def _test():
import doctest
from pyspark.context import SparkContext
from pyspark.sql import Row, SQLContext, SparkSession
import pyspark.sql.dataframe
from pyspark.sql.functions import from_unixtime
globs = pyspark.sql.dataframe.__dict__.copy()
sc = SparkContext('local[4]', 'PythonTest')
globs['sc'] = sc
globs['sqlContext'] = SQLContext(sc)
globs['spark'] = SparkSession(sc)
globs['df'] = sc.parallelize([(2, 'Alice'), (5, 'Bob')])\
.toDF(StructType([StructField('age', IntegerType()),
StructField('name', StringType())]))
globs['df2'] = sc.parallelize([Row(name='Tom', height=80), Row(name='Bob', height=85)]).toDF()
globs['df3'] = sc.parallelize([Row(name='Alice', age=2),
Row(name='Bob', age=5)]).toDF()
globs['df4'] = sc.parallelize([Row(name='Alice', age=10, height=80),
Row(name='Bob', age=5, height=None),
Row(name='Tom', age=None, height=None),
Row(name=None, age=None, height=None)]).toDF()
globs['sdf'] = sc.parallelize([Row(name='Tom', time=1479441846),
Row(name='Bob', time=1479442946)]).toDF()
(failure_count, test_count) = doctest.testmod(
pyspark.sql.dataframe, globs=globs,
optionflags=doctest.ELLIPSIS | doctest.NORMALIZE_WHITESPACE | doctest.REPORT_NDIFF)
globs['sc'].stop()
if failure_count:
exit(-1)
python类ELLIPSIS的实例源码
def _test():
import os
import doctest
import tempfile
from pyspark.context import SparkContext
from pyspark.sql import Row, SQLContext
import pyspark.sql.context
os.chdir(os.environ["SPARK_HOME"])
globs = pyspark.sql.context.__dict__.copy()
sc = SparkContext('local[4]', 'PythonTest')
globs['tempfile'] = tempfile
globs['os'] = os
globs['sc'] = sc
globs['sqlContext'] = SQLContext(sc)
globs['rdd'] = rdd = sc.parallelize(
[Row(field1=1, field2="row1"),
Row(field1=2, field2="row2"),
Row(field1=3, field2="row3")]
)
globs['df'] = rdd.toDF()
jsonStrings = [
'{"field1": 1, "field2": "row1", "field3":{"field4":11}}',
'{"field1" : 2, "field3":{"field4":22, "field5": [10, 11]},'
'"field6":[{"field7": "row2"}]}',
'{"field1" : null, "field2": "row3", '
'"field3":{"field4":33, "field5": []}}'
]
globs['jsonStrings'] = jsonStrings
globs['json'] = sc.parallelize(jsonStrings)
(failure_count, test_count) = doctest.testmod(
pyspark.sql.context, globs=globs,
optionflags=doctest.ELLIPSIS | doctest.NORMALIZE_WHITESPACE)
globs['sc'].stop()
if failure_count:
exit(-1)
def _test():
import doctest
import os
import tempfile
import py4j
from pyspark.context import SparkContext
from pyspark.sql import SparkSession, Row
import pyspark.sql.readwriter
os.chdir(os.environ["SPARK_HOME"])
globs = pyspark.sql.readwriter.__dict__.copy()
sc = SparkContext('local[4]', 'PythonTest')
try:
spark = SparkSession.builder.enableHiveSupport().getOrCreate()
except py4j.protocol.Py4JError:
spark = SparkSession(sc)
globs['tempfile'] = tempfile
globs['os'] = os
globs['sc'] = sc
globs['spark'] = spark
globs['df'] = spark.read.parquet('python/test_support/sql/parquet_partitioned')
(failure_count, test_count) = doctest.testmod(
pyspark.sql.readwriter, globs=globs,
optionflags=doctest.ELLIPSIS | doctest.NORMALIZE_WHITESPACE | doctest.REPORT_NDIFF)
sc.stop()
if failure_count:
exit(-1)
def _test():
import doctest
import os
import tempfile
from pyspark.sql import Row, SparkSession, SQLContext
import pyspark.sql.streaming
os.chdir(os.environ["SPARK_HOME"])
globs = pyspark.sql.streaming.__dict__.copy()
try:
spark = SparkSession.builder.getOrCreate()
except py4j.protocol.Py4JError:
spark = SparkSession(sc)
globs['tempfile'] = tempfile
globs['os'] = os
globs['spark'] = spark
globs['sqlContext'] = SQLContext.getOrCreate(spark.sparkContext)
globs['sdf'] = \
spark.readStream.format('text').load('python/test_support/sql/streaming')
globs['sdf_schema'] = StructType([StructField("data", StringType(), False)])
globs['df'] = \
globs['spark'].readStream.format('text').load('python/test_support/sql/streaming')
(failure_count, test_count) = doctest.testmod(
pyspark.sql.streaming, globs=globs,
optionflags=doctest.ELLIPSIS | doctest.NORMALIZE_WHITESPACE | doctest.REPORT_NDIFF)
globs['spark'].stop()
if failure_count:
exit(-1)
def _test():
import doctest
from pyspark.context import SparkContext
globs = globals().copy()
# The small batch size here ensures that we see multiple batches,
# even in these small test examples:
globs['sc'] = SparkContext('local[4]', 'PythonTest')
(failure_count, test_count) = doctest.testmod(
globs=globs, optionflags=doctest.ELLIPSIS)
globs['sc'].stop()
if failure_count:
exit(-1)
def _test():
import doctest
from pyspark.sql import SparkSession
import pyspark.mllib.evaluation
globs = pyspark.mllib.evaluation.__dict__.copy()
spark = SparkSession.builder\
.master("local[4]")\
.appName("mllib.evaluation tests")\
.getOrCreate()
globs['sc'] = spark.sparkContext
