2015-06-30 19:17:46 -04:00
|
|
|
#
|
|
|
|
# Licensed to the Apache Software Foundation (ASF) under one or more
|
|
|
|
# contributor license agreements. See the NOTICE file distributed with
|
|
|
|
# this work for additional information regarding copyright ownership.
|
|
|
|
# The ASF licenses this file to You under the Apache License, Version 2.0
|
|
|
|
# (the "License"); you may not use this file except in compliance with
|
|
|
|
# the License. You may obtain a copy of the License at
|
|
|
|
#
|
|
|
|
# http://www.apache.org/licenses/LICENSE-2.0
|
|
|
|
#
|
|
|
|
# Unless required by applicable law or agreed to in writing, software
|
|
|
|
# distributed under the License is distributed on an "AS IS" BASIS,
|
|
|
|
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
|
|
|
# See the License for the specific language governing permissions and
|
|
|
|
# limitations under the License.
|
|
|
|
#
|
|
|
|
|
|
|
|
import py4j
|
|
|
|
|
|
|
|
|
2015-10-29 00:45:00 -04:00
|
|
|
class CapturedException(Exception):
|
|
|
|
def __init__(self, desc, stackTrace):
|
|
|
|
self.desc = desc
|
|
|
|
self.stackTrace = stackTrace
|
|
|
|
|
|
|
|
def __str__(self):
|
|
|
|
return repr(self.desc)
|
|
|
|
|
|
|
|
|
|
|
|
class AnalysisException(CapturedException):
|
2015-06-30 19:17:46 -04:00
|
|
|
"""
|
|
|
|
Failed to analyze a SQL query plan.
|
|
|
|
"""
|
|
|
|
|
|
|
|
|
2016-03-28 15:31:12 -04:00
|
|
|
class ParseException(CapturedException):
|
|
|
|
"""
|
|
|
|
Failed to parse a SQL command.
|
|
|
|
"""
|
|
|
|
|
|
|
|
|
2015-10-29 00:45:00 -04:00
|
|
|
class IllegalArgumentException(CapturedException):
|
2015-07-19 03:32:56 -04:00
|
|
|
"""
|
|
|
|
Passed an illegal or inappropriate argument.
|
|
|
|
"""
|
|
|
|
|
|
|
|
|
2016-06-15 13:46:02 -04:00
|
|
|
class StreamingQueryException(CapturedException):
|
2016-04-28 18:22:28 -04:00
|
|
|
"""
|
2016-06-15 13:46:02 -04:00
|
|
|
Exception that stopped a :class:`StreamingQuery`.
|
2016-04-28 18:22:28 -04:00
|
|
|
"""
|
|
|
|
|
|
|
|
|
[SPARK-14603][SQL][FOLLOWUP] Verification of Metadata Operations by Session Catalog
#### What changes were proposed in this pull request?
This follow-up PR is to address the remaining comments in https://github.com/apache/spark/pull/12385
The major change in this PR is to issue better error messages in PySpark by using the mechanism that was proposed by davies in https://github.com/apache/spark/pull/7135
For example, in PySpark, if we input the following statement:
```python
>>> l = [('Alice', 1)]
>>> df = sqlContext.createDataFrame(l)
>>> df.createTempView("people")
>>> df.createTempView("people")
```
Before this PR, the exception we will get is like
```
Traceback (most recent call last):
File "<stdin>", line 1, in <module>
File "/Users/xiaoli/IdeaProjects/sparkDelivery/python/pyspark/sql/dataframe.py", line 152, in createTempView
self._jdf.createTempView(name)
File "/Users/xiaoli/IdeaProjects/sparkDelivery/python/lib/py4j-0.10.1-src.zip/py4j/java_gateway.py", line 933, in __call__
File "/Users/xiaoli/IdeaProjects/sparkDelivery/python/pyspark/sql/utils.py", line 63, in deco
return f(*a, **kw)
File "/Users/xiaoli/IdeaProjects/sparkDelivery/python/lib/py4j-0.10.1-src.zip/py4j/protocol.py", line 312, in get_return_value
py4j.protocol.Py4JJavaError: An error occurred while calling o35.createTempView.
: org.apache.spark.sql.catalyst.analysis.TempTableAlreadyExistsException: Temporary table 'people' already exists;
at org.apache.spark.sql.catalyst.catalog.SessionCatalog.createTempView(SessionCatalog.scala:324)
at org.apache.spark.sql.SparkSession.createTempView(SparkSession.scala:523)
at org.apache.spark.sql.Dataset.createTempView(Dataset.scala:2328)
at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
at sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:57)
at sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
at java.lang.reflect.Method.invoke(Method.java:606)
at py4j.reflection.MethodInvoker.invoke(MethodInvoker.java:237)
at py4j.reflection.ReflectionEngine.invoke(ReflectionEngine.java:357)
at py4j.Gateway.invoke(Gateway.java:280)
at py4j.commands.AbstractCommand.invokeMethod(AbstractCommand.java:128)
at py4j.commands.CallCommand.execute(CallCommand.java:79)
at py4j.GatewayConnection.run(GatewayConnection.java:211)
at java.lang.Thread.run(Thread.java:745)
```
After this PR, the exception we will get become cleaner:
```
Traceback (most recent call last):
File "<stdin>", line 1, in <module>
File "/Users/xiaoli/IdeaProjects/sparkDelivery/python/pyspark/sql/dataframe.py", line 152, in createTempView
self._jdf.createTempView(name)
File "/Users/xiaoli/IdeaProjects/sparkDelivery/python/lib/py4j-0.10.1-src.zip/py4j/java_gateway.py", line 933, in __call__
File "/Users/xiaoli/IdeaProjects/sparkDelivery/python/pyspark/sql/utils.py", line 75, in deco
raise AnalysisException(s.split(': ', 1)[1], stackTrace)
pyspark.sql.utils.AnalysisException: u"Temporary table 'people' already exists;"
```
#### How was this patch tested?
Fixed an existing PySpark test case
Author: gatorsmile <gatorsmile@gmail.com>
Closes #13126 from gatorsmile/followup-14684.
