本文整理汇总了Python中pysparkling.Context.saveAsTextFile方法的典型用法代码示例。如果您正苦于以下问题：Python Context.saveAsTextFile方法的具体用法？Python Context.saveAsTextFile怎么用？Python Context.saveAsTextFile使用的例子？那么恭喜您, 这里精选的方法代码示例或许可以为您提供帮助。您也可以进一步了解该方法所在类pysparkling.Context的用法示例。
在下文中一共展示了Context.saveAsTextFile方法的7个代码示例，这些例子默认根据受欢迎程度排序。您可以为喜欢或者感觉有用的代码点赞，您的评价将有助于系统推荐出更棒的Python代码示例。
示例1: test_hdfs_file_exists
# 需要导入模块: from pysparkling import Context [as 别名]
# 或者: from pysparkling.Context import saveAsTextFile [as 别名]
def test_hdfs_file_exists():
random.seed()
fn1 = '{}/pysparkling_test_{:d}.txt'.format(
HDFS_TEST_PATH, random.random() * 999999.0)
fn2 = '{}/pysparkling_test_{:d}.txt'.format(
HDFS_TEST_PATH, random.random() * 999999.0)
rdd = Context().parallelize('Hello World {0}'.format(x) for x in range(10))
rdd.saveAsTextFile(fn1)
assert File(fn1).exists() and not File(fn2).exists()示例2: test_gs_textFile_loop
# 需要导入模块: from pysparkling import Context [as 别名]
# 或者: from pysparkling.Context import saveAsTextFile [as 别名]
def test_gs_textFile_loop():
random.seed()
fn = '{}/pysparkling_test_{:d}.txt'.format(
GS_TEST_PATH, random.random() * 999999.0)
rdd = Context().parallelize('Line {0}'.format(n) for n in range(200))
rdd.saveAsTextFile(fn)
rdd_check = Context().textFile(fn)
assert (
rdd.count() == rdd_check.count() and
all(e1 == e2 for e1, e2 in zip(rdd.collect(), rdd_check.collect()))
)示例3: test_hdfs_textFile_loop
# 需要导入模块: from pysparkling import Context [as 别名]
# 或者: from pysparkling.Context import saveAsTextFile [as 别名]
def test_hdfs_textFile_loop():
random.seed()
fn = '{}/pysparkling_test_{:d}.txt'.format(
HDFS_TEST_PATH, random.random() * 999999.0)
print('HDFS test file: {0}'.format(fn))
rdd = Context().parallelize('Hello World {0}'.format(x) for x in range(10))
rdd.saveAsTextFile(fn)
read_rdd = Context().textFile(fn)
print(rdd.collect())
print(read_rdd.collect())
assert (
rdd.count() == read_rdd.count() and
all(r1 == r2 for r1, r2 in zip(rdd.collect(), read_rdd.collect()))
)示例4: test_hdfs_textFile_loop
# 需要导入模块: from pysparkling import Context [as 别名]
# 或者: from pysparkling.Context import saveAsTextFile [as 别名]
def test_hdfs_textFile_loop():
if not HDFS_TEST_PATH:
raise SkipTest
random.seed()
fn = HDFS_TEST_PATH+'/pysparkling_test_{0}.txt'.format(
int(random.random()*999999.0)
)
rdd = Context().parallelize('Hello World {0}'.format(x) for x in range(10))
rdd.saveAsTextFile(fn)
read_rdd = Context().textFile(fn)
assert (
rdd.count() == read_rdd.count() and
all(r1 == r2 for r1, r2 in zip(rdd.collect(), read_rdd.collect()))
)示例5: test_hdfs_file_exists
# 需要导入模块: from pysparkling import Context [as 别名]
# 或者: from pysparkling.Context import saveAsTextFile [as 别名]
def test_hdfs_file_exists():
if not HDFS_TEST_PATH:
raise SkipTest
random.seed()
fn1 = HDFS_TEST_PATH+'/pysparkling_test_{0}.txt'.format(
int(random.random()*999999.0)
)
fn2 = HDFS_TEST_PATH+'/pysparkling_test_{0}.txt'.format(
int(random.random()*999999.0)
)
rdd = Context().parallelize('Hello World {0}'.format(x) for x in range(10))
rdd.saveAsTextFile(fn1)
assert File(fn1).exists() and not File(fn2).exists()示例6: test_s3_textFile_loop
# 需要导入模块: from pysparkling import Context [as 别名]
# 或者: from pysparkling.Context import saveAsTextFile [as 别名]
def test_s3_textFile_loop():
if not AWS_ACCESS_KEY_ID or not S3_TEST_PATH:
raise SkipTest
random.seed()
fn = S3_TEST_PATH+'/pysparkling_test_{0}.txt'.format(
int(random.random()*999999.0)
)
rdd = Context().parallelize("Line {0}".format(n) for n in range(200))
rdd.saveAsTextFile(fn)
rdd_check = Context().textFile(fn)
assert (
rdd.count() == rdd_check.count() and
all(e1 == e2 for e1, e2 in zip(rdd.collect(), rdd_check.collect()))
)示例7: test_gs_textFile_loop
# 需要导入模块: from pysparkling import Context [as 别名]
# 或者: from pysparkling.Context import saveAsTextFile [as 别名]
def test_gs_textFile_loop():
if not OAUTH2_CLIENT_ID or not GS_TEST_PATH:
raise SkipTest
random.seed()
fn = '{}/pysparkling_test_{0}.txt'.format(
GS_TEST_PATH, int(random.random() * 999999.0)
)
rdd = Context().parallelize("Line {0}".format(n) for n in range(200))
rdd.saveAsTextFile(fn)
rdd_check = Context().textFile(fn)
assert (
rdd.count() == rdd_check.count() and
all(e1 == e2 for e1, e2 in zip(rdd.collect(), rdd_check.collect()))
)