You are viewing a plain text version of this content. The canonical link for it is here.
Posted to issues@spark.apache.org by "Borys Biletskyy (Jira)" <ji...@apache.org> on 2019/10/10 11:07:00 UTC
[jira] [Updated] (SPARK-29428) Can't persist/set None-valued param
[ https://issues.apache.org/jira/browse/SPARK-29428?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ]
Borys Biletskyy updated SPARK-29428:
------------------------------------
Description:
{code:java}
import pytest
from pyspark import keyword_only
from pyspark.ml import Model
from pyspark.sql import DataFrame
from pyspark.ml.util import DefaultParamsReadable, DefaultParamsWritable
from pyspark.ml.param.shared import HasInputCol
from pyspark.sql.functions import *
class NoneParamTester(Model,
HasInputCol,
DefaultParamsReadable,
DefaultParamsWritable
):
@keyword_only
def __init__(self, inputCol: str = None):
super(NoneParamTester, self).__init__()
kwargs = self._input_kwargs
self.setParams(**kwargs)
@keyword_only
def setParams(self, inputCol: str = None):
kwargs = self._input_kwargs
self._set(**kwargs)
return self
def _transform(self, data: DataFrame) -> DataFrame:
return data
class TestNoneParam(object):
def test_persist_none(self, spark, temp_dir):
path = temp_dir + '/test_model'
model = NoneParamTester(inputCol=None)
assert model.isDefined(model.inputCol)
assert model.isSet(model.inputCol)
assert model.getInputCol() is None
model.write().overwrite().save(path)
NoneParamTester.load(path) # TypeError: Could not convert <class 'NoneType'> to string type
def test_set_none(self, spark):
model = NoneParamTester(inputCol=None)
assert model.isDefined(model.inputCol)
assert model.isSet(model.inputCol)
assert model.getInputCol() is None
model.set(model.inputCol, None) # TypeError: Could not convert <class 'NoneType'> to string type
{code}
was:
{code:java}
import pytest
from pyspark import keyword_only
from pyspark.ml import Model
from pyspark.sql import DataFrame
from pyspark.ml.util import DefaultParamsReadable, DefaultParamsWritable
from pyspark.ml.param.shared import HasInputCol
from pyspark.sql.functions import *
class NoneParamTester(Model,
HasInputCol,
DefaultParamsReadable,
DefaultParamsWritable
):
@keyword_only
def __init__(self, inputCol: str = None):
super(NoneParamTester, self).__init__()
kwargs = self._input_kwargs
self.setParams(**kwargs)
@keyword_only
def setParams(self, inputCol: str = None):
kwargs = self._input_kwargs
self._set(**kwargs)
return self
def _transform(self, data: DataFrame) -> DataFrame:
return data
class TestHasInputColParam(object):
def test_persist_none(self, spark, temp_dir):
path = temp_dir + '/test_model'
model = NoneParamTester(inputCol=None)
assert model.isDefined(model.inputCol)
assert model.isSet(model.inputCol)
assert model.getInputCol() is None
model.write().overwrite().save(path)
NoneParamTester.load(path) # TypeError: Could not convert <class 'NoneType'> to string type
def test_set_none(self, spark):
model = NoneParamTester(inputCol=None)
assert model.isDefined(model.inputCol)
assert model.isSet(model.inputCol)
assert model.getInputCol() is None
model.set(model.inputCol, None) # TypeError: Could not convert <class 'NoneType'> to string type
{code}
> Can't persist/set None-valued param
> ------------------------------------
>
> Key: SPARK-29428
> URL: https://issues.apache.org/jira/browse/SPARK-29428
> Project: Spark
> Issue Type: Bug
> Components: ML, PySpark
> Affects Versions: 2.3.2
> Reporter: Borys Biletskyy
> Priority: Major
>
> {code:java}
> import pytest
> from pyspark import keyword_only
> from pyspark.ml import Model
> from pyspark.sql import DataFrame
> from pyspark.ml.util import DefaultParamsReadable, DefaultParamsWritable
> from pyspark.ml.param.shared import HasInputCol
> from pyspark.sql.functions import *
> class NoneParamTester(Model,
> HasInputCol,
> DefaultParamsReadable,
> DefaultParamsWritable
> ):
> @keyword_only
> def __init__(self, inputCol: str = None):
> super(NoneParamTester, self).__init__()
> kwargs = self._input_kwargs
> self.setParams(**kwargs)
> @keyword_only
> def setParams(self, inputCol: str = None):
> kwargs = self._input_kwargs
> self._set(**kwargs)
> return self
> def _transform(self, data: DataFrame) -> DataFrame:
> return data
> class TestNoneParam(object):
> def test_persist_none(self, spark, temp_dir):
> path = temp_dir + '/test_model'
> model = NoneParamTester(inputCol=None)
> assert model.isDefined(model.inputCol)
> assert model.isSet(model.inputCol)
> assert model.getInputCol() is None
> model.write().overwrite().save(path)
> NoneParamTester.load(path) # TypeError: Could not convert <class 'NoneType'> to string type
> def test_set_none(self, spark):
> model = NoneParamTester(inputCol=None)
> assert model.isDefined(model.inputCol)
> assert model.isSet(model.inputCol)
> assert model.getInputCol() is None
> model.set(model.inputCol, None) # TypeError: Could not convert <class 'NoneType'> to string type
> {code}
--
This message was sent by Atlassian Jira
(v8.3.4#803005)
---------------------------------------------------------------------
To unsubscribe, e-mail: issues-unsubscribe@spark.apache.org
For additional commands, e-mail: issues-help@spark.apache.org