2016-05-19 14:46:11 -04:00
|
|
|
class QueryExecutionException(CapturedException):
|
|
|
|
"""
|
|
|
|
Failed to execute a query.
|
|
|
|
"""
|
|
|
|
|
|
|
|
|
2015-06-30 19:17:46 -04:00
|
|
|
def capture_sql_exception(f):
|
|
|
|
def deco(*a, **kw):
|
|
|
|
try:
|
|
|
|
return f(*a, **kw)
|
|
|
|
except py4j.protocol.Py4JJavaError as e:
|
2015-07-01 19:43:18 -04:00
|
|
|
s = e.java_exception.toString()
|
2015-10-29 00:45:00 -04:00
|
|
|
stackTrace = '\n\t at '.join(map(lambda x: x.toString(),
|
|
|
|
e.java_exception.getStackTrace()))
|
2015-07-01 19:43:18 -04:00
|
|
|
if s.startswith('org.apache.spark.sql.AnalysisException: '):
|
2015-10-29 00:45:00 -04:00
|
|
|
raise AnalysisException(s.split(': ', 1)[1], stackTrace)
|
[SPARK-14603][SQL][FOLLOWUP] Verification of Metadata Operations by Session Catalog
#### What changes were proposed in this pull request?
This follow-up PR is to address the remaining comments in https://github.com/apache/spark/pull/12385
The major change in this PR is to issue better error messages in PySpark by using the mechanism that was proposed by davies in https://github.com/apache/spark/pull/7135
For example, in PySpark, if we input the following statement:
```python
>>> l = [('Alice', 1)]
>>> df = sqlContext.createDataFrame(l)
>>> df.createTempView("people")
>>> df.createTempView("people")
```
Before this PR, the exception we will get is like
```
Traceback (most recent call last):
File "<stdin>", line 1, in <module>
File "/Users/xiaoli/IdeaProjects/sparkDelivery/python/pyspark/sql/dataframe.py", line 152, in createTempView
self._jdf.createTempView(name)
File "/Users/xiaoli/IdeaProjects/sparkDelivery/python/lib/py4j-0.10.1-src.zip/py4j/java_gateway.py", line 933, in __call__
File "/Users/xiaoli/IdeaProjects/sparkDelivery/python/pyspark/sql/utils.py", line 63, in deco
return f(*a, **kw)
File "/Users/xiaoli/IdeaProjects/sparkDelivery/python/lib/py4j-0.10.1-src.zip/py4j/protocol.py", line 312, in get_return_value
py4j.protocol.Py4JJavaError: An error occurred while calling o35.createTempView.
: org.apache.spark.sql.catalyst.analysis.TempTableAlreadyExistsException: Temporary table 'people' already exists;
at org.apache.spark.sql.catalyst.catalog.SessionCatalog.createTempView(SessionCatalog.scala:324)
at org.apache.spark.sql.SparkSession.createTempView(SparkSession.scala:523)
at org.apache.spark.sql.Dataset.createTempView(Dataset.scala:2328)
at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
at sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:57)
at sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
at java.lang.reflect.Method.invoke(Method.java:606)
at py4j.reflection.MethodInvoker.invoke(MethodInvoker.java:237)
at py4j.reflection.ReflectionEngine.invoke(ReflectionEngine.java:357)
at py4j.Gateway.invoke(Gateway.java:280)
at py4j.commands.AbstractCommand.invokeMethod(AbstractCommand.java:128)
at py4j.commands.CallCommand.execute(CallCommand.java:79)
at py4j.GatewayConnection.run(GatewayConnection.java:211)
at java.lang.Thread.run(Thread.java:745)
```
After this PR, the exception we will get become cleaner:
```
Traceback (most recent call last):
File "<stdin>", line 1, in <module>
File "/Users/xiaoli/IdeaProjects/sparkDelivery/python/pyspark/sql/dataframe.py", line 152, in createTempView
self._jdf.createTempView(name)
File "/Users/xiaoli/IdeaProjects/sparkDelivery/python/lib/py4j-0.10.1-src.zip/py4j/java_gateway.py", line 933, in __call__
File "/Users/xiaoli/IdeaProjects/sparkDelivery/python/pyspark/sql/utils.py", line 75, in deco
raise AnalysisException(s.split(': ', 1)[1], stackTrace)
pyspark.sql.utils.AnalysisException: u"Temporary table 'people' already exists;"
```
#### How was this patch tested?
Fixed an existing PySpark test case
Author: gatorsmile <gatorsmile@gmail.com>
Closes #13126 from gatorsmile/followup-14684.
2016-05-19 14:46:11 -04:00
|
|
|
if s.startswith('org.apache.spark.sql.catalyst.analysis'):
|
2016-05-10 14:25:39 -04:00
|
|
|
raise AnalysisException(s.split(': ', 1)[1], stackTrace)
|
2016-03-31 12:25:09 -04:00
|
|
|
if s.startswith('org.apache.spark.sql.catalyst.parser.ParseException: '):
|
2016-03-28 15:31:12 -04:00
|
|
|
raise ParseException(s.split(': ', 1)[1], stackTrace)
|
2016-06-15 13:46:02 -04:00
|
|
|
if s.startswith('org.apache.spark.sql.streaming.StreamingQueryException: '):
|
|
|
|
raise StreamingQueryException(s.split(': ', 1)[1], stackTrace)
|
[SPARK-14603][SQL][FOLLOWUP] Verification of Metadata Operations by Session Catalog
#### What changes were proposed in this pull request?
This follow-up PR is to address the remaining comments in https://github.com/apache/spark/pull/12385
The major change in this PR is to issue better error messages in PySpark by using the mechanism that was proposed by davies in https://github.com/apache/spark/pull/7135
For example, in PySpark, if we input the following statement:
```python
>>> l = [('Alice', 1)]
>>> df = sqlContext.createDataFrame(l)
>>> df.createTempView("people")
>>> df.createTempView("people")
```
Before this PR, the exception we will get is like
```
Traceback (most recent call last):
File "<stdin>", line 1, in <module>
File "/Users/xiaoli/IdeaProjects/sparkDelivery/python/pyspark/sql/dataframe.py", line 152, in createTempView
self._jdf.createTempView(name)
File "/Users/xiaoli/IdeaProjects/sparkDelivery/python/lib/py4j-0.10.1-src.zip/py4j/java_gateway.py", line 933, in __call__
File "/Users/xiaoli/IdeaProjects/sparkDelivery/python/pyspark/sql/utils.py", line 63, in deco
return f(*a, **kw)
File "/Users/xiaoli/IdeaProjects/sparkDelivery/python/lib/py4j-0.10.1-src.zip/py4j/protocol.py", line 312, in get_return_value
py4j.protocol.Py4JJavaError: An error occurred while calling o35.createTempView.
: org.apache.spark.sql.catalyst.analysis.TempTableAlreadyExistsException: Temporary table 'people' already exists;
at org.apache.spark.sql.catalyst.catalog.SessionCatalog.createTempView(SessionCatalog.scala:324)
at org.apache.spark.sql.SparkSession.createTempView(SparkSession.scala:523)
at org.apache.spark.sql.Dataset.createTempView(Dataset.scala:2328)
at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
at sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:57)
at sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
at java.lang.reflect.Method.invoke(Method.java:606)
at py4j.reflection.MethodInvoker.invoke(MethodInvoker.java:237)
at py4j.reflection.ReflectionEngine.invoke(ReflectionEngine.java:357)
at py4j.Gateway.invoke(Gateway.java:280)
at py4j.commands.AbstractCommand.invokeMethod(AbstractCommand.java:128)
at py4j.commands.CallCommand.execute(CallCommand.java:79)
at py4j.GatewayConnection.run(GatewayConnection.java:211)
at java.lang.Thread.run(Thread.java:745)
```
After this PR, the exception we will get become cleaner:
```
Traceback (most recent call last):
File "<stdin>", line 1, in <module>
File "/Users/xiaoli/IdeaProjects/sparkDelivery/python/pyspark/sql/dataframe.py", line 152, in createTempView
self._jdf.createTempView(name)
File "/Users/xiaoli/IdeaProjects/sparkDelivery/python/lib/py4j-0.10.1-src.zip/py4j/java_gateway.py", line 933, in __call__
File "/Users/xiaoli/IdeaProjects/sparkDelivery/python/pyspark/sql/utils.py", line 75, in deco
raise AnalysisException(s.split(': ', 1)[1], stackTrace)
pyspark.sql.utils.AnalysisException: u"Temporary table 'people' already exists;"
```
#### How was this patch tested?
Fixed an existing PySpark test case
Author: gatorsmile <gatorsmile@gmail.com>
Closes #13126 from gatorsmile/followup-14684.
