def setUpClass(cls):
ReusedPySparkTestCase.setUpClass()
cls.tempdir = tempfile.NamedTemporaryFile(delete=False)
os.unlink(cls.tempdir.name)
cls.sqlCtx = SQLContext(cls.sc)
cls.testData = [Row(key=i, value=str(i)) for i in range(100)]
rdd = cls.sc.parallelize(cls.testData)
cls.df = rdd.toDF()
def setUpClass(cls):
ReusedPySparkTestCase.setUpClass()
cls.tempdir = tempfile.NamedTemporaryFile(delete=False)
os.unlink(cls.tempdir.name)
print "type", type(cls.sc)
print "type", type(cls.sc._jsc)
_scala_HiveContext =\
cls.sc._jvm.org.apache.spark.sql.hive.test.TestHiveContext(cls.sc._jsc.sc())
cls.sqlCtx = HiveContext(cls.sc, _scala_HiveContext)
cls.testData = [Row(key=i, value=str(i)) for i in range(100)]
cls.df = cls.sc.parallelize(cls.testData).toDF()
def setUpClass(cls):
ReusedPySparkTestCase.setUpClass()
cls.tempdir = tempfile.NamedTemporaryFile(delete=False)
try:
cls.sc._jvm.org.apache.hadoop.hive.conf.HiveConf()
except py4j.protocol.Py4JError:
cls.sqlCtx = None
return
os.unlink(cls.tempdir.name)
_scala_HiveContext = cls.sc._jvm.org.apache.spark.sql.hive.test.TestHiveContext(cls.sc._jsc.sc())
cls.sqlCtx = HiveContext(cls.sc, _scala_HiveContext)
cls.testData = [Row(key=i, value=str(i)) for i in range(100)]
cls.df = cls.sc.parallelize(cls.testData).toDF()
def setUpClass(cls):
ReusedPySparkTestCase.setUpClass()
cls.tempdir = tempfile.NamedTemporaryFile(delete=False)
try:
cls.sc._jvm.org.apache.hadoop.hive.conf.HiveConf()
except py4j.protocol.Py4JError:
cls.sqlCtx = None
return
os.unlink(cls.tempdir.name)
_scala_HiveContext =\
cls.sc._jvm.org.apache.spark.sql.hive.test.TestHiveContext(cls.sc._jsc.sc())
cls.sqlCtx = HiveContext(cls.sc, _scala_HiveContext)
cls.testData = [Row(key=i, value=str(i)) for i in range(100)]
cls.df = cls.sc.parallelize(cls.testData).toDF()
def setUpClass(cls):
ReusedPySparkTestCase.setUpClass()
cls.tempdir = tempfile.NamedTemporaryFile(delete=False)
cls.hive_available = True
try:
cls.sc._jvm.org.apache.hadoop.hive.conf.HiveConf()
except py4j.protocol.Py4JError:
cls.hive_available = False
except TypeError:
cls.hive_available = False
os.unlink(cls.tempdir.name)
if cls.hive_available:
cls.spark = HiveContext._createForTesting(cls.sc)
cls.testData = [Row(key=i, value=str(i)) for i in range(100)]
cls.df = cls.sc.parallelize(cls.testData).toDF()
def setUpClass(cls):
ReusedPySparkTestCase.setUpClass()
cls.tempdir = tempfile.mkdtemp()
def setUpClass(cls):
ReusedPySparkTestCase.setUpClass()
cls.spark = SparkSession(cls.sc)
cls.tempdir = tempfile.mkdtemp()
def setUpClass(cls):
ReusedPySparkTestCase.setUpClass()
cls.spark = SparkSession(cls.sc)
def setUpClass(cls):
PySparkTestCase.setUpClass()
cls.spark = SparkSession(cls.sc)