This is an automated email from the ASF dual-hosted git repository.
kszucs pushed a commit to branch master
in repository https://gitbox.apache.org/repos/asf/arrow.git
The following commit(s) were added to refs/heads/master by this push:
new 09d3496 ARROW-4260: [Python] NumPy buffer protocol failure
09d3496 is described below
commit 09d34964996a718beb2def4e4173974f8a3d862e
Author: Krisztián Szűcs <[email protected]>
AuthorDate: Tue Jan 15 17:02:26 2019 +0100
ARROW-4260: [Python] NumPy buffer protocol failure
The following error only occurred when both numpy=1.16 and pickle5 was
installed.
It's a numpy issue https://github.com/numpy/numpy/issues/12745, so skipping
the test until it's resolved.
```
====================================================== FAILURES
=======================================================
__________________________________________
test_serialize_deserialize_pandas __________________________________________
ValueError: cannot include dtype 'M' in a buffer
The above exception was the direct cause of the following exception:
def test_serialize_deserialize_pandas():
# ARROW-1784, serialize and deserialize DataFrame by decomposing
# BlockManager
df = _fully_loaded_dataframe_example()
> _check_serialize_components_roundtrip(df)
pyarrow/tests/test_convert_pandas.py:2278:
_ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _
_ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _
pyarrow/tests/test_convert_pandas.py:2268: in
_check_serialize_components_roundtrip
components = ctx.serialize(df).to_components()
pyarrow/serialization.pxi:198: in pyarrow.lib.SerializationContext.serialize
return serialize(obj, context=self)
pyarrow/serialization.pxi:345: in pyarrow.lib.serialize
check_status(SerializeObject(context, wrapped_value, &serialized.data))
pyarrow/serialization.pxi:153: in
pyarrow.lib.SerializationContext._serialize_callback
serialized_obj = {"data": self.custom_serializers[type_id](obj)}
_ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _
_ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _
x = MultiIndex(levels=[[2000-01-01 00:00:00, 2000-01-02 00:00:00,
2000-01-03 00:00:00, 2000-01-04 00:00:00, 2000-01-05 00:00:00], ['bar', 'foo']],
labels=[[0, 0, 1, 1, 2, 2, 3, 3, 4, 4], [1, 0, 1, 0, 1, 0, 1, 0,
1, 0]])
def _pickle_to_buffer(x):
> pickled = builtin_pickle.dumps(x,
protocol=builtin_pickle.HIGHEST_PROTOCOL)
E SystemError: <built-in function __import__> returned a result with
an error set
```
Author: Krisztián Szűcs <[email protected]>
Closes #3403 from kszucs/travis_numpy_version and squashes the following
commits:
e3162a8b <Krisztián Szűcs> pin to minor
77e9b64f <Krisztián Szűcs> reason
301226d1 <Krisztián Szűcs> skip serialize test
39a7161d <Krisztián Szűcs> appveyor
ae1f16d9 <Krisztián Szűcs> pin numpy to 1.14
---
ci/appveyor-cpp-build.bat | 15 ++++++++-------
ci/cpp-msvc-build-main.bat | 2 +-
ci/travis_script_python.sh | 4 ++--
python/pyarrow/tests/test_convert_pandas.py | 5 +++--
4 files changed, 14 insertions(+), 12 deletions(-)
diff --git a/ci/appveyor-cpp-build.bat b/ci/appveyor-cpp-build.bat
index 387dd55..78f5e41 100644
--- a/ci/appveyor-cpp-build.bat
+++ b/ci/appveyor-cpp-build.bat
@@ -95,11 +95,12 @@ if "%JOB%" == "Build_Debug" (
exit /B 0
)
-conda create -n arrow -q -y ^
+conda create -n arrow -q -y -c conda-forge ^
+ --file=ci\conda_env_python.yml ^
python=%PYTHON% ^
- six pytest setuptools numpy pandas cython hypothesis ^
- thrift-cpp=0.11.0 boost-cpp ^
- -c conda-forge
+ numpy=1.14 ^
+ thrift-cpp=0.11 ^
+ boost-cpp
call activate arrow
@@ -109,9 +110,9 @@ set BOOST_LIBRARYDIR=%CONDA_PREFIX%\Library\lib
if "%JOB%" == "Toolchain" (
@rem Install pre-built "toolchain" packages for faster builds
- conda install -q -y --file=ci\conda_env_cpp.yml ^
- python=%PYTHON% ^
- -c conda-forge
+ conda install -q -y -c conda-forge ^
+ --file=ci\conda_env_cpp.yml ^
+ python=%PYTHON%
set ARROW_BUILD_TOOLCHAIN=%CONDA_PREFIX%\Library
)
diff --git a/ci/cpp-msvc-build-main.bat b/ci/cpp-msvc-build-main.bat
index 6441707..d9d7e54 100644
--- a/ci/cpp-msvc-build-main.bat
+++ b/ci/cpp-msvc-build-main.bat
@@ -72,7 +72,7 @@ popd
pushd python
-pip install pickle5
+pip install -r requirements.txt pickle5
set PYARROW_CXXFLAGS=%ARROW_CXXFLAGS%
set PYARROW_CMAKE_GENERATOR=%GENERATOR%
diff --git a/ci/travis_script_python.sh b/ci/travis_script_python.sh
index e9a1122..c3e2d19 100755
--- a/ci/travis_script_python.sh
+++ b/ci/travis_script_python.sh
@@ -50,7 +50,7 @@ conda create -y -q -p $CONDA_ENV_DIR \
nomkl \
cmake \
pip \
- numpy=1.13.1 \
+ numpy=1.14 \
python=${PYTHON_VERSION} \
${CONDA_JVM_DEPS}
@@ -124,7 +124,7 @@ $ARROW_CPP_BUILD_DIR/$ARROW_BUILD_TYPE/arrow-python-test
pushd $ARROW_PYTHON_DIR
# Other stuff pip install
-pip install -q -r requirements.txt
+pip install -r requirements.txt
if [ "$PYTHON_VERSION" == "3.6" ]; then
pip install -q pickle5
diff --git a/python/pyarrow/tests/test_convert_pandas.py
b/python/pyarrow/tests/test_convert_pandas.py
index 466d2e9..264b51c 100644
--- a/python/pyarrow/tests/test_convert_pandas.py
+++ b/python/pyarrow/tests/test_convert_pandas.py
@@ -23,6 +23,7 @@ import multiprocessing as mp
from collections import OrderedDict
from datetime import date, datetime, time, timedelta
+from distutils.version import LooseVersion
import hypothesis as h
import hypothesis.extra.pytz as tzst
@@ -2224,8 +2225,6 @@ class TestConvertMisc(object):
def _fully_loaded_dataframe_example():
- from distutils.version import LooseVersion
-
index = pd.MultiIndex.from_arrays([
pd.date_range('2000-01-01', periods=5).repeat(2),
np.tile(np.array(['foo', 'bar'], dtype=object), 5)
@@ -2271,6 +2270,8 @@ def _check_serialize_components_roundtrip(df):
tm.assert_frame_equal(df, deserialized)
[email protected](LooseVersion(np.__version__) >= '0.16',
+ reason='Until numpy/numpy#12745 is resolved')
def test_serialize_deserialize_pandas():
# ARROW-1784, serialize and deserialize DataFrame by decomposing
# BlockManager