2016-05-19 14:46:11 -04:00
|
|
|
if s.startswith('org.apache.spark.sql.execution.QueryExecutionException: '):
|
|
|
|
raise QueryExecutionException(s.split(': ', 1)[1], stackTrace)
|
2015-07-19 03:32:56 -04:00
|
|
|
if s.startswith('java.lang.IllegalArgumentException: '):
|
2015-10-29 00:45:00 -04:00
|
|
|
raise IllegalArgumentException(s.split(': ', 1)[1], stackTrace)
|
2015-06-30 19:17:46 -04:00
|
|
|
raise
|
|
|
|
return deco
|
|
|
|
|
|
|
|
|
|
|
|
def install_exception_handler():
|
|
|
|
"""
|
|
|
|
Hook an exception handler into Py4j, which could capture some SQL exceptions in Java.
|
|
|
|
|
|
|
|
When calling Java API, it will call `get_return_value` to parse the returned object.
|
|
|
|
If any exception happened in JVM, the result will be Java exception object, it raise
|
|
|
|
py4j.protocol.Py4JJavaError. We replace the original `get_return_value` with one that
|
|
|
|
could capture the Java exception and throw a Python one (with the same error message).
|
|
|
|
|
|
|
|
It's idempotent, could be called multiple times.
|
|
|
|
"""
|
|
|
|
original = py4j.protocol.get_return_value
|
|
|
|
# The original `get_return_value` is not patched, it's idempotent.
|
|
|
|
patched = capture_sql_exception(original)
|
2017-01-04 10:07:29 -05:00
|
|
|
# only patch the one used in py4j.java_gateway (call Java API)
|
2015-06-30 19:17:46 -04:00
|
|
|
py4j.java_gateway.get_return_value = patched
|
2015-11-18 11:18:54 -05:00
|
|
|
|
|
|
|
|
|
|
|
def toJArray(gateway, jtype, arr):
|
|
|
|
"""
|
|
|
|
Convert python list to java type array
|
|
|
|
:param gateway: Py4j Gateway
|
|
|
|
:param jtype: java type of element in array
|
|
|
|
:param arr: python type list
|
|
|
|
"""
|
|
|
|
jarr = gateway.new_array(jtype, len(arr))
|
|
|
|
for i in range(0, len(arr)):
|
|
|
|
jarr[i] = arr[i]
|
|
|
|
return jarr
|
2017-12-21 06:43:56 -05:00
|
|
|
|
|
|
|
|
2017-12-22 06:09:51 -05:00
|
|
|
def require_minimum_pandas_version():
|
|
|
|
""" Raise ImportError if minimum version of Pandas is not installed
|
|
|
|
"""
|
[SPARK-23319][TESTS] Explicitly specify Pandas and PyArrow versions in PySpark tests (to skip or test)
## What changes were proposed in this pull request?
This PR proposes to explicitly specify Pandas and PyArrow versions in PySpark tests to skip or test.
We declared the extra dependencies:
https://github.com/apache/spark/blob/b8bfce51abf28c66ba1fc67b0f25fe1617c81025/python/setup.py#L204
In case of PyArrow:
Currently we only check if pyarrow is installed or not without checking the version. It already fails to run tests. For example, if PyArrow 0.7.0 is installed:
```
======================================================================
ERROR: test_vectorized_udf_wrong_return_type (pyspark.sql.tests.ScalarPandasUDF)
----------------------------------------------------------------------
Traceback (most recent call last):
File "/.../spark/python/pyspark/sql/tests.py", line 4019, in test_vectorized_udf_wrong_return_type
f = pandas_udf(lambda x: x * 1.0, MapType(LongType(), LongType()))
File "/.../spark/python/pyspark/sql/functions.py", line 2309, in pandas_udf
return _create_udf(f=f, returnType=return_type, evalType=eval_type)
File "/.../spark/python/pyspark/sql/udf.py", line 47, in _create_udf
require_minimum_pyarrow_version()
File "/.../spark/python/pyspark/sql/utils.py", line 132, in require_minimum_pyarrow_version
"however, your version was %s." % pyarrow.__version__)
ImportError: pyarrow >= 0.8.0 must be installed on calling Python process; however, your version was 0.7.0.
----------------------------------------------------------------------
Ran 33 tests in 8.098s
FAILED (errors=33)
```
In case of Pandas:
There are few tests for old Pandas which were tested only when Pandas version was lower, and I rewrote them to be tested when both Pandas version is lower and missing.
## How was this patch tested?
Manually tested by modifying the condition:
```
test_createDataFrame_column_name_encoding (pyspark.sql.tests.ArrowTests) ... skipped 'Pandas >= 1.19.2 must be installed; however, your version was 0.19.2.'
test_createDataFrame_does_not_modify_input (pyspark.sql.tests.ArrowTests) ... skipped 'Pandas >= 1.19.2 must be installed; however, your version was 0.19.2.'
test_createDataFrame_respect_session_timezone (pyspark.sql.tests.ArrowTests) ... skipped 'Pandas >= 1.19.2 must be installed; however, your version was 0.19.2.'
```
```
test_createDataFrame_column_name_encoding (pyspark.sql.tests.ArrowTests) ... skipped 'Pandas >= 0.19.2 must be installed; however, it was not found.'
test_createDataFrame_does_not_modify_input (pyspark.sql.tests.ArrowTests) ... skipped 'Pandas >= 0.19.2 must be installed; however, it was not found.'
test_createDataFrame_respect_session_timezone (pyspark.sql.tests.ArrowTests) ... skipped 'Pandas >= 0.19.2 must be installed; however, it was not found.'
```
```
test_createDataFrame_column_name_encoding (pyspark.sql.tests.ArrowTests) ... skipped 'PyArrow >= 1.8.0 must be installed; however, your version was 0.8.0.'
test_createDataFrame_does_not_modify_input (pyspark.sql.tests.ArrowTests) ... skipped 'PyArrow >= 1.8.0 must be installed; however, your version was 0.8.0.'
test_createDataFrame_respect_session_timezone (pyspark.sql.tests.ArrowTests) ... skipped 'PyArrow >= 1.8.0 must be installed; however, your version was 0.8.0.'