(failure_count, test_count) = doctest.testmod(globs=globs, optionflags=doctest.ELLIPSIS)
spark.stop()
if failure_count:
exit(-1)
def _test():
import doctest
from pyspark.sql import SparkSession
globs = globals().copy()
spark = SparkSession.builder\
.master("local[4]")\
.appName("mllib.stat.statistics tests")\
.getOrCreate()
globs['sc'] = spark.sparkContext
(failure_count, test_count) = doctest.testmod(globs=globs, optionflags=doctest.ELLIPSIS)
spark.stop()
if failure_count:
exit(-1)
def _test():
import doctest
from pyspark.sql import SparkSession
import pyspark.mllib.classification
globs = pyspark.mllib.classification.__dict__.copy()
spark = SparkSession.builder\
.master("local[4]")\
.appName("mllib.classification tests")\
.getOrCreate()
globs['sc'] = spark.sparkContext
(failure_count, test_count) = doctest.testmod(globs=globs, optionflags=doctest.ELLIPSIS)
spark.stop()
if failure_count:
exit(-1)
def _test():
import doctest
globs = globals().copy()
from pyspark.sql import SparkSession
spark = SparkSession.builder\
.master("local[4]")\
.appName("mllib.tree tests")\
.getOrCreate()
globs['sc'] = spark.sparkContext
(failure_count, test_count) = doctest.testmod(globs=globs, optionflags=doctest.ELLIPSIS)
spark.stop()
if failure_count:
exit(-1)
def _test():
import doctest
from pyspark.sql import SparkSession
globs = globals().copy()
spark = SparkSession.builder\
.master("local[4]")\
.appName("mllib.feature tests")\
.getOrCreate()
globs['sc'] = spark.sparkContext
(failure_count, test_count) = doctest.testmod(globs=globs, optionflags=doctest.ELLIPSIS)
spark.stop()
if failure_count:
exit(-1)
def _test():
import doctest
from pyspark.sql import SparkSession
globs = globals().copy()
# The small batch size here ensures that we see multiple batches,
# even in these small test examples:
spark = SparkSession.builder\
.master("local[2]")\
.appName("mllib.random tests")\
.getOrCreate()
globs['sc'] = spark.sparkContext
(failure_count, test_count) = doctest.testmod(globs=globs, optionflags=doctest.ELLIPSIS)
spark.stop()
if failure_count:
exit(-1)
def _test():
import doctest
(failure_count, test_count) = doctest.testmod(optionflags=doctest.ELLIPSIS)
if failure_count:
exit(-1)
def _test():
import doctest
import pyspark.mllib.recommendation
from pyspark.sql import SQLContext
globs = pyspark.mllib.recommendation.__dict__.copy()
sc = SparkContext('local[4]', 'PythonTest')
globs['sc'] = sc
globs['sqlContext'] = SQLContext(sc)
(failure_count, test_count) = doctest.testmod(globs=globs, optionflags=doctest.ELLIPSIS)
globs['sc'].stop()
if failure_count:
exit(-1)
def additional_tests():
import doctest, unittest
suite = unittest.TestSuite((
doctest.DocFileSuite(
os.path.join('tests', 'api_tests.txt'),
optionflags=doctest.ELLIPSIS, package='pkg_resources',
),
))
if sys.platform == 'win32':
suite.addTest(doctest.DocFileSuite('win_script_wrapper.txt'))
return suite
def test_suite():
"""Discover all tests in the tests dir"""
test_loader = unittest.TestLoader()
# Read in unit tests
test_suite = test_loader.discover('tests')
# Doctest all md and rst files
for root, dirs, files in os.walk("."):
for f in files:
if f.endswith(".rst") or f.endswith(".md"):
test_suite.addTests(
doctest.DocFileSuite(os.path.join(root, f),
optionflags=doctest.ELLIPSIS))
return test_suite
def test_suite():
import doctest
return doctest.DocFileSuite(
'README.txt',
optionflags=doctest.ELLIPSIS|doctest.REPORT_ONLY_FIRST_FAILURE,
)
def loadTestsFromModule(self, module):
#print '*** ipdoctest - lTM',module # dbg
if not self.matches(module.__name__):
log.debug("Doctest doesn't want module %s", module)
return
tests = self.finder.find(module,globs=self.globs,
extraglobs=self.extraglobs)
if not tests:
return
# always use whitespace and ellipsis options
optionflags = doctest.NORMALIZE_WHITESPACE | doctest.ELLIPSIS
tests.sort()
module_file = module.__file__
if module_file[-4:] in ('.pyc', '.pyo'):
module_file = module_file[:-1]
for test in tests:
if not test.examples:
continue
if not test.filename:
test.filename = module_file
yield DocTestCase(test,
optionflags=optionflags,
checker=self.checker)
def additional_tests():
import doctest, unittest
suite = unittest.TestSuite((
doctest.DocFileSuite(
os.path.join('tests', 'api_tests.txt'),
optionflags=doctest.ELLIPSIS, package='pkg_resources',
),
))
if sys.platform == 'win32':
suite.addTest(doctest.DocFileSuite('win_script_wrapper.txt'))
return suite
def additional_tests():
import doctest, unittest
suite = unittest.TestSuite((
doctest.DocFileSuite(
os.path.join('tests', 'api_tests.txt'),
optionflags=doctest.ELLIPSIS, package='pkg_resources',
),
))
if sys.platform == 'win32':
suite.addTest(doctest.DocFileSuite('win_script_wrapper.txt'))
return suite