nested(nested_list, expected):
     assert list(iterate_nested(nested_list)) == expected
+
+
+def test_find_stack_level():
+    assert utils.find_stack_level() == 1
+    assert utils.find_stack_level(test_mode=True) == 2
+
+    def f():
+        return utils.find_stack_level(test_mode=True)
+
+    assert f() == 3