```
```
test_createDataFrame_column_name_encoding (pyspark.sql.tests.ArrowTests) ... skipped 'PyArrow >= 0.8.0 must be installed; however, it was not found.'
test_createDataFrame_does_not_modify_input (pyspark.sql.tests.ArrowTests) ... skipped 'PyArrow >= 0.8.0 must be installed; however, it was not found.'
test_createDataFrame_respect_session_timezone (pyspark.sql.tests.ArrowTests) ... skipped 'PyArrow >= 0.8.0 must be installed; however, it was not found.'
```
Author: hyukjinkwon <gurwls223@gmail.com>
Closes #20487 from HyukjinKwon/pyarrow-pandas-skip.
2018-02-07 09:28:10 -05:00
|
|
|
# TODO(HyukjinKwon): Relocate and deduplicate the version specification.
|
|
|
|
minimum_pandas_version = "0.19.2"
|
|
|
|
|
2017-12-22 06:09:51 -05:00
|
|
|
from distutils.version import LooseVersion
|
[SPARK-23319][TESTS] Explicitly specify Pandas and PyArrow versions in PySpark tests (to skip or test)
## What changes were proposed in this pull request?
This PR proposes to explicitly specify Pandas and PyArrow versions in PySpark tests to skip or test.
We declared the extra dependencies:
https://github.com/apache/spark/blob/b8bfce51abf28c66ba1fc67b0f25fe1617c81025/python/setup.py#L204
In case of PyArrow:
Currently we only check if pyarrow is installed or not without checking the version. It already fails to run tests. For example, if PyArrow 0.7.0 is installed:
```
======================================================================
ERROR: test_vectorized_udf_wrong_return_type (pyspark.sql.tests.ScalarPandasUDF)
----------------------------------------------------------------------
Traceback (most recent call last):
File "/.../spark/python/pyspark/sql/tests.py", line 4019, in test_vectorized_udf_wrong_return_type
f = pandas_udf(lambda x: x * 1.0, MapType(LongType(), LongType()))
File "/.../spark/python/pyspark/sql/functions.py", line 2309, in pandas_udf
return _create_udf(f=f, returnType=return_type, evalType=eval_type)
File "/.../spark/python/pyspark/sql/udf.py", line 47, in _create_udf
require_minimum_pyarrow_version()
File "/.../spark/python/pyspark/sql/utils.py", line 132, in require_minimum_pyarrow_version
"however, your version was %s." % pyarrow.__version__)
ImportError: pyarrow >= 0.8.0 must be installed on calling Python process; however, your version was 0.7.0.
----------------------------------------------------------------------
Ran 33 tests in 8.098s
FAILED (errors=33)
```
In case of Pandas:
There are few tests for old Pandas which were tested only when Pandas version was lower, and I rewrote them to be tested when both Pandas version is lower and missing.
## How was this patch tested?
Manually tested by modifying the condition:
```
test_createDataFrame_column_name_encoding (pyspark.sql.tests.ArrowTests) ... skipped 'Pandas >= 1.19.2 must be installed; however, your version was 0.19.2.'
test_createDataFrame_does_not_modify_input (pyspark.sql.tests.ArrowTests) ... skipped 'Pandas >= 1.19.2 must be installed; however, your version was 0.19.2.'
test_createDataFrame_respect_session_timezone (pyspark.sql.tests.ArrowTests) ... skipped 'Pandas >= 1.19.2 must be installed; however, your version was 0.19.2.'
```
```
test_createDataFrame_column_name_encoding (pyspark.sql.tests.ArrowTests) ... skipped 'Pandas >= 0.19.2 must be installed; however, it was not found.'
test_createDataFrame_does_not_modify_input (pyspark.sql.tests.ArrowTests) ... skipped 'Pandas >= 0.19.2 must be installed; however, it was not found.'
test_createDataFrame_respect_session_timezone (pyspark.sql.tests.ArrowTests) ... skipped 'Pandas >= 0.19.2 must be installed; however, it was not found.'
```
```
test_createDataFrame_column_name_encoding (pyspark.sql.tests.ArrowTests) ... skipped 'PyArrow >= 1.8.0 must be installed; however, your version was 0.8.0.'
test_createDataFrame_does_not_modify_input (pyspark.sql.tests.ArrowTests) ... skipped 'PyArrow >= 1.8.0 must be installed; however, your version was 0.8.0.'
test_createDataFrame_respect_session_timezone (pyspark.sql.tests.ArrowTests) ... skipped 'PyArrow >= 1.8.0 must be installed; however, your version was 0.8.0.'
```
```
test_createDataFrame_column_name_encoding (pyspark.sql.tests.ArrowTests) ... skipped 'PyArrow >= 0.8.0 must be installed; however, it was not found.'
test_createDataFrame_does_not_modify_input (pyspark.sql.tests.ArrowTests) ... skipped 'PyArrow >= 0.8.0 must be installed; however, it was not found.'
test_createDataFrame_respect_session_timezone (pyspark.sql.tests.ArrowTests) ... skipped 'PyArrow >= 0.8.0 must be installed; however, it was not found.'
```
Author: hyukjinkwon <gurwls223@gmail.com>
Closes #20487 from HyukjinKwon/pyarrow-pandas-skip.
2018-02-07 09:28:10 -05:00
|
|
|
try:
|
|
|
|
import pandas
|
2018-03-27 23:06:12 -04:00
|
|
|
have_pandas = True
|
[SPARK-23319][TESTS] Explicitly specify Pandas and PyArrow versions in PySpark tests (to skip or test)
## What changes were proposed in this pull request?
This PR proposes to explicitly specify Pandas and PyArrow versions in PySpark tests to skip or test.
We declared the extra dependencies:
https://github.com/apache/spark/blob/b8bfce51abf28c66ba1fc67b0f25fe1617c81025/python/setup.py#L204
In case of PyArrow:
Currently we only check if pyarrow is installed or not without checking the version. It already fails to run tests. For example, if PyArrow 0.7.0 is installed:
```
======================================================================
ERROR: test_vectorized_udf_wrong_return_type (pyspark.sql.tests.ScalarPandasUDF)
----------------------------------------------------------------------
Traceback (most recent call last):
File "/.../spark/python/pyspark/sql/tests.py", line 4019, in test_vectorized_udf_wrong_return_type
f = pandas_udf(lambda x: x * 1.0, MapType(LongType(), LongType()))
File "/.../spark/python/pyspark/sql/functions.py", line 2309, in pandas_udf
return _create_udf(f=f, returnType=return_type, evalType=eval_type)
File "/.../spark/python/pyspark/sql/udf.py", line 47, in _create_udf
require_minimum_pyarrow_version()
File "/.../spark/python/pyspark/sql/utils.py", line 132, in require_minimum_pyarrow_version
"however, your version was %s." % pyarrow.__version__)
ImportError: pyarrow >= 0.8.0 must be installed on calling Python process; however, your version was 0.7.0.
----------------------------------------------------------------------
Ran 33 tests in 8.098s
FAILED (errors=33)
```
In case of Pandas:
There are few tests for old Pandas which were tested only when Pandas version was lower, and I rewrote them to be tested when both Pandas version is lower and missing.
## How was this patch tested?
Manually tested by modifying the condition:
```
test_createDataFrame_column_name_encoding (pyspark.sql.tests.ArrowTests) ... skipped 'Pandas >= 1.19.2 must be installed; however, your version was 0.19.2.'
test_createDataFrame_does_not_modify_input (pyspark.sql.tests.ArrowTests) ... skipped 'Pandas >= 1.19.2 must be installed; however, your version was 0.19.2.'
test_createDataFrame_respect_session_timezone (pyspark.sql.tests.ArrowTests) ... skipped 'Pandas >= 1.19.2 must be installed; however, your version was 0.19.2.'
```
```
test_createDataFrame_column_name_encoding (pyspark.sql.tests.ArrowTests) ... skipped 'Pandas >= 0.19.2 must be installed; however, it was not found.'
test_createDataFrame_does_not_modify_input (pyspark.sql.tests.ArrowTests) ... skipped 'Pandas >= 0.19.2 must be installed; however, it was not found.'
test_createDataFrame_respect_session_timezone (pyspark.sql.tests.ArrowTests) ... skipped 'Pandas >= 0.19.2 must be installed; however, it was not found.'
```
```
test_createDataFrame_column_name_encoding (pyspark.sql.tests.ArrowTests) ... skipped 'PyArrow >= 1.8.0 must be installed; however, your version was 0.8.0.'
test_createDataFrame_does_not_modify_input (pyspark.sql.tests.ArrowTests) ... skipped 'PyArrow >= 1.8.0 must be installed; however, your version was 0.8.0.'
test_createDataFrame_respect_session_timezone (pyspark.sql.tests.ArrowTests) ... skipped 'PyArrow >= 1.8.0 must be installed; however, your version was 0.8.0.'
```
```
test_createDataFrame_column_name_encoding (pyspark.sql.tests.ArrowTests) ... skipped 'PyArrow >= 0.8.0 must be installed; however, it was not found.'
test_createDataFrame_does_not_modify_input (pyspark.sql.tests.ArrowTests) ... skipped 'PyArrow >= 0.8.0 must be installed; however, it was not found.'
test_createDataFrame_respect_session_timezone (pyspark.sql.tests.ArrowTests) ... skipped 'PyArrow >= 0.8.0 must be installed; however, it was not found.'
```
Author: hyukjinkwon <gurwls223@gmail.com>
Closes #20487 from HyukjinKwon/pyarrow-pandas-skip.
2018-02-07 09:28:10 -05:00
|
|
|
except ImportError:
|
2018-03-27 23:06:12 -04:00
|
|
|
have_pandas = False
|
|
|
|
if not have_pandas:
|
[SPARK-23319][TESTS] Explicitly specify Pandas and PyArrow versions in PySpark tests (to skip or test)
## What changes were proposed in this pull request?
This PR proposes to explicitly specify Pandas and PyArrow versions in PySpark tests to skip or test.
We declared the extra dependencies:
https://github.com/apache/spark/blob/b8bfce51abf28c66ba1fc67b0f25fe1617c81025/python/setup.py#L204
In case of PyArrow:
Currently we only check if pyarrow is installed or not without checking the version. It already fails to run tests. For example, if PyArrow 0.7.0 is installed:
```
======================================================================
ERROR: test_vectorized_udf_wrong_return_type (pyspark.sql.tests.ScalarPandasUDF)
----------------------------------------------------------------------
Traceback (most recent call last):
File "/.../spark/python/pyspark/sql/tests.py", line 4019, in test_vectorized_udf_wrong_return_type
f = pandas_udf(lambda x: x * 1.0, MapType(LongType(), LongType()))
File "/.../spark/python/pyspark/sql/functions.py", line 2309, in pandas_udf
return _create_udf(f=f, returnType=return_type, evalType=eval_type)
File "/.../spark/python/pyspark/sql/udf.py", line 47, in _create_udf
require_minimum_pyarrow_version()
File "/.../spark/python/pyspark/sql/utils.py", line 132, in require_minimum_pyarrow_version
"however, your version was %s." % pyarrow.__version__)
ImportError: pyarrow >= 0.8.0 must be installed on calling Python process; however, your version was 0.7.0.
----------------------------------------------------------------------
Ran 33 tests in 8.098s
FAILED (errors=33)
```
In case of Pandas:
There are few tests for old Pandas which were tested only when Pandas version was lower, and I rewrote them to be tested when both Pandas version is lower and missing.
## How was this patch tested?
Manually tested by modifying the condition:
```
test_createDataFrame_column_name_encoding (pyspark.sql.tests.ArrowTests) ... skipped 'Pandas >= 1.19.2 must be installed; however, your version was 0.19.2.'
test_createDataFrame_does_not_modify_input (pyspark.sql.tests.ArrowTests) ... skipped 'Pandas >= 1.19.2 must be installed; however, your version was 0.19.2.'
test_createDataFrame_respect_session_timezone (pyspark.sql.tests.ArrowTests) ... skipped 'Pandas >= 1.19.2 must be installed; however, your version was 0.19.2.'
```
```
test_createDataFrame_column_name_encoding (pyspark.sql.tests.ArrowTests) ... skipped 'Pandas >= 0.19.2 must be installed; however, it was not found.'
test_createDataFrame_does_not_modify_input (pyspark.sql.tests.ArrowTests) ... skipped 'Pandas >= 0.19.2 must be installed; however, it was not found.'
test_createDataFrame_respect_session_timezone (pyspark.sql.tests.ArrowTests) ... skipped 'Pandas >= 0.19.2 must be installed; however, it was not found.'
```
```
test_createDataFrame_column_name_encoding (pyspark.sql.tests.ArrowTests) ... skipped 'PyArrow >= 1.8.0 must be installed; however, your version was 0.8.0.'
test_createDataFrame_does_not_modify_input (pyspark.sql.tests.ArrowTests) ... skipped 'PyArrow >= 1.8.0 must be installed; however, your version was 0.8.0.'
test_createDataFrame_respect_session_timezone (pyspark.sql.tests.ArrowTests) ... skipped 'PyArrow >= 1.8.0 must be installed; however, your version was 0.8.0.'
```
```
test_createDataFrame_column_name_encoding (pyspark.sql.tests.ArrowTests) ... skipped 'PyArrow >= 0.8.0 must be installed; however, it was not found.'
test_createDataFrame_does_not_modify_input (pyspark.sql.tests.ArrowTests) ... skipped 'PyArrow >= 0.8.0 must be installed; however, it was not found.'
test_createDataFrame_respect_session_timezone (pyspark.sql.tests.ArrowTests) ... skipped 'PyArrow >= 0.8.0 must be installed; however, it was not found.'
```
Author: hyukjinkwon <gurwls223@gmail.com>
Closes #20487 from HyukjinKwon/pyarrow-pandas-skip.
2018-02-07 09:28:10 -05:00
|
|
|
raise ImportError("Pandas >= %s must be installed; however, "
|
|
|
|
"it was not found." % minimum_pandas_version)
|
|
|
|
if LooseVersion(pandas.__version__) < LooseVersion(minimum_pandas_version):
|
|
|
|
raise ImportError("Pandas >= %s must be installed; however, "
|
|
|
|
"your version was %s." % (minimum_pandas_version, pandas.__version__))
|
2017-12-22 06:09:51 -05:00
|
|
|
|
|
|
|
|
|
|
|
def require_minimum_pyarrow_version():
|
2017-12-21 06:43:56 -05:00
|
|
|
""" Raise ImportError if minimum version of pyarrow is not installed
|
|
|
|
"""
|
[SPARK-23319][TESTS] Explicitly specify Pandas and PyArrow versions in PySpark tests (to skip or test)
## What changes were proposed in this pull request?
This PR proposes to explicitly specify Pandas and PyArrow versions in PySpark tests to skip or test.
We declared the extra dependencies:
https://github.com/apache/spark/blob/b8bfce51abf28c66ba1fc67b0f25fe1617c81025/python/setup.py#L204
In case of PyArrow:
Currently we only check if pyarrow is installed or not without checking the version. It already fails to run tests. For example, if PyArrow 0.7.0 is installed:
```
======================================================================
ERROR: test_vectorized_udf_wrong_return_type (pyspark.sql.tests.ScalarPandasUDF)
----------------------------------------------------------------------
Traceback (most recent call last):
File "/.../spark/python/pyspark/sql/tests.py", line 4019, in test_vectorized_udf_wrong_return_type
f = pandas_udf(lambda x: x * 1.0, MapType(LongType(), LongType()))
File "/.../spark/python/pyspark/sql/functions.py", line 2309, in pandas_udf
return _create_udf(f=f, returnType=return_type, evalType=eval_type)
File "/.../spark/python/pyspark/sql/udf.py", line 47, in _create_udf
require_minimum_pyarrow_version()
File "/.../spark/python/pyspark/sql/utils.py", line 132, in require_minimum_pyarrow_version
"however, your version was %s." % pyarrow.__version__)
ImportError: pyarrow >= 0.8.0 must be installed on calling Python process; however, your version was 0.7.0.
----------------------------------------------------------------------
Ran 33 tests in 8.098s
FAILED (errors=33)
```
In case of Pandas:
There are few tests for old Pandas which were tested only when Pandas version was lower, and I rewrote them to be tested when both Pandas version is lower and missing.
## How was this patch tested?
Manually tested by modifying the condition:
```
test_createDataFrame_column_name_encoding (pyspark.sql.tests.ArrowTests) ... skipped 'Pandas >= 1.19.2 must be installed; however, your version was 0.19.2.'
test_createDataFrame_does_not_modify_input (pyspark.sql.tests.ArrowTests) ... skipped 'Pandas >= 1.19.2 must be installed; however, your version was 0.19.2.'
test_createDataFrame_respect_session_timezone (pyspark.sql.tests.ArrowTests) ... skipped 'Pandas >= 1.19.2 must be installed; however, your version was 0.19.2.'
```
```
test_createDataFrame_column_name_encoding (pyspark.sql.tests.ArrowTests) ... skipped 'Pandas >= 0.19.2 must be installed; however, it was not found.'
test_createDataFrame_does_not_modify_input (pyspark.sql.tests.ArrowTests) ... skipped 'Pandas >= 0.19.2 must be installed; however, it was not found.'
test_createDataFrame_respect_session_timezone (pyspark.sql.tests.ArrowTests) ... skipped 'Pandas >= 0.19.2 must be installed; however, it was not found.'
```
```
test_createDataFrame_column_name_encoding (pyspark.sql.tests.ArrowTests) ... skipped 'PyArrow >= 1.8.0 must be installed; however, your version was 0.8.0.'
test_createDataFrame_does_not_modify_input (pyspark.sql.tests.ArrowTests) ... skipped 'PyArrow >= 1.8.0 must be installed; however, your version was 0.8.0.'
test_createDataFrame_respect_session_timezone (pyspark.sql.tests.ArrowTests) ... skipped 'PyArrow >= 1.8.0 must be installed; however, your version was 0.8.0.'
```
```
test_createDataFrame_column_name_encoding (pyspark.sql.tests.ArrowTests) ... skipped 'PyArrow >= 0.8.0 must be installed; however, it was not found.'
test_createDataFrame_does_not_modify_input (pyspark.sql.tests.ArrowTests) ... skipped 'PyArrow >= 0.8.0 must be installed; however, it was not found.'
test_createDataFrame_respect_session_timezone (pyspark.sql.tests.ArrowTests) ... skipped 'PyArrow >= 0.8.0 must be installed; however, it was not found.'
```
Author: hyukjinkwon <gurwls223@gmail.com>
Closes #20487 from HyukjinKwon/pyarrow-pandas-skip.
2018-02-07 09:28:10 -05:00
|
|
|
# TODO(HyukjinKwon): Relocate and deduplicate the version specification.
|
|
|
|
minimum_pyarrow_version = "0.8.0"
|
|
|
|
|
2017-12-21 06:43:56 -05:00
|
|
|
from distutils.version import LooseVersion
|
[SPARK-23319][TESTS] Explicitly specify Pandas and PyArrow versions in PySpark tests (to skip or test)
## What changes were proposed in this pull request?
This PR proposes to explicitly specify Pandas and PyArrow versions in PySpark tests to skip or test.
We declared the extra dependencies:
https://github.com/apache/spark/blob/b8bfce51abf28c66ba1fc67b0f25fe1617c81025/python/setup.py#L204
In case of PyArrow:
Currently we only check if pyarrow is installed or not without checking the version. It already fails to run tests. For example, if PyArrow 0.7.0 is installed:
```
======================================================================
ERROR: test_vectorized_udf_wrong_return_type (pyspark.sql.tests.ScalarPandasUDF)
----------------------------------------------------------------------
Traceback (most recent call last):
File "/.../spark/python/pyspark/sql/tests.py", line 4019, in test_vectorized_udf_wrong_return_type
f = pandas_udf(lambda x: x * 1.0, MapType(LongType(), LongType()))
File "/.../spark/python/pyspark/sql/functions.py", line 2309, in pandas_udf
return _create_udf(f=f, returnType=return_type, evalType=eval_type)
File "/.../spark/python/pyspark/sql/udf.py", line 47, in _create_udf
require_minimum_pyarrow_version()
File "/.../spark/python/pyspark/sql/utils.py", line 132, in require_minimum_pyarrow_version
"however, your version was %s." % pyarrow.__version__)
ImportError: pyarrow >= 0.8.0 must be installed on calling Python process; however, your version was 0.7.0.
----------------------------------------------------------------------
Ran 33 tests in 8.098s
FAILED (errors=33)
```
In case of Pandas:
There are few tests for old Pandas which were tested only when Pandas version was lower, and I rewrote them to be tested when both Pandas version is lower and missing.
## How was this patch tested?
Manually tested by modifying the condition:
```
test_createDataFrame_column_name_encoding (pyspark.sql.tests.ArrowTests) ... skipped 'Pandas >= 1.19.2 must be installed; however, your version was 0.19.2.'
test_createDataFrame_does_not_modify_input (pyspark.sql.tests.ArrowTests) ... skipped 'Pandas >= 1.19.2 must be installed; however, your version was 0.19.2.'
test_createDataFrame_respect_session_timezone (pyspark.sql.tests.ArrowTests) ... skipped 'Pandas >= 1.19.2 must be installed; however, your version was 0.19.2.'
```
```
test_createDataFrame_column_name_encoding (pyspark.sql.tests.ArrowTests) ... skipped 'Pandas >= 0.19.2 must be installed; however, it was not found.'
test_createDataFrame_does_not_modify_input (pyspark.sql.tests.ArrowTests) ... skipped 'Pandas >= 0.19.2 must be installed; however, it was not found.'
test_createDataFrame_respect_session_timezone (pyspark.sql.tests.ArrowTests) ... skipped 'Pandas >= 0.19.2 must be installed; however, it was not found.'
```
```
test_createDataFrame_column_name_encoding (pyspark.sql.tests.ArrowTests) ... skipped 'PyArrow >= 1.8.0 must be installed; however, your version was 0.8.0.'
test_createDataFrame_does_not_modify_input (pyspark.sql.tests.ArrowTests) ... skipped 'PyArrow >= 1.8.0 must be installed; however, your version was 0.8.0.'
test_createDataFrame_respect_session_timezone (pyspark.sql.tests.ArrowTests) ... skipped 'PyArrow >= 1.8.0 must be installed; however, your version was 0.8.0.'
```
```
test_createDataFrame_column_name_encoding (pyspark.sql.tests.ArrowTests) ... skipped 'PyArrow >= 0.8.0 must be installed; however, it was not found.'
test_createDataFrame_does_not_modify_input (pyspark.sql.tests.ArrowTests) ... skipped 'PyArrow >= 0.8.0 must be installed; however, it was not found.'
test_createDataFrame_respect_session_timezone (pyspark.sql.tests.ArrowTests) ... skipped 'PyArrow >= 0.8.0 must be installed; however, it was not found.'
```
Author: hyukjinkwon <gurwls223@gmail.com>
Closes #20487 from HyukjinKwon/pyarrow-pandas-skip.
2018-02-07 09:28:10 -05:00
|
|
|
try:
|
|
|
|
import pyarrow
|
2018-03-27 23:06:12 -04:00
|
|
|
have_arrow = True
|
[SPARK-23319][TESTS] Explicitly specify Pandas and PyArrow versions in PySpark tests (to skip or test)
## What changes were proposed in this pull request?
This PR proposes to explicitly specify Pandas and PyArrow versions in PySpark tests to skip or test.
We declared the extra dependencies:
https://github.com/apache/spark/blob/b8bfce51abf28c66ba1fc67b0f25fe1617c81025/python/setup.py#L204
In case of PyArrow:
Currently we only check if pyarrow is installed or not without checking the version. It already fails to run tests. For example, if PyArrow 0.7.0 is installed:
```
======================================================================
ERROR: test_vectorized_udf_wrong_return_type (pyspark.sql.tests.ScalarPandasUDF)
----------------------------------------------------------------------
Traceback (most recent call last):
File "/.../spark/python/pyspark/sql/tests.py", line 4019, in test_vectorized_udf_wrong_return_type
f = pandas_udf(lambda x: x * 1.0, MapType(LongType(), LongType()))
File "/.../spark/python/pyspark/sql/functions.py", line 2309, in pandas_udf
return _create_udf(f=f, returnType=return_type, evalType=eval_type)
File "/.../spark/python/pyspark/sql/udf.py", line 47, in _create_udf
require_minimum_pyarrow_version()
File "/.../spark/python/pyspark/sql/utils.py", line 132, in require_minimum_pyarrow_version
"however, your version was %s." % pyarrow.__version__)
ImportError: pyarrow >= 0.8.0 must be installed on calling Python process; however, your version was 0.7.0.
----------------------------------------------------------------------
Ran 33 tests in 8.098s
FAILED (errors=33)
```
In case of Pandas:
There are few tests for old Pandas which were tested only when Pandas version was lower, and I rewrote them to be tested when both Pandas version is lower and missing.
## How was this patch tested?
Manually tested by modifying the condition:
```
test_createDataFrame_column_name_encoding (pyspark.sql.tests.ArrowTests) ... skipped 'Pandas >= 1.19.2 must be installed; however, your version was 0.19.2.'
test_createDataFrame_does_not_modify_input (pyspark.sql.tests.ArrowTests) ... skipped 'Pandas >= 1.19.2 must be installed; however, your version was 0.19.2.'
test_createDataFrame_respect_session_timezone (pyspark.sql.tests.ArrowTests) ... skipped 'Pandas >= 1.19.2 must be installed; however, your version was 0.19.2.'
```
```
test_createDataFrame_column_name_encoding (pyspark.sql.tests.ArrowTests) ... skipped 'Pandas >= 0.19.2 must be installed; however, it was not found.'
test_createDataFrame_does_not_modify_input (pyspark.sql.tests.ArrowTests) ... skipped 'Pandas >= 0.19.2 must be installed; however, it was not found.'
test_createDataFrame_respect_session_timezone (pyspark.sql.tests.ArrowTests) ... skipped 'Pandas >= 0.19.2 must be installed; however, it was not found.'
```
```
test_createDataFrame_column_name_encoding (pyspark.sql.tests.ArrowTests) ... skipped 'PyArrow >= 1.8.0 must be installed; however, your version was 0.8.0.'
test_createDataFrame_does_not_modify_input (pyspark.sql.tests.ArrowTests) ... skipped 'PyArrow >= 1.8.0 must be installed; however, your version was 0.8.0.'
test_createDataFrame_respect_session_timezone (pyspark.sql.tests.ArrowTests) ... skipped 'PyArrow >= 1.8.0 must be installed; however, your version was 0.8.0.'
```
```
test_createDataFrame_column_name_encoding (pyspark.sql.tests.ArrowTests) ... skipped 'PyArrow >= 0.8.0 must be installed; however, it was not found.'
test_createDataFrame_does_not_modify_input (pyspark.sql.tests.ArrowTests) ... skipped 'PyArrow >= 0.8.0 must be installed; however, it was not found.'
test_createDataFrame_respect_session_timezone (pyspark.sql.tests.ArrowTests) ... skipped 'PyArrow >= 0.8.0 must be installed; however, it was not found.'
```
Author: hyukjinkwon <gurwls223@gmail.com>
Closes #20487 from HyukjinKwon/pyarrow-pandas-skip.
2018-02-07 09:28:10 -05:00
|
|
|
except ImportError:
|
2018-03-27 23:06:12 -04:00
|
|
|
have_arrow = False
|
|
|
|
if not have_arrow:
|
[SPARK-23319][TESTS] Explicitly specify Pandas and PyArrow versions in PySpark tests (to skip or test)
## What changes were proposed in this pull request?
This PR proposes to explicitly specify Pandas and PyArrow versions in PySpark tests to skip or test.
We declared the extra dependencies:
https://github.com/apache/spark/blob/b8bfce51abf28c66ba1fc67b0f25fe1617c81025/python/setup.py#L204
In case of PyArrow:
Currently we only check if pyarrow is installed or not without checking the version. It already fails to run tests. For example, if PyArrow 0.7.0 is installed:
```
======================================================================
ERROR: test_vectorized_udf_wrong_return_type (pyspark.sql.tests.ScalarPandasUDF)
----------------------------------------------------------------------
Traceback (most recent call last):
File "/.../spark/python/pyspark/sql/tests.py", line 4019, in test_vectorized_udf_wrong_return_type
f = pandas_udf(lambda x: x * 1.0, MapType(LongType(), LongType()))
File "/.../spark/python/pyspark/sql/functions.py", line 2309, in pandas_udf
return _create_udf(f=f, returnType=return_type, evalType=eval_type)
File "/.../spark/python/pyspark/sql/udf.py", line 47, in _create_udf
require_minimum_pyarrow_version()
File "/.../spark/python/pyspark/sql/utils.py", line 132, in require_minimum_pyarrow_version
"however, your version was %s." % pyarrow.__version__)
ImportError: pyarrow >= 0.8.0 must be installed on calling Python process; however, your version was 0.7.0.
----------------------------------------------------------------------
Ran 33 tests in 8.098s
FAILED (errors=33)
```
In case of Pandas:
There are few tests for old Pandas which were tested only when Pandas version was lower, and I rewrote them to be tested when both Pandas version is lower and missing.
## How was this patch tested?
Manually tested by modifying the condition:
```
test_createDataFrame_column_name_encoding (pyspark.sql.tests.ArrowTests) ... skipped 'Pandas >= 1.19.2 must be installed; however, your version was 0.19.2.'
test_createDataFrame_does_not_modify_input (pyspark.sql.tests.ArrowTests) ... skipped 'Pandas >= 1.19.2 must be installed; however, your version was 0.19.2.'
test_createDataFrame_respect_session_timezone (pyspark.sql.tests.ArrowTests) ... skipped 'Pandas >= 1.19.2 must be installed; however, your version was 0.19.2.'
```
```
test_createDataFrame_column_name_encoding (pyspark.sql.tests.ArrowTests) ... skipped 'Pandas >= 0.19.2 must be installed; however, it was not found.'
test_createDataFrame_does_not_modify_input (pyspark.sql.tests.ArrowTests) ... skipped 'Pandas >= 0.19.2 must be installed; however, it was not found.'
test_createDataFrame_respect_session_timezone (pyspark.sql.tests.ArrowTests) ... skipped 'Pandas >= 0.19.2 must be installed; however, it was not found.'
```
```
test_createDataFrame_column_name_encoding (pyspark.sql.tests.ArrowTests) ... skipped 'PyArrow >= 1.8.0 must be installed; however, your version was 0.8.0.'
test_createDataFrame_does_not_modify_input (pyspark.sql.tests.ArrowTests) ... skipped 'PyArrow >= 1.8.0 must be installed; however, your version was 0.8.0.'
test_createDataFrame_respect_session_timezone (pyspark.sql.tests.ArrowTests) ... skipped 'PyArrow >= 1.8.0 must be installed; however, your version was 0.8.0.'
```
```
test_createDataFrame_column_name_encoding (pyspark.sql.tests.ArrowTests) ... skipped 'PyArrow >= 0.8.0 must be installed; however, it was not found.'
test_createDataFrame_does_not_modify_input (pyspark.sql.tests.ArrowTests) ... skipped 'PyArrow >= 0.8.0 must be installed; however, it was not found.'
test_createDataFrame_respect_session_timezone (pyspark.sql.tests.ArrowTests) ... skipped 'PyArrow >= 0.8.0 must be installed; however, it was not found.'
```
Author: hyukjinkwon <gurwls223@gmail.com>
Closes #20487 from HyukjinKwon/pyarrow-pandas-skip.
2018-02-07 09:28:10 -05:00
|
|
|
raise ImportError("PyArrow >= %s must be installed; however, "
|
|
|
|
"it was not found." % minimum_pyarrow_version)
|
|
|
|
if LooseVersion(pyarrow.__version__) < LooseVersion(minimum_pyarrow_version):
|
|
|
|
raise ImportError("PyArrow >= %s must be installed; however, "
|
|
|
|
"your version was %s." % (minimum_pyarrow_version, pyarrow.__version__))
|
2018-06-19 16:56:51 -04:00
|
|
|
|
|
|
|
|
2018-08-27 22:57:13 -04:00
|
|
|
def require_test_compiled():
|
|
|
|
""" Raise Exception if test classes are not compiled
|
|
|
|
"""
|
|
|
|
import os
|
|
|
|
import glob
|
|
|
|
try:
|
|
|
|
spark_home = os.environ['SPARK_HOME']
|
|
|
|
except KeyError:
|
|
|
|
raise RuntimeError('SPARK_HOME is not defined in environment')
|
|
|
|
|
|
|
|
test_class_path = os.path.join(
|
|
|
|
spark_home, 'sql', 'core', 'target', '*', 'test-classes')
|
|
|
|
paths = glob.glob(test_class_path)
|
|
|
|
|
|
|
|
if len(paths) == 0:
|
|
|
|
raise RuntimeError(
|
|
|
|
"%s doesn't exist. Spark sql test classes are not compiled." % test_class_path)
|
|
|
|
|
|
|
|
|
2018-06-19 16:56:51 -04:00
|
|
|
class ForeachBatchFunction(object):
|
|
|
|
"""
|
|
|
|
This is the Python implementation of Java interface 'ForeachBatchFunction'. This wraps
|
|
|
|
the user-defined 'foreachBatch' function such that it can be called from the JVM when
|
|
|
|
the query is active.
|
|
|
|
"""
|
|
|
|
|
|
|
|
def __init__(self, sql_ctx, func):
|
|
|
|
self.sql_ctx = sql_ctx
|
|
|
|
self.func = func
|
|
|
|
|
|
|
|
def call(self, jdf, batch_id):
|
|
|
|
from pyspark.sql.dataframe import DataFrame
|
|
|
|
try:
|
|
|
|
self.func(DataFrame(jdf, self.sql_ctx), batch_id)
|
|
|
|
except Exception as e:
|
|
|
|
self.error = e
|
|
|
|
raise e
|
|
|
|
|
|
|
|
class Java:
|
|
|
|
implements = ['org.apache.spark.sql.execution.streaming.sources.PythonForeachBatchFunction']